Next Article in Journal
The Role of Ultrasound in Accessing the Distal Radial Artery at the Anatomical Snuffbox for Cardiovascular Interventions
Previous Article in Journal
RNA Foci Formation in a Retinal Glial Model for Spinocerebellar Ataxia Type 7
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:

Artificial Intelligence and Precision Medicine: A New Frontier for the Treatment of Brain Tumors

Anil K. Philip
Betty Annie Samuel
Saurabh Bhatia
Shaden A. M. Khalifa
3 and
Hesham R. El-Seedi
School of Pharmacy, University of Nizwa, Birkat Al Mouz, Nizwa 616, Oman
Natural and Medical Science Research Center, University of Nizwa, Birkat Al Mouz, Nizwa 616, Oman
Department of Molecular Biosciences, The Wenner-Gren Institute, Stockholm University, S-106 91 Stockholm, Sweden
International Research Center for Food Nutrition and Safety, Jiangsu University, Zhenjiang 212013, China
Pharmacognosy Group, Department of Pharmaceutical Biosciences, BMC, Uppsala University, SE-751 24 Uppsala, Sweden
International Joint Research Laboratory of Intelligent Agriculture and Agri-Products Processing, Jiangsu Education Department, Jiangsu University, Nanjing 210024, China
Authors to whom correspondence should be addressed.
Life 2023, 13(1), 24;
Submission received: 14 November 2022 / Revised: 8 December 2022 / Accepted: 19 December 2022 / Published: 22 December 2022


Brain tumors are a widespread and serious neurological phenomenon that can be life- threatening. The computing field has allowed for the development of artificial intelligence (AI), which can mimic the neural network of the human brain. One use of this technology has been to help researchers capture hidden, high-dimensional images of brain tumors. These images can provide new insights into the nature of brain tumors and help to improve treatment options. AI and precision medicine (PM) are converging to revolutionize healthcare. AI has the potential to improve cancer imaging interpretation in several ways, including more accurate tumor genotyping, more precise delineation of tumor volume, and better prediction of clinical outcomes. AI-assisted brain surgery can be an effective and safe option for treating brain tumors. This review discusses various AI and PM techniques that can be used in brain tumor treatment. These new techniques for the treatment of brain tumors, i.e., genomic profiling, microRNA panels, quantitative imaging, and radiomics, hold great promise for the future. However, there are challenges that must be overcome for these technologies to reach their full potential and improve healthcare.

1. Introduction

Brain tumors are a common form of cancer that can affect critical brain regions, often leading to cancer-related deaths (2.3%) [1]. According to the World Health Organization (WHO), glioblastoma, a tumor (grade IV) of the central nervous system (CNS), accounts for more than 60% of adult brain tumors [2]. Radiation therapy is a common treatment for glioblastoma, but it can have negative side effects, such as weakening the blood-brain barrier (BBB), making patients more susceptible to brain metastases [3]. For example, there have been reports of secondary brain tumors following radiation therapy for glioblastoma [4]. The process of metastasis is complex, involving multiple biological hurdles that tumor cells must overcome before they can establish themselves as metastatic lesions. Furthermore, the development of cancer treatments becomes more challenging when faced with intratumor heterogeneity, or the variation of genetic makeup within a tumor [5]. Use of brain-inspired computing could help simplify cancer management by providing a way to mimic the neural network of the human brain [6]. AI in healthcare can help to diagnose brain tumors [7] through the use of brain scans. In one study, AI was able to correctly identify 98% of brain tumors [8]. Machine learning algorithms applied to medical images can help to extract hidden features that human experts may not be able to discern. This can improve the accuracy of cancer diagnosis, prognosis, and treatment plans [9]. For example, in a study, deep learning technology was used on 1991 healthy samples and 12 cancer types showing an accuracy of 94.70% in identifying cancer [10].
The National Academy of Medicine states that AI technology in healthcare may offer benefits such as increased access to specialist healthcare and reduced human limitations [11]. A recent study found that AI-assisted surgery led to fewer complications and shorter hospital stays [12]. The use of AI in healthcare is growing rapidly. Global AI in the healthcare market is expected to grow to $150 billion by 2026 [13]. This growth is being driven by the increasing digitization of healthcare data [14], the improved ability of AI to analyze these data, and the potential benefits of AI in healthcare, such as early detection of disease, improved diagnosis, treatment recommendations, and personalized medicine [15]. AI is playing an increasingly important role in small-molecule drug discovery and development. AI is expected to play a major role in target selection, hit identification, and lead optimization in the near future [16]. For example, when eToxPred (a machine learning-based approach) was applied to estimate the toxicity and synthesis feasibility of small organic molecules, it showed accuracy as high as 72% [17]. Studies have shown that image-based diagnostic systems that use AI can often outperform clinicians. AI is able to more accurately recognize patterns and structures, which leads to more accurate diagnoses [18]. AI systems will improve with time based on real-life scenarios, feedback, and knowledge [19]. PM is an emerging medical model that uses a person’s genetic and molecular makeup to guide decisions about which medical treatments will work best for them [20]. The model has been used since the late 1990s to help select and customize treatments for individual patients with cancer [21]. The term “precision” in medicine and public health is becoming prevalent [22], and also involves medicines guided by molecules [23] or person-centred medicine [24], and provides evidence-based precise medical services [25]. PM is used in many fields, including clinical and preventive medicine [26,27]. PM identifies groups of patients benefiting from different treatment approaches using multiple data types [28], including data on a patient’s genes, environment, and lifestyle, enhancing patient health outcomes [29]. The information received from this approach can support PM in practice by helping to locate research related to a patient, and clinical trials [30].
Cancers are difficult to treat in patients due to a variety of reasons, including intra-tumoral heterogeneity and plasticity. Heterogeneity can make it difficult for drugs to target all of the cancer cells, and plasticity can allow cancer cells to become resistant to drugs over time [31,32]. Additionally, the presence of different subpopulations of cells within a tumor can cause the tumor to be dependent on these different cell groups for continued growth [33], and is therefore the main reason for treatment failures in cancer [32]. Intratumoral heterogeneity can be due to microenvironmental, genetic, and epigenetic factors [34]. Although we do not understand intratumoral heterogeneity very well [35], by understanding cellular subtypes and their development, cells can be targeted with PM [36]. Individualizing PM treatment must account for the patient’s cancer cells, genetic profile, and brain structure, especially when it comes to gliomas—a type of brain tumor that can be difficult to diagnose and treat. A new AI model created by researchers has the potential to be useful for diagnosing gliomas, as it can distinguish between urine samples from cancer patients and non-cancer patients. This model could be helpful for physicians in diagnosing and individualizing PM treatment for glioma patients [37,38]. Additionally, proteomics can provide a way to examine gliomas using fluid-based biomarkers [39]. This can help in understanding variations within this type of cancer, and potentially lead to better treatment options [40,41]. However, PM faces challenges due to the involvement of patient data, which includes data for disease, population diversity, and ethical reflections [42].

1.1. Molecular and Genomic Profiling of Brain Tumors and the Use of PM

Care of cancer patients can involve molecular profiling to choose the best treatment option [43] by finding gene mutations that may contribute to the disease, and targeting drugs that work best for that patient’s individual genetic makeup [44]. However, this method overlooks important molecular features that could have clinical significance [45], namely, prediction of drug-target group [46], molecular fingerprint representation [47], profile-to-cell line matchmaking [48], and drug-target interactions [49]. This method uses tissue biopsies to identify potential predictors of sensitivity and resistance [50]. If AI could correctly predict whether a tumor is benign or malignant, it could help doctors avoid performing unnecessary and potentially risky biopsies on patients. Studies have shown that AI can accurately predict whether a brain tumor is benign or malignant [51] with 95% accuracy [52], which would avoid the need for biopsy [53]. PM initiatives are a step forward in cancer treatment, but they come with challenges. Tumor tissue is difficult to work with, and other diagnostic and therapeutic methods are needed to overcome these challenges [54].
Molecular profiling of tumors can provide information on the specific genetic alterations present in the tumor, which can be used to guide treatment decisions. This has led to the development of targeted cancer therapies and the restructuring of clinical trials. Cancer is being treated at the molecular level by understanding the genetic profiles of tumors. The information can be used by clinicians to diagnose and treat cancer patients [55]. Cancer patients with brain tumors and metastases have not responded well to immunotherapy in the past [56]. A study found that immunotherapy and targeted therapy based on PM can treat brain metastases [57]. Genomic and molecular profiling of tumors reveals the function of tumor-derived genetic markers [58,59]. A study relating tumor biology with circulating tumor DNA (tDNA) levels was conducted and showed that patients with solid tumors had genomic alterations detected by plasma tDNA assay. The study supports the use of a genomic tumor profiling assay to detect genomic alterations in plasma tDNA from patients with active tumors [60]. Gene expression arrays (used in melanoma classifications) [61], and next-generation sequencing (NGS) are helping physicians determine how patients will respond to a particular therapy. These arrays and NGS will advance gene profiling technology to develop patient-specific treatments [62,63]. PM is very effective in treating some types of brain tumors, such as glioblastoma [64], using photodynamic therapy (PDT) [65]. Several approaches to overcome the challenges of implementing PM in glioblastoma have been reported, and integrated sequencing strategies have provided new insights into the molecular classifications and genomic landscape of several types of cancer [66]. The personalized PM service will use the microbiome, advanced clinical phenotyping (measurement of physical characteristics), diagnostics, advanced genomic imaging, and personalized genomics to enable PM [67,68,69]. Cancer immunotherapies targeting immune checkpoints are effective in enhancing immunity [70]. Immunotherapies for cancer patients can be improved by recognizing neoantigens and targeting them. Neoantigens are antigens that originate from somatic mutations. These mutated proteins located in tumor cells trigger a T-cell immune response [71]. PM can identify the type of brain tumor and the most effective treatment [72]. This may benefit patients with rare cancers that do, or cancers that do not, respond well to conventional treatments [73]. A study published in Nature reported that PM targets mutations in the IDH1 gene, which improves survival rates for patients with brain tumors [74]. Furthermore, PM targets genes for brain-specific [75] marker of metastasis [76] to provide an effective means to target cancer cells. Targeting reduces the risk of harming healthy brain tissue. With PM, patients will receive the best possible care and potential problems will be prevented [22].
Project management is a key part of developing new drugs and promoting the use of PMs in healthcare settings to improve patient care. PMs play a crucial role in many different settings, but their impact is especially significant when it comes to developing new treatments for specific types of cancer [77]. Deep learning is a new medical technology that is helping doctors save lives and improve patient outcomes. However, it is also creating new ethical dilemmas and raising questions about access to this information [78]. Deep learning is a branch of machine learning that employs algorithms to figure out high-level concepts from data. Machine learning, on the other hand, works on developing computer programs that have the ability to access data and interpret them. The biggest distinction between deep learning and machine learning is the level of abstraction it uses. Machine learning algorithms focus on low-level patterns present in data, while deep learning algorithms focus on high-level abstractions. There are several advantages of deep learning compared to traditional machine learning technologies. For example, deep learning typically results in fewer false positives per individual compared to traditional machine learning, indicating greater accuracy [79]. Researching human genetics has allowed for more precise cancer treatments through the usage of targeted drugs. For example, Zhao et al., describes an integrative analysis that indicates 13% of patients benefit from current targeted therapy based on gene mutation, and the proportion increases to 31% when drug repositioning is considered [80]. By identifying the gene responsible for cancer, researchers are able to target it with available drugs. However, a challenge that often arises is gene mutation, which can happen over the lifetime of a tumor. This makes it more difficult to predict which treatments would be the most effective. Another obstacle is that the gene mutation may be unique to an individual, making it difficult to create generalized detection tools [81].
It is challenging to recruit patients for PM studies due to the heterogeneity of the population. Informed consent is also an issue, as parents and patients may not fully understand the implications of participating in such a study [82]. Figure 1 [78] represents the attrition of patients during the process of genomic profiling to drug matching [83]. As can be seen, a large number of patients (30%) are lost between the initial stages of recruitment and the final stage of drug matching [17].
Informatics systems could simplify the recruitment process for clinical trials in PM by integrating genomic data and eligibility for clinical trials. This would allow for more accurate and efficient recruitment, as well as reducing the overall time and cost associated with clinical trials [84,85,86]. It is difficult to develop and study biomarkers due to the complexity of tumor heterogeneity. Another potential issue that can affect the precision of biomarkers is sampling bias [87]. Furthermore, due to the diversity of brain tumors, tissue banks are difficult to use for PM with respect to proper representation of the removed diseased area [88]. Thus, due to clonal development in brain tumors, it is important to look at many portions of the tumor [89]. The challenge of PM is predicting which tumors will respond to standard therapy and which will not. This may require the use of an angiogenesis inhibitor for tumors that do not respond to standard therapy [90,91]. Targeted drugs cannot change how a tumor forms, but they might be able to improve a person’s quality of life, according to some studies. However, there is disagreement among researchers as to whether targeted drugs are effective in cancer treatment, posing another obstacle to developing these drugs [92,93].

1.2. MicroRNA (miRNA) Panels as Markers in Brain Tumors

Brain tumors are often characterized by their expression of miRNAs [94]. The expression of miRNAs may provide information on tumor biology and the effect of therapeutic interventions [95]. MiRNAs can be tumor suppressors or promoters due to dysregulation in different types of cancer [96]. Additionally, miRNA can serve as a marker for non-invasive early detection of brain tumors [97]. A study carried out in 2170 patients with glioma and 1456 participants (healthy) in China supported earlier findings of the use of miRNAs as a marker for the detection of glioma [98]. A study, conducted in 31 people aged 61.1 to 62.9 years, analyzed miRNA expression levels in serum exosomes from cancer patients. The study found that hsa-miR-576-3p (small non-coding RNAs of 20–22 nucleotides) is a useful biomarker for predicting brain metastases in patients with breast cancer [99]. Some of these miRNAs may indicate a poor prognosis, while others may be associated with a better outcome [100]. MiRNAs may be useful markers for cancer diagnosis and monitoring. A prognostic [101] and diagnostic marker [102] can be found in up-regulation of miR-21. Various miRNA panels are potential markers for diagnosis, tumor grade, and prognosis [103]. Detection of diffuse glioma can be simplified by the use of miRNA. Furthermore, miRNA can differentiate primary CNS lymphoma from glioblastoma [104].
MiRNAs could be key targets for treating brain tumors, and may also help make tumors more sensitive to radiation therapy [105]. However, the role of miRNAs in biological processes (such as cell cycle, proliferation, apoptosis, and differentiation) needs to be carefully evaluated before using them as therapeutic targets [106]. Research is progressing on miRNA-based therapies for treating inflammatory diseases [107]. The safety of miRNA- based therapies can be ensured by developing nanocarrier-based platforms, which can also deliver miRNA-based therapies in a controlled and cell-specific manner [108]. Table 1 represents some relevant studies on the role of miRNAs in the oncogenesis of glioblastoma.

2. AI in Brain Tumor Imaging

The rapid growth of the AI industry, with substantial investment from technology firms, has outpaced expectations. Investing in AI projects [115,116], especially those related to medicine, is becoming increasingly popular [117]. The brain tumor diagnostics market is expected to grow rapidly in the coming years. The market was valued at $844.63 million in 2021 and is expected to reach $2476.14 million by 2028, growing at a compound annual growth rate (CAGR) of 16.6% from 2021 to 2028 [118]. AI helps doctors make better decisions by using complex computation and reasoning to help make decisions [11]. In medicine, AI is used for automated diagnostic procedures and treatments for patients [119]. An AI-based approach to cancer imaging can help improve tumor detection and characterization, as well as monitor the tumor’s response to treatment and check for early signs of cancer in other parts of the body [120].
Radiologists can find brain tumors quickly and effectively by using computer-aided diagnosis systems. These systems make use of supervised or unsupervised machine learning, transfer learning, or deep neural models (Xception model), all of which have been successful in the medical field thus far. AI and deep learning are expected to continue having breakthroughs in the future [121]. Molecular imaging provides the framework for new developments in the diagnosis of brain tumors. This technology allows for the visualization of molecular processes in the brain, which can provide critical information for diagnosis and treatment [122]. AI-based imaging algorithms (CXR-vision model, LIDC-IDRI model, LUNA16 model, and the CT-based volumetric analysis) have proven to be effective in diagnosing various cancers such as lung cancer [123], breast cancer (Mirai), and brain tumors [124]. Brain tumors have unique biological features which can be exploited by certain MRI sequences. T1-weighted images taken after gadolinium administration show enhanced areas where the blood-brain barrier has been breached, allowing gadolinium to enter the tumor from the intravascular space [125]. Orthogonal wavelet transforms and deep learning techniques are being used for the detection and classification of brain tumors [126]. A deep wavelet autoencoder (DWAE) model is being used to predict the location of a brain tumor based on the analysis of multimodal data such as MRI images, perfusion MRI images and PET scans. Furthermore, the combination of a DWAE model with a support vector machine helps the model learn the distribution of tumor volumes within the brain, and predict the classification of a tumor based on its volume [127].
Medical image segmentation is the process of partitioning a digital image into multiple segments (sets of pixels). The goal of segmentation is to simplify and/or change the representation of an image into something that is more meaningful and easier to analyze [128]. One important task in medical image processing is segmenting brain tumors from MRI scans. This helps doctors better understand the size and location of the tumor, as well as how it has changed over time. Deep learning-based segmentation of brain tumors is a popular method because it is automated and provides cutting-edge results [129]. For example, the deep capsule network (CapsNet) and latent-dynamic condition random field (LDCRF) can be used to segment brain tumors automatically. In contrast, a study of deep learning-based methods for detecting small tumors found that these methods were often inaccurate, resulting in misclassifications [130]. To better understand the human brain, doctors and researchers look for abnormalities. A study suggests that through finding these abnormalities and targeting them specifically, customized treatments for metastatic brain tumors (MBT) could be possible. This is in addition to the ability of MBT to provide a personalized diagnosis through its molecular expression profile. Furthermore, approximately 20–40% of MBT cases showed loss of DNA (MGMT) expression, highlighting the usefulness of this method. Another strength of MBT is that it expresses a variety of receptor and signal transduction molecules. This could potentially allow for individualized treatment using molecule-targeted drugs [131].

2.1. Quantitative Imaging of Brain Tumors

Magnetic resonance tomography (MRT), computed tomography (CT), and positron emission tomography (PET) are imaging techniques that are used to determine the location and size of a brain tumor. CT, MRT, and PET scans require contrast agents to produce clear images of the tumor [132]. The transcapillary transport of water-soluble compounds can be measured by PET methods in vivo. The PET method helps to understand brain tumors and their response to therapy. PET scans are also useful for determining the size and location of a tumor, which can aid in surgical planning [133]. PET scans are a valuable tool for studying the biology of brain tumors and could improve our understanding of brain tumors [134] by identifying areas of high metabolism that may be linked to tumor growth [135]. 18F-Fluorodeoxyglucose PET can be used to predict the prognosis of a patient and to distinguish nonmalignant from malignant lesions. 18F-Fluoroethyltyrosine, 11C-methionine, and 18F-L-3,4-dihydroxyphenylalanine are all high sensitivity markers that can be used to detect recurrent or residual cancer [136]. 3D-U-Net convolutional neural networks (CNNs) have been used to segment gliomas from 18-fluoroethyl-tyrosine PET scans. The CNNs showed high accuracy, with 78% positive prediction, 99% negative prediction, 88% sensitivity, and 99% specificity [137]. AMT-PET scanning identifies primary and metastatic brain tumors with 90% accuracy. This could advance the diagnosis and treatment of patients with metastatic brain tumors. Machine learning trained on MRIs predicts brain tumor outcomes better than established methods [138]. Brain MRI characterizes and visualizes the structure of interest in medical imaging. An AI-based automated method has been proposed that uses a classifier to identify and segment pathological tissue, such as tumors and atrophy, on brain MRI [139]. Aptamers are often used in PET research due to their high binding affinity and specificity. Aptamers can be easily labelled with radioisotopes, which allows researchers to study how molecules interact with each other [140]. Reduced fluorescence emission from brain tumors can be up to 50% lower than surrounding normal brain tissue, making tissue autofluorescence ideal for distinguishing between normal and tumor-affected brains. This technique is beneficial because it is noninvasive and can provide accurate results. Autofluorescence imaging has been used to successfully detect and map brain tumors in human patients [141].
Cancer is caused by uncontrolled cell division. Pathology is the key to understanding and diagnosing cancer [142,143]. Therefore, it is essential to obtain an accurate diagnosis to determine the best treatment plan [144]. That is why ultrasounds need image classification and object recognition algorithms that use deep learning to obtain precise results. These AI technologies include convolutional neural networks and recurrent neural networks. These algorithms have helped to examine medical images of various malignant neoplasms, such as brain tumors [145,146]. The rapid and noninvasive diagnosis of brain tumors is becoming increasingly popular [147]. This is in part due to the difficulty in diagnosing gliomas using MRI alone, and the possibility of irreversible errors. AI algorithms can help streamline this process and make it more accurate [148].

2.2. Radiomics in Brain Tumor Diagnosis

A precise diagnosis is essential for cancer treatment planning and predicting patient outcomes. Tumor classification and post-treatment response assessment are both improved when a precise diagnosis is made. In 2016, the WHO released an updated classification of brain tumors that integrated information on genetics [149]. Qualitative markers, such as tumor density and enhancement pattern, are used in conventional radiographic evaluation of tumors. In a study, it was shown that radiomics allowed for radiographic images to be digitally decoded to quantitative properties, which could then be used to distinguish between low-grade and high-grade gliomas [150]. Images fed into big data analytical tools provide information on tumor biology and therapeutic response [151]. Radiomics is the study of how medical images can be used to extract quantitative features that can be used to predict clinical outcomes [152]. Currently, there are no standard assessments of scientific integrity and clinical relevance [153]. Radiomics provides valuable information on tumor responses to therapy by incorporating AI into the glioblastoma multiforme (GBM) assessment of tumors using data from images. Radiomics uses sophisticated image analysis methods, such as diffusion and perfusion imaging, to provide accurate diagnosis and treatment of GBM [154]. Deep radiomic characteristics demonstrated markedly better precision (p < 0.05), with an AUC of 89.15%, compared to 78.07% for standard radiomic characteristics, for short and long-term survival prediction in patients with recurrent GBM [155]. Radiomics based on deep learning needs larger datasets to achieve better results due to the strong correlation between the extracted features and the input data. However, the limited availability of the dataset prevents radiomic implementation in many research areas. On the contrary, one technique that avoids this constraint is transfer learning. Transfer learning uses pre-trained neural networks for training interrelated purposes. For example, a neural network trained on imaging data to segment gliomas can be used for segmentation of brain metastases [149]. In one study, the researchers identified a signature of 11 radiographic characteristics to predict both survival and stratification in patients with newly diagnosed glioblastoma. The radiomic signature demonstrated improved performance over established radiological and clinical risk models [156]. Radiomics continues to integrate oncology, radiology, and machine learning, and is growing rapidly. In the future, radiomics will play an important role in precision diagnostics and oncology due to the ever-increasing clinical data and advances in machine learning methods. To improve the acceptability of radiomics, reproducibility and interpretability should be the focus. As per a study, radiomics can improve the accuracy of cancer diagnosis by up to 20% [157].
Radiogenomics (‘imaging genomics’) is a rapidly growing field that studies the relationship of genomic features of a disease to imaging biomarkers. In an earlier study, unsupervised learning algorithms and a knowledge based unsupervised fuzzy clustering approach, which is a type of algorithm, were discussed [125]. This new field is enabled by a three-way combination of textural, functional, and morphological signatures that are derived from high-throughput quantitative metrics extraction of MR images at the voxel level. The clinical application of radiogenomics is limited by the heterogeneity of brain tumors. Spatial and temporal heterogeneity can result in adverse clinical outcomes. Current cancer treatments work uniformly in tumors regardless of spatial or temporal variation in cancer cell behavior and survival. Performing whole tumor analysis by radiogenomics can address this limitation [158]. In response to modern chemotherapy/immunotherapy and radiation therapy, radiomics and radiogenomics show promise in providing accurate diagnosis, prediction of prognosis, and evaluation of tumor response.

2.3. Convolutional Neural Networks for Clinical Diagnostics

Different CNN architectures can be trained more quickly and accurately by using a combination of CNNs and stochastic gradient optimization algorithms. Emerging AI approaches, such as neural networks, deep learning, and CNN, help to retrieve important clinical data. These clinical data can be used for treatment planning and post-treatment monitoring [159]. By developing a fast and stable convergence method, it is possible to reduce the amount of time and resources needed to tune the momentum hyperparameters in popular CNN optimizers. This could improve the classification of images used in medical diagnostics [160]. CNNs can solve the problem of computer-aided diagnosis [161]. Ker et al., used a CNN to classify brain histological samples into high or low-grade glioma with 98% and 100% accuracy, respectively [162]. A demonstration by Havaei et al., showed that a CNN was 30 times faster and more precise than cutting-edge segmenting platforms [79]. Deep CNNs can extract significant features with high accuracy from GBM histopathology images [163]. With continuous improvements in the prediction of the accuracy of the system, deep CNNs can be a powerful clinical tool for the early detection and management of GBM. Raman spectroscopy probes have recently been used to find brain tumors in real time during surgery. This technology can detect diseased tissues up to a millimeter deep because it collects high-quality signals rapidly [164]. This ability is beneficial in neurosurgical procedures [165]. It can detect tumor margins and give surgeons immediate feedback on whether tumor cells are still present [166]. Clinical data shows that tumor classification based on a combination of 3D CNN characteristics is highly accurate and can improve clinical outcomes by facilitating the selection of the most appropriate treatment regimen for patients [167].

3. Future of AI in Brain Tumor

Although AI technologies have changed diagnostic radiology a lot, there are many areas that still need improvement. These areas include AI applied to detect, segment, and classify brain tumors, which would make patient care better [168]. The recent integration of an AI system into the clinical workflow indicates that AI can be used to improve clinical care [169]. AI can be used for early diagnosis of gliomas in the absence of visual contrast; however, there is currently a lack of high-quality image data which limits its potential. A future step in AI development and imaging technologies is to recognize pre-metastatic niches. The early detection of these niches provides an accurate assessment of a patient’s probability to develop metastatic or micrometastatic disease. AI applications can be divided into two categories: (1) upstream AI applications that concern operational analytics, and (2) downstream AI applications that are focused on the imaging data themselves [170]. Improvement in the accuracy and efficiency of AI applications is possible by combining different types of annotations. A distinction like this can be limiting because it prevents different annotation types from being combined. This will increase the interest in and supervision of medical image analysis [171]. AI in neurology has a promising future because it has the potential to predict seizures [172] and grade brain tumors [173]. The model was significantly improved when it was used to segment brain tumors on MR images. This was done by multitasking with global labels and local annotations [174]. The researchers showed that AI algorithms can accurately segment intracranial hemorrhages on brain CT images and measure hemorrhage volumes. The device could be used to detect and measure head and neck vascular tumors or malformations [175]. AI has the potential to provide significant advances in the accurate interpretation of cancer imaging, including extrapolation of the tumor genotype, volumetric delineation over time, and prediction of clinical outcome based on the phenotype of its radiographic appearance [151].

4. Challenges for Using AI with Brain Tumors

Brain gliomas are one of the most difficult cancers to detect and classify [176]. Gliomas are often small and difficult to see on imaging tests, and their symptoms can be vague and mimic other conditions. Deep learning and machine learning have the potential to change the diagnosis of glioma in the future [147]. AI is becoming increasingly popular in smart healthcare [177,178]. A significant barrier healthcare providers face is the lack of resources and investment in information technology. Another is the lack of training on how to use big data. Big data can be analyzed using sophisticated methods that are designed to handle the volume, variety, and velocity of big data. An intelligent tutoring system or process-oriented e-learning system can help train personnel in big data. Additionally, there are concerns about data security and privacy [179], for example access control models and privacy-preserving protocols. Centralized AI is being used by healthcare providers to overcome the issue of not having enough data to train machine learning models. However, it may be difficult to transfer sensitive patient information from hospitals to these processing centers, as this requires a lot of time and resources. This could then limit inter-center research cooperation [179]. Instead, healthcare institutions could use federated learning to collaborate with each other. Federated learning is a machine learning technique that trains an algorithm across multiple decentralized edge devices or servers holding local data. This offers a way to unlock information without anyone seeing or touching the data. Federated learning would allow different healthcare providers to keep their sensitive data private while still being able to train machine learning models on shared data. Despite some progress, brain tumor research still has many limitations. A challenge has been grading tumors by human interpretation of images. This process involves some subjectivity in the classification of tumor grade based on morphology and the person interpreting the images. Therefore, a more accurate diagnosis can be sought through an automated image analytic process, which will assist in a quantitatively objective classification process for brain tumors [180]. Emerging AI methods have shown great promise for medical imaging in radiology [149].

5. Conclusions

The use of AI as a support tool in cancer intervention and prevention strategies has shown promising results. AI-assisted brain tumor surgery can result in safer and more effective treatment. By integrating clinical, radiological, and molecular markers, AI has the potential to significantly improve patient care. Recent developments in PM have emphasized targeted therapies and customized treatment techniques. Although the large-scale implementation of AI and PM in brain tumor treatment is facing challenges, the tremendous pace at which they are getting developed holds a great promise to remarkable progress in the outcomes.

Author Contributions

Conceptualization, A.K.P. and B.A.S., data curation, A.K.P. and B.A.S., methodology A.K.P. and B.A.S.; supervision, A.K.P. and H.R.E.-S., writing—original draft preparation, A.K.P., B.A.S., S.B., S.A.M.K. and H.R.E.-S., writing—review and editing, A.K.P., B.A.S., S.B., S.A.M.K. and H.R.E.-S.; All authors have read and agreed to the published version of the manuscript.


This research received no external funding.


The authors would like to thank the University of Nizwa, Oman for the facilities provided. H. El-Seedi highly appreciates and thanks the Plan of High-end Foreign Experts of the Ministry of Science and Technology (G2022016009L).

Conflicts of Interest

The authors report no conflict of interest.


  1. Alnaami, I.; Sarhan, L.; Alqahtani, A.; Alghamdi, A.; Alkhashrami, S.; Mostafa, O. Does brain tumor epidemiology differ from place to another? Saudi single tertiary care center experience. Biomed. Res. 2018, 29, 2982–2987. [Google Scholar] [CrossRef] [Green Version]
  2. Chang, J.; Guo, C.; Li, J.; Liang, Z.; Wang, Y.; Yu, A.; Liu, R.; Guo, Y.; Chen, J.; Huang, S. EN1 regulates cell growth and proliferation in human glioma cells via Hedgehog signaling. Int. J. Mol. Sci. 2022, 23, 1123. [Google Scholar] [CrossRef] [PubMed]
  3. Chevli, N.; Hunt, A.; Haque, W.; Farach, A.M.; Messer, J.A.; Sukpraprut-Braaten, S.; Bernicker, E.H.; Zhang, J.; Butler, E.B.; Teh, B.S. Time Interval to Initiation of Whole-Brain Radiation Therapy in Patients With Small Cell Lung Cancer With Brain Metastasis. Adv. Rad. Oncol. 2021, 6, 100783. [Google Scholar] [CrossRef] [PubMed]
  4. Wang, Y.; Song, S.; Su, X.; Wu, J.; Dai, Z.; Cui, D.; Reng, Y.; Fan, J.; Shen, Y.; Wu, Q.; et al. Radiation-induced glioblastoma with rhabdoid characteristics following treatment for medulloblastoma: A case report and review of the literature. Mol. Clin. Oncol. 2018, 9, 415–418. [Google Scholar] [CrossRef] [PubMed]
  5. de Sousa e Melo, F.; Vermeulen, L.; Fessler, E.; Medema, J.P. Cancer heterogeneity-a multifaceted view. EMBO Rep. 2013, 14, 686–695. [Google Scholar] [CrossRef] [Green Version]
  6. Zhu, X.; Sun, Y.; Liu, H.; Li, Q.; Xu, H. Simulation of the spiking neural network based on practical memristor. MATEC Web Conf. 2018, 173, 1–4. [Google Scholar] [CrossRef]
  7. Shoeibi, A.; Khodatars, M.; Alizadehsani, R.; Ghassemi, N.; Jafari, M.; Moridian, P.; Khadem, A.; Sadeghi, D.; Hussain, S.; Zare, A.; et al. Automated detection and forecasting of COVID-19 using deep learning techniques: A review. arXiv 2020, arXiv:2007.10785. [Google Scholar] [CrossRef]
  8. Mittal, A.; Kumar, D. Ai CNNs (Artificially-integrated convolutional neural networks) for brain tumor prediction. PHAT 2019, 17, e5. [Google Scholar] [CrossRef]
  9. Jian, A.; Liu, S.; Ieva, A.D. Artificial intelligence for survival prediction in brain tumors on neuroimaging. Neurosurgery 2022, 91, 8–26. [Google Scholar] [CrossRef]
  10. Sun, Y.; Zhu, S.; Ma, K.; Liu, W.; Yue, Y.; Hu, G.; Lu, H.; Chen, W. Identification of 12 cancer types through genome deep learning. Sci. Rep. 2019, 9, 17256. [Google Scholar] [CrossRef]
  11. Johnson, K.B.; Wei, W.Q.; Weeraratne, D.; Frisse, M.E.; Misulis, K.; Rhee, K.; Zhao, J.; Snowdon, J.L. Precision medicine, AI, and the future of personalized health care. Clin. Transl. Sci. 2020, 14, 86–93. [Google Scholar] [CrossRef] [PubMed]
  12. Nwoye, E.O.; Woo, W.L.; Gao, B.; Anyanwu, T. Artificial intelligence for emerging technology in surgery: Systematic review and validation. IEEE Rev. Biomed. Eng. 2022, 16, 1–22. [Google Scholar] [CrossRef]
  13. Owoyemi, A.; Owoyemi, J.; Osiyemi, A.; Boyd, A. Artificial Intelligence for Healthcare in Africa. Front. Digit. Health 2020, 2, 6. [Google Scholar] [CrossRef] [PubMed]
  14. Soellner, M.; Koenigstorfer, J. Compliance with medical recommendations depending on the use of artificial intelligence as a diagnostic method. BMC Med. Inform. Decis. Mak. 2021, 21, 236. [Google Scholar] [CrossRef]
  15. Carrillo-Perez, F.; Pecho, O.E.; Morales, J.C.; Paravina, R.D.; Bona, A.D.; Ghinea, R.; Pulgar, R.; del Mar Pérez, M.; Herrera, L.J. Applications of artificial intelligence in dentistry: A comprehensive review. J. Esthet. Restor. Dent. 2021, 34, 259–280. [Google Scholar] [CrossRef] [PubMed]
  16. Sahoo, A.; Dar, G.M. A comprehensive review on the application of artificial intelligence in drug discovery. Appl. Biol. Chem. J. 2021, 2, 34–48. [Google Scholar] [CrossRef]
  17. Paul, D.; Sanap, G.; Shenoy, S.; Kalyane, D.; Kalia, K.; Tekade, R.K. Artificial intelligence in drug discovery and development. Drug Discov. Today 2021, 26, 80–93. [Google Scholar] [CrossRef]
  18. Barinov, L.; Jairaj, A.; Becker, M.D.; Seymour, S.; Lee, E.; Schram, A.W.; Lane, E.; Goldszal, A.F.; Quigley, D.; Paster, L. Impact of data presentation on physician performance utilizing artificial intelligence-based computer-aided diagnosis and decision support systems. J. Digit. Imaging 2019, 32, 408–416. [Google Scholar] [CrossRef] [Green Version]
  19. Karnuta, J.M.; Luu, B.C.; Haeberle, H.S.; Saluan, P.M.; Frangiamore, S.J.; Stearns, K.L.; Farrow, L.D.; Nwachukwu, B.U.; Verma, N.N.; Makhni, E.C.; et al. Machine learning outperforms regression analysis to predict next-season major league baseball player injuries: Epidemiology and validation of 13, 982 player-years from performance and injury profile trends, 2000–2017. Orthop. J. Sport. Med. 2020, 8, 2325967120963046. [Google Scholar] [CrossRef]
  20. Bohr, A.; Memarzadeh, K. The rise of artificial intelligence in healthcare applications. In Artificial Intelligence in Healthcare; Academic Press: Cambridge, MA, USA, 2020; pp. 25–60. [Google Scholar] [CrossRef]
  21. Lee, M.S.; Flammer, A.J.; Lerman, L.O.; Lerman, A. Personalized medicine in cardiovascular diseases. Korean Circ. J. 2012, 42, 583. [Google Scholar] [CrossRef] [Green Version]
  22. Chowkwanyun, M.; Bayer, R.; Galea, S. Public health-between novelty and hype. N. Engl. J. Med. 2018, 379, 1398–1400. [Google Scholar] [CrossRef] [PubMed]
  23. Lloyd, K.C.K.; Khanna, C.; Hendricks, W.; Trent, J.; Kotlikoff, M. Precision medicine: An opportunity for a paradigm shift in veterinary medicine. J. Am. Vet. Med. Assoc. 2016, 248, 45–48. [Google Scholar] [CrossRef] [PubMed] [Green Version]
  24. Amedei, A.; Boem, F. I’ve Gut A Feeling: Microbiota impacting the conceptual and experimental perspectives of personalized medicine. Int. J. Mol. Sci. 2018, 19, 3756. [Google Scholar] [CrossRef] [Green Version]
  25. Gourraud, P.A.; Henry, R.G.; Cree, B.A.C.; Crane, J.C.; Lizee, A.; Olson, M.P.; Santaniello, A.V.; Datta, E.; Zhu, A.H.; Bevan, C.J.; et al. Precision medicine in chronic disease management: The multiple sclerosis BioScreen. Ann. Neurol. 2014, 76, 633–642. [Google Scholar] [CrossRef] [Green Version]
  26. Leopold, J.A.; Maron, B.A.; Loscalzo, J. The application of big data to cardiovascular disease: Paths to precision medicine. J. Clin. Investig. 2020, 130, 29–38. [Google Scholar] [CrossRef]
  27. Narimatsu, H. Gene interactions in preventive medicine: Current status and expectations for the future. Int. J. Mol. Sci. 2017, 18, 302. [Google Scholar] [CrossRef] [PubMed] [Green Version]
  28. Vargas, A.J.; Harris, C.C. Biomarker development in the precision medicine era: Lung cancer as a case study. Nat. Rev. Cancer 2016, 16, 525–537. [Google Scholar] [CrossRef]
  29. Simmons, M.; Singhal, A.; Lu, Z. Text mining for precision medicine: Bringing structure to EHRs and biomedical literature to understand genes and health. Adv. Exp. Med. Biol. 2016, 939, 139–166. [Google Scholar] [CrossRef] [Green Version]
  30. Roberts, K.; Demner-Fushman, D.; Voorhees, E.M.; Hersh, W.R.; Bedrick, S.; Lazar, A.J.; Pant, S. Overview of the TREC 2020 precision medicine track. Text Retr. Conf. 2020, 1266, 1–10. [Google Scholar]
  31. Lauko, A.J.; Lo, A.; Ahluwalia, M.S.; Lathia, J.D. Cancer cell heterogeneity & plasticity in glioblastoma and brain tumors. Semin. Cancer Biol. 2022, 82, 162–175. [Google Scholar] [CrossRef]
  32. Schmelz, K.; Toedling, J.; Huska, M.R.; Cwikla, M.C.; Kruetzfeldt, L.M.; Proba, J.; Ambros, P.F.; Ambros, I.M.; Boral, S.; Lodrini, M.; et al. Spatial and temporal intratumour heterogeneity has potential consequences for single biopsy-based neuroblastoma treatment decisions. Nat. Commun. 2021, 12, 6804. [Google Scholar] [CrossRef] [PubMed]
  33. Pribluda, A.; de la Cruz, C.C.; Jackson, E.L. Intratumoral heterogeneity: From diversity comes resistance. Clin. Cancer Res. 2015, 21, 2916–2923. [Google Scholar] [CrossRef] [PubMed] [Green Version]
  34. Patel, H.; Nilendu, P.; Jahagirdar, D.; Pal, J.K.; Sharma, N.K. Modulating secreted components of tumor microenvironment: A masterstroke in tumor therapeutics. Cancer Biol. Ther. 2017, 19, 3–12. [Google Scholar] [CrossRef] [PubMed]
  35. Woldu, S.L.; Amatruda, J.F.; Bagrodia, A. Testicular germ cell tumor genomics. Curr. Opin. Urol. 2017, 27, 41–47. [Google Scholar] [CrossRef]
  36. Tu, S.M.; Bilen, M.A.; Hess, K.R.; Broaddus, R.R.; Kopetz, S.; Wei, C.; Pagliaro, L.C.; Karam, J.A.; Ward, J.F.; Wood, C.G.; et al. Intratumoral heterogeneity: Role of differentiation in a potentially lethal phenotype of testicular cancer. Cancer 2016, 122, 1836–1843. [Google Scholar] [CrossRef]
  37. Ghiaseddin, A.; Minh, L.B.H.; Janiszewska, M.; Shin, D.; Wick, W.; Mitchell, D.A.; Wen, P.Y.; Grossman, S.A. Adult precision medicine: Learning from the past to enhance the future. Neurooncol. Adv. 2020, 3, vdaa145. [Google Scholar] [CrossRef] [PubMed]
  38. Carpenter, C.D.; Alnahhas, I.; Gonzalez, J.; Giglio, P.; Puduvalli, V.K. Changing Paradigms for Targeted Therapies against Diffuse Infiltrative Gliomas: Tackling a Moving Target. Expert Rev. Neurother. 2019, 19, 663–677. [Google Scholar] [CrossRef]
  39. Wu, J.; Zhang, J.; Wei, J.; Zhao, Y.; Gao, Y. Urinary biomarker discovery in gliomas using mass spectrometry-based clinical proteomics. Chin. Neurosurg. J. 2020, 6, 11. [Google Scholar] [CrossRef] [Green Version]
  40. Pantel, K.; Alix-Panabières, C. Liquid biopsy and minimal residual disease—Latest advances and implications for cure. Nat. Rev. Clin. Oncol. 2019, 16, 409–424. [Google Scholar] [CrossRef]
  41. Sheng, Z.; Yu, J.; Deng, K.; Andrade-Barazarte, H.; Zemmar, A.; Li, S.; Li, N.; Yan, Z.; Chen, Z.; Sun, Y.; et al. Characterizing the genomic landscape of brain glioma with circulating tumor DNA from tumor in situ fluid. Front. Oncol. 2021, 11, 584988. [Google Scholar] [CrossRef]
  42. Molinari, C.; Marisi, G.; Passardi, A.; Matteucci, L.; De Maio, G.; Ulivi, P. Heterogeneity in colorectal cancer: A challenge for personalized medicine? Int. J. Mol. Sci. 2018, 19, 3733. [Google Scholar] [CrossRef] [PubMed] [Green Version]
  43. Schork, N.J. Personalized medicine: Time for one-person trials. Nature 2015, 520, 609–611. [Google Scholar] [CrossRef] [PubMed] [Green Version]
  44. Deluche, E.; Onesti, E.; Andre, F. Precision medicine for metastatic breast cancer. Am. Soc. Clin. Oncol. Educ. Book 2015, 35, e2–e7. [Google Scholar] [CrossRef] [PubMed] [Green Version]
  45. Kuderer, N.M.; Burton, K.A.; Blau, S.; Senecal, F.; Gadi, V.K.; Parker, S.; Mahen, E.; Veenstra, D.; Carlson, J.J.; Lyman, G.H.; et al. Participant attitudes toward an intensive trial of multiple biopsies, multidimensional molecular analysis, and reporting of results in metastatic triple-negative breast cancer. JCO Precis. Oncol. 2017, 1, 1–13. [Google Scholar] [CrossRef]
  46. Che, J.Y.; Chen, L.; Guo, Z.H.; Wang, S.; Aorigele. Drug target group prediction with multiple drug networks. Comb. Chem. High Throughput Screen. 2020, 23, 274–284. [Google Scholar] [CrossRef]
  47. Zagidullin, B.; Wang, Z.; Guan, Y.; Pitkänen, E.; Tang, J. Comparative analysis of molecular fingerprints in prediction of drug combination effects. Brief. Bioinform. 2021, 22, bbab291. [Google Scholar] [CrossRef]
  48. Reardon, B.; Van Allen, E.M. Molecular Profile to Cancer Cell Line Matchmaking. 2021. Available online: (accessed on 2 December 2022).
  49. Udrescu, L.; Bogdan, P.; Chis¸, A.; Sirbu, I.O.; Topirceanu, A.; Varu¸t, R.M.; Udrescu, M. Uncovering new drug properties in target-based drug-drug similarity networks. Pharmaceutics 2020, 12, 879. [Google Scholar] [CrossRef]
  50. McNeil, C. NCI-MATCH launch highlights new trial design in precision-medicine era. J. Nat. Cancer Inst. 2015, 107, djv193. [Google Scholar] [CrossRef]
  51. Goyal, H.; Mann, R.; Gandhi, Z.; Perisetti, A.; Ali, A.; Ali, K.A.; Sharma, N.; Saligram, S.; Tharian, B.; Inamdar, S. Scope of artificial intelligence in screening and diagnosis of colorectal cancer. J. Clin. Med. Res. 2020, 9, 3313. [Google Scholar] [CrossRef]
  52. Minato, J.; Tokunaga, H.; Okamoto, S.; Shibuya, Y.; Niikura, H.; Yaegashi, N. Is imprint cytology useful to diagnose malignancy for Brenner tumors? A case series at a single institute. Acta Cytol. 2017, 61, 153–159. [Google Scholar] [CrossRef]
  53. Cruz, J.; López-Yáñez, I.; Argüelles-Cruz, A.J.; Marquez, C. Risk detection of malignant tumors in mammograms using unconventional computing. Res. Comp. Sci. 2014, 78, 55–66. [Google Scholar] [CrossRef]
  54. Zhu, J.; Strickler, J.H. Clinical applications of liquid biopsies in gastrointestinal oncology. J. Gastrointest. Oncol. 2016, 7, 675–686. [Google Scholar] [CrossRef] [Green Version]
  55. Marron, J.M.; DuBois, S.G.; Bender, J.G.; Kim, A.; Crompton, B.D.; Meyer, S.C.; Janeway, K.A.; Mack, J.W. Patient/parent perspectives on genomic tumor profiling of pediatric solid tumors: The individualized cancer therapy (iCat) experience. Pediatr. Blood Cancer 2016, 63, 1974–1982. [Google Scholar] [CrossRef] [PubMed] [Green Version]
  56. Haughton, M.E.; Chan, M.D.; Watabe, K.; Bonomi, M.; Debinski, W.; Lesser, G.J.; Ruiz, J. Treatment of brain metastases of lung cancer in the era of precision medicine. Front. Biosci. 2016, 8, 219–232. [Google Scholar] [CrossRef]
  57. Chen, W.; Hoffmann, A.D.; Liu, H.; Liu, X. Organotropism: New insights into molecular mechanisms of breast cancer metastasis. NPJ Precis. Oncol. 2018, 2, 4. [Google Scholar] [CrossRef] [PubMed] [Green Version]
  58. Montero-Conde, C.; Graña-Castro, O.; Martín-Serrano, G.; Martínez-Montes, Á.M.; Zarzuela, E.; Muñoz, J.; Torres-Perez, R.; Pita, G.; Cordero-Barreal, A.; Leandro-García, L.J.; et al. Hsa-miR-139-5p is a prognostic thyroid cancer marker involved in HNRNPF-mediated alternative splicing. Int. J. Cancer 2019, 146, 521–530. [Google Scholar] [CrossRef]
  59. Blee, S.M.; Shah, R.P.; Pinheiro, A.P.; Switchenko, J.; Dixon, M.; Owonikoko, T.K.; Hill, C.E.; Szabo, S.M.; Pentz, R.D. Physician communication and patient understanding of molecular testing terminology. Oncologist 2021, 26, 934–940. [Google Scholar] [CrossRef]
  60. Zhou, C.; Yuan, Z.; Ma, W.; Qi, L.; Mahavongtrakul, A.; Li, Y.; Li, H.; Gong, J.; Fan, R.R.; Li, J.; et al. Clinical utility of tumor genomic profiling in patients with high plasma circulating tumor DNA burden or metabolically active tumors. J. Hematol. Oncol. 2018, 11, 129. [Google Scholar] [CrossRef]
  61. Sini, G.; Colombino, M.; Lissia, A.; Maxia, S.; Gulino, M.; Paliogiannis, P.; Palomba, G.; Palmieri, G.; Cossu, A.; Rubino, C. Primary dermal melanoma in a patient with a history of multiple malignancies: A case report with molecular characterization. Case Rep. Dermatol. 2013, 5, 192–197. [Google Scholar] [CrossRef]
  62. Nishimura, S.; Sugimoto, A.; Kushiyama, S.; Togano, S.; Kuroda, K.; Yamamoto, Y.; Yamauchi, M.; Sumi, T.; Kaneda, H.; Kawaguchi, T.; et al. Clinical benefit for clinical sequencing using cancer panel testing. PLoS ONE 2021, 16, e0247090. [Google Scholar] [CrossRef]
  63. Matsumura, Y.; Owada-Ozaki, Y.; Suzuki, H. Significance of testing for TP53 gene mutations in lung adenocarcinoma using targeted gene sequencing. J. Thorac. Dis. 2018, 10, 4147–4150. [Google Scholar] [CrossRef] [PubMed]
  64. Baptiste, M.; Moinuddeen, S.S.; Soliz, C.L.; Ehsan, H.; Kaneko, G. Making sense of genetic information: The promising evolution of clinical stratification and precision oncology using machine learning. Genes 2021, 12, 722. [Google Scholar] [CrossRef] [PubMed]
  65. Baydoun, M.; Moralès, O.; Frochot, C.; Ludovic, C.; Leroux, B.; Thecua, E.; Ziane, L.; Grabarz, A.; Kumar, A.; de Schutter, C.; et al. Photodynamic therapy using a new folate receptor-targeted photosensitizer on peritoneal ovarian cancer cells induces the release of extracellular vesicles with immunoactivating properties. J. Clin. Med. 2020, 9, 1185. [Google Scholar] [CrossRef]
  66. Prados, M.D.; Byron, S.A.; Tran, N.L.; Phillips, J.J.; Molinaro, A.M.; Ligon, K.L.; Wen, P.Y.; Kuhn, J.G.; Mellinghoff, I.K.; de Groot, J.F.; et al. Toward precision medicine in glioblastoma: The promise and the challenges. Neuro. Oncol. 2015, 17, 1051–1063. [Google Scholar] [CrossRef] [PubMed] [Green Version]
  67. Geifman, N.; Haviv, I.; Kurzrock, R.; Rubin, E. Promoting precision cancer medicine through a community-driven knowledge-base. J. Pers. Med. 2014, 4, 475–488. [Google Scholar] [CrossRef] [Green Version]
  68. Auffray, C.; Caulfield, T.; Griffin, J.L.; Khoury, M.J.; Lupski, J.R.; Schwab, M. From genomic medicine to precision medicine: Highlights of 2015. Genome Med. 2016, 8, 12. [Google Scholar] [CrossRef] [PubMed] [Green Version]
  69. Eden, C.; Johnson, K.W.; Gottesman, O.; Bottinger, E.P.; Abul-Husn, N.S. Medical student preparedness for an era of personalized medicine: Findings from one US medical school. Pers. Med. 2016, 13, 129–141. [Google Scholar] [CrossRef] [Green Version]
  70. Ye, P.; Chi, X.; Cha, J.H.; Luo, S.; Yang, G.; Yan, X.; Yang, W.H. Potential of e3 ubiquitin ligases in cancer immunity: Opportunities and challenges. Cells 2021, 10, 3309. [Google Scholar] [CrossRef]
  71. Kiyotani, K.; Toyoshima, Y.; Nakamura, Y. Personalized immunotherapy in cancer precision medicine. Cancer Biol. Med. 2021, 18, 955–965. [Google Scholar] [CrossRef]
  72. Aramini, B.; Masciale, V.; Banchelli, F.; D’Amico, R.; Dominici, M.; Husnain Haider, K. Precision medicine in lung cancer: Challenges and opportunities in diagnostic and therapeutic purposes. In Lung Cancer—Modern Multidisciplinary Management; Park, S.H., Ed.; IntechOpen: London, UK, 2021. [Google Scholar] [CrossRef]
  73. Costa, F.F. Basic research, applied medicine and EHRs—Are we on the right track? J. Cancer Sci. Ther. 2011, 3, i–ii. [Google Scholar] [CrossRef]
  74. Rubin, M.A. Health: Make precision medicine work for cancer care. Nature 2015, 520, 290–291. [Google Scholar] [CrossRef] [Green Version]
  75. Felsky, D.; Sariya, S.; Santa-Maria, I.; French, L.; Schneider, J.A.; Bennett, D.A.; Mayeux, R.; De Jager, P.L.; Tosto, G. The caribbean-hispanic alzheimer’s brain transcriptome reveals ancestry-specific disease mechanisms. Alzheimers Dement. 2020, 16, e043068. [Google Scholar] [CrossRef]
  76. Karadas, A.K.; Dilmac, S.; Aytac, G.; Tanriover, G. Melatonin decreases metastasis, primary tumor growth and angiogenesis in a mice model of breast cancer. Human Exp. Toxicol. 2021, 40, 1545–1557. [Google Scholar] [CrossRef] [PubMed]
  77. Pinker, K.; Chin, J.; Melsaether, A.N.; Morris, E.A.; Moy, L. Precision medicine and radiogenomics in breast cancer: New approaches toward diagnosis and treatment. Radiology 2018, 287, 732–747. [Google Scholar] [CrossRef] [PubMed]
  78. Agrawal, A.; McHale, J.; Oettl, A. Finding Needles in Haystacks: Artificial Intelligence and Recombinant Growth; National Bureau of Economic Research: Cambridge, MA, USA, 2018. [Google Scholar] [CrossRef]
  79. Williams, S.; Horsfall, H.L.; Funnell, J.P.; Hanrahan, J.G.; Khan, D.Z.; Muirhead, W.; Stoyanov, D.; Marcus, H.J. Artificial intelligence in brain tumour surgery-an emerging paradigm. Cancers 2021, 13, 5010. [Google Scholar] [CrossRef]
  80. Zhao, J.; Cheng, F.; Wang, Y.; Arteaga, C.L.; Zhao, Z. Systematic prioritization of druggable mutations in 5000 genomes across 16 cancer types using a structural genomics-based approach. Mol. Cell. Proteom. 2015, 15, 642–656. [Google Scholar] [CrossRef] [PubMed] [Green Version]
  81. Bai, R.; Lv, Z.; Chen, X.; Guo, H.; Bai, L.; Tian, H.; Li, W.; Cui, J. Precision detection technology: Equipping precision oncology with wings. J. Oncol. 2020, 2020, 9068121. [Google Scholar] [CrossRef] [PubMed]
  82. Lourenco, R.D.A.; McCarthy, M.C.; McMillan, L.J.; Sullivan, M.; Gillam, L. Understanding decisions to participate in genomic medicine in childrencancer care: A comparison of what influences parents, health care providers, and the general community. Pediatr. Blood Cancer 2021, 68, e29101. [Google Scholar] [CrossRef]
  83. Malone, E.R.; Oliva, M.; Sabatini, P.J.B.; Stockley, T.L.; Siu, L.L. Molecular profiling for precision cancer therapies. Genome Med. 2020, 12, 8. [Google Scholar] [CrossRef] [Green Version]
  84. Klein, H.; Mazor, T.; Siegel, E.; Trukhanov, P.; Ovalle, A.; Fitz, C.D.V.; Zwiesler, Z.; Kumari, P.; Van Der Veen, B.; Marriott, E.; et al. MatchMiner: An open-source platform for cancer precision medicine. NPJ Precis. Med. 2022, 6, 69. [Google Scholar] [CrossRef]
  85. Lopez-Chavez, A.; Thomas, A.; Rajan, A.; Raffeld, M.; Morrow, B.; Kelly, R.; Carter, C.A.; Guha, U.; Killian, K.; Lau, C.C.; et al. Molecular profiling and targeted therapy for advanced thoracic malignancies: A biomarker-derived, multiarm, multihistology phase ii basket trial. J. Clin. Oncol. 2015, 33, 1000–1007. [Google Scholar] [CrossRef] [PubMed]
  86. Redig, A.J.; Jänne, P.A. Basket trials and the evolution of clinical trial design in an era of genomic medicine. J. Clin. Oncol. 2015, 33, 975–977. [Google Scholar] [CrossRef] [PubMed] [Green Version]
  87. Sandhu, R.; Roll, J.D.; Rivenbark, A.G.; Coleman, W.B. Dysregulation of the epigenome in human breast cancer. Am. J. Pathol. 2015, 185, 282–292. [Google Scholar] [CrossRef] [PubMed]
  88. Sottoriva, A.; Spiteri, I.; Piccirillo, S.G.M.; Touloumis, A.; Collins, V.P.; Marioni, J.C.; Curtis, C.; Watts, C.; Tavaré, S. Intratumor heterogeneity in human glioblastoma reflects cancer evolutionary dynamics. Proc. Natl. Acad. Sci. USA 2013, 110, 4009–4014. [Google Scholar] [CrossRef] [PubMed] [Green Version]
  89. Snyder, J.; Poisson, L.M.; Noushmehr, H.; Castro, A.V.; deCarvalho, A.C.; Robin, A.; Mukherjee, A.; Lee, I.; Walbert, T. Clinical and research applications of a brain tumor tissue bank in the age of precision medicine. Per. Med. 2019, 16, 145–156. [Google Scholar] [CrossRef]
  90. Lambrechts, D.; Lenz, H.J.; de Haas, S.; Carmeliet, P.; Scherer, S.J. Markers of response for the antiangiogenic agent bevacizumab. J. Clin. Oncol. 2013, 31, 1219–1230. [Google Scholar] [CrossRef]
  91. Humbert, O.; Riedinger, J.M.; Vrigneaud, J.M.; Kanoun, S.; Dygai-Cochet, I.; Berriolo-Riedinger, A.; Toubeau, M.; Depardon, E.; Lassere, M.; Tisserand, S.; et al. 18F-fdg pet tumor blood flow changes after 1 cycle of neoadjuvant chemotherapy predicts outcome in triple-negative breast cancer. J. Nuc. Med. 2016, 57, 1707–1712. [Google Scholar] [CrossRef] [Green Version]
  92. Hunter, D.J. Uncertainty in the era of precision medicine. N. Engl. J. Med. 2016, 375, 711–713. [Google Scholar] [CrossRef]
  93. Zhang, X.; Yang, H.; Zhang, R. Challenges and future of precision medicine strategies for breast cancer based on a database on drug reactions. Biosci. Rep. 2019, 39, BSR20190230. [Google Scholar] [CrossRef] [Green Version]
  94. Xu, J.; Liao, X.; Wong, C. Downregulations of B-cell lymphoma 2 and myeloid cell leukemia sequence 1 by microRNA 153 induce apoptosis in a glioblastoma cell line DBTRG-05MG. Int. J. Cancer 2010, 126, 1029–1035. [Google Scholar] [CrossRef]
  95. Schwarzenbach, H.; Nishida, N.; Calin, G.A.; Pantel, K. Clinical relevance of circulating cell-free microRNAs in cancer. Nat. Rev. Clin. Oncol. 2014, 11, 145–156. [Google Scholar] [CrossRef] [PubMed]
  96. Shi, Y.; Liu, Z.; Lin, Q.; Luo, Q.; Cen, Y.; Li, J.; Fang, X.; Gong, C. MiRNAs and cancer: Key link in diagnosis and therapy. Genes 2021, 12, 1289. [Google Scholar] [CrossRef] [PubMed]
  97. Aalami, A.H.; Abdeahad, H.; Shoghi, A.; Mesgari, M.; Amirabadi, A.; Sahebkar, A. Brain tumors and circulating micrornas: A systematic review and diagnostic meta-analysis. Expert Rev. Mol. Diagn. 2021, 22, 201–211. [Google Scholar] [CrossRef]
  98. He, J.; Jiang, Y.; Liu, L.; Zuo, Z.; Zeng, C. Circulating micrornas as promising diagnostic biomarkers for patients with glioma: A meta-analysis. Front. Neurol. 2020, 11, 610163. [Google Scholar] [CrossRef]
  99. Curtaz, C.J.; Reifschläger, L.; Strähle, L.; Feldheim, J.; Feldheim, J.J.; Schmitt, C.; Kiesel, M.; Herbert, S.L.; Wöckel, A.; Meybohm, P.; et al. Analysis of micrornas in exosomes of breast cancer patients in search of molecular prognostic factors in brain metastases. Int. J. Mol. Sci. 2022, 23, 3683. [Google Scholar] [CrossRef]
  100. Eibl, R.H.; Schneemann, M. Liquid biopsy and primary brain tumors. Cancers 2021, 13, 5429. [Google Scholar] [CrossRef]
  101. Wang, Q.; Li, P.; Li, A.; Jiang, W.; Wang, H.; Wang, J.; Xie, K. Plasma specific miRNAs as predictive biomarkers for diagnosis and prognosis of glioma. J. Exp. Clin. Cancer Res 2012, 31, 97. [Google Scholar] [CrossRef] [PubMed] [Green Version]
  102. Siegal, T.; Charbit, H.; Paldor, I.; Zelikovitch, B.; Canello, T.; Benis, A.; Wong, M.L.; Morokoff, A.P.; Kaye, A.H.; Lavon, I. Dynamics of circulating hypoxia-mediated miRNAs and tumor response in patients with high-grade glioma treated with bevacizumab. J. Neurosur. 2016, 125, 1008–1015. [Google Scholar] [CrossRef] [PubMed]
  103. Ali, H.; Harting, R.; de Vries, R.; Ali, M.; Wurdinger, T.; Best, M.G. Blood-based biomarkers for glioma in the context of gliomagenesis: A systematic review. Front. Oncol. 2021, 11, 665235. [Google Scholar] [CrossRef]
  104. Ohno, M.; Matsuzaki, J.; Kawauchi, J.; Aoki, Y.; Miura, J.; Takizawa, S.; Kato, K.; Sakamoto, H.; Matsushita, Y.; Takahashi, M.; et al. Assessment of the diagnostic utility of serum microrna classification in patients with diffuse glioma. JAMA Netw. Open 2019, 2, e1916953. [Google Scholar] [CrossRef]
  105. Gareev, I.F.; Beylerli, O.; Liang, Y.; Xiang, H.; Liu, C.; Xu, X.; Yuan, C.; Ahmad, A.; Yang, G. The role of micrornas in therapeutic resistance of malignant primary brain tumors. Front. Cell Dev. Biol. 2021, 9, 740303. [Google Scholar] [CrossRef]
  106. Li, N.; Shi, H.; Zhang, L.; Li, X.; Gao, L.; Zhang, G.; Shi, Y.; Guo, S. MiR-188 Inhibits glioma cell proliferation and cell cycle progression through targeting β-catenin. Oncol. Res. Featur. Preclin. Clin. Cancer Ther. 2018, 26, 785–794. [Google Scholar] [CrossRef] [PubMed]
  107. Lu, Q.; Wu, R.; Zhao, M.; Garcia-Gomez, A.; Ballestar, E. miRNAs as therapeutic targets in inflammatory disease. Trends Pharmacol. Sci. 2019, 40, 853–865. [Google Scholar] [CrossRef] [PubMed]
  108. El-Sayed, S.R.; Cristante, J.; Guyon, L.; Denis, J.; Chabre, O.; Cherradi, N. MicroRNA therapeutics in cancer: Current advances and challenges. Cancers 2021, 13, 2680. [Google Scholar] [CrossRef] [PubMed]
  109. Papagiannakopoulos, T.; Friedmann-Morvinski, D.; Neveu, P.; Dugas, J.C.; Gill, R.M.; Huillard, E.; Liu, C.; Zong, H.; Rowitch, D.H.; Barres, B.A.; et al. Pro-neural miR-128 is a glioma tumor suppressor that targets mitogenic kinases. Oncogene 2012, 31, 1884–1895. [Google Scholar] [CrossRef] [Green Version]
  110. Mathew, L.K.; Skuli, N.; Mucaj, V.; Lee, S.S.; Zinn, P.O.; Sathyan, P.; Imtiyaz, H.Z.; Zhang, Z.; Davuluri, R.V.; Rao, S.; et al. miR-218 opposes a critical RTK-HIF pathway in mesenchymal glioblastoma. Proc. Natl. Acad. Sci. USA 2014, 111, 291–296. [Google Scholar] [CrossRef] [Green Version]
  111. Tomei, S.; Volontè, A.; Ravindran, S.; Mazzoleni, S.; Wang, E.; Galli, R.; Maccalli, C. MicroRNA expression profile distinguishes glioblastoma stem cells from differentiated tumor cells. J. Pers. Med. 2021, 11, 264. [Google Scholar] [CrossRef]
  112. Chen, M.; Medarova, Z.; Moore, A. Role of microRNAs in glioblastoma. Oncotarget 2021, 12, 1707–1723. [Google Scholar] [CrossRef]
  113. Aloizou, A.M.; Pateraki, G.; Siokas, V.; Mentis, A.F.A.; Liampas, I.; Lazopoulos, G.; Kovatsi, L.; Mitsias, P.D.; Bogdanos, D.P.; Paterakis, K.; et al. The role of MiRNA-21 in gliomas: Hope for a novel therapeutic intervention? Toxicol. Rep. 2020, 7, 1514–1530. [Google Scholar] [CrossRef]
  114. Min, R.Q.; Ma, Q. MicroRNA-381 inhibits metastasis and epithelial-mesenchymal transition of glioblastoma cells through targeting LEF1. Eur. Rev. Med. Pharmacol. Sci. 2020, 24, 6825–6833. [Google Scholar] [CrossRef]
  115. Kaswa, R.; Nair, A.; Murphy, S.; Von Pressentin, K.B. Artificial intelligence: A strategic opportunity for enhancing primary care in south africa. S. Afr. Fam. Pract. 2022, 64, a5596. [Google Scholar] [CrossRef] [PubMed]
  116. Matheny, M.E.; Whicher, D.; Israni, S.T. Artificial intelligence in health care: A report from the national academy of medicine. JAMA 2019, 323, 509–510. [Google Scholar] [CrossRef]
  117. Buch, V.H.; Ahmed, I.; Maruthappu, M. Artificial intelligence in medicine: Current trends and future possibilities. Br. J. Gen. Pract. 2018, 68, 143–144. [Google Scholar] [CrossRef] [PubMed] [Green Version]
  118. Research and Markets, Insights on the Brain Cancer Diagnostics Global Market to 2028—Increase in Prevalence of Brain Cancer Worldwide Is Driving Growth. Available online: (accessed on 3 December 2022).
  119. Battineni, G.; Sagaro, G.G.; Chinatalapudi, N.; Amenta, F. Applications of machine learning predictive models in the chronic disease diagnosis. J. Pers. Med. 2020, 10, 21. [Google Scholar] [CrossRef] [PubMed] [Green Version]
  120. Iuga, A.I.; Carolus, H.; Höink, A.J.; Brosch, T.; Klinder, T.; Maintz, D.; Persigehl, T.; Bae, B.; Püsken, M. Automated detection and segmentation of thoracic lymph nodes from CT using 3D foveal fully convolutional neural networks. BMC Med. Imaging 2021, 21, 69. [Google Scholar] [CrossRef] [PubMed]
  121. Asif, S.; Yi, W.; ul Ain, Q.; Hou, J.; Yi, T.; Si, J. Improving effectiveness of different deep transfer learning-based models for detecting brain tumors from mr images. IEEE Access 2022, 10, 34716–34730. [Google Scholar] [CrossRef]
  122. Sandu, N.; Schaller, B. Stem cell transplantation in brain tumors: A new field for molecular imaging? Mol. Med. 2010, 16, 433–437. [Google Scholar] [CrossRef] [Green Version]
  123. Zarzeczny, A.; Babyn, P.; Adams, S.J.; Longo, J. Artificial intelligence-based imaging analytics and lung cancer diagnostics: Considerations for health system leaders. Healthc. Manag. Forum 2020, 34, 169–174. [Google Scholar] [CrossRef]
  124. Liu, T.; Yuan, Z.; Wu, L.; Badami, B. Optimal brain tumor diagnosis based on deep learning and balanced sparrow search algorithm. Int. J. Imaging Syst. Technol. 2021, 31, 1921–1935. [Google Scholar] [CrossRef]
  125. Zhou, M.; Scott, J.; Chaudhury, B.; Hall, L.; Goldgof, D.; Yeom, K.W.; Iv, M.; Ou, Y.; Kalpathy-Cramer, J.; Napel, S.; et al. Radiomics in brain tumor: Image assessment, quantitative feature descriptors, and machine-learning approaches. Am. J. Neuroradiol. 2018, 39, 208–216. [Google Scholar] [CrossRef] [Green Version]
  126. Arif, M.; Ajesh, F.; Shamsudheen, S.; Geman, O.; Izdrui, D.; Vicoveanu, D. Brain tumor detection and classification by mri using biologically inspired orthogonal wavelet transform and deep learning techniques. J. Healthc. Eng. 2022, 2022, e2693621. [Google Scholar] [CrossRef] [PubMed]
  127. Kader, I.A.E.; Xu, G.; Shuai, Z.; Saminu, S.; Javaid, I.; Ahmad, I.S.; Kamhi, S. Brain tumor detection and classification on mr images by a deep wavelet auto-encoder model. Diagnostics 2021, 11, 1589. [Google Scholar] [CrossRef] [PubMed]
  128. Gui, L.; Li, C.; Yang, X. Medical image segmentation based on level set and isoperimetric constraint. Phys. Medica 2017, 42, 162–173. [Google Scholar] [CrossRef] [PubMed]
  129. Işın, A.; Direkoglu, C.; Şah, M. Review of MRI-based brain tumor image segmentation using deep learning methods. Procedia Comput. Sci. 2016, 102, 317–324. [Google Scholar] [CrossRef] [Green Version]
  130. Lee, J.; Shin, D.; Oh, S.H.; Kim, H. Method to minimize the errors of ai: Quantifying and exploiting uncertainty of deep learning in brain tumor segmentation. Sensors 2022, 22, 2406. [Google Scholar] [CrossRef]
  131. Kato, Y.; Nishihara, H.; Yuzawa, S.; Mohri, H.; Kanno, H.; Hatanaka, Y.; Kimura, T.; Tanino, M.; Tanaka, S. Immunohistochemical molecular expression profile of metastatic brain tumor for potent personalized medicine. Brain Tumor Pathol. 2012, 30, 167–174. [Google Scholar] [CrossRef] [Green Version]
  132. Krafft, C.; Rösch, P.; Popp, J. Raman Spectroscopy in Medicine. In digital Encyclopedia of Applied Physics; Wiley-VCH Verlag GmbH & Co. KGaA, Ed.; Wiley-VCH Verlag GmbH & Co. KGaA: Weinheim, Germany, 2009; p. 985. [Google Scholar] [CrossRef]
  133. Groothuis, D.R.; Lapin, G.D.; Vriesendorp, F.J.; Mikhael, M.A.; Patlak, C.S. A method to quantitatively measure transcapillary transport of iodinated compounds in canine brain tumors with computed tomography. J. Cereb. Blood Flow Metab. 1991, 11, 939–948. [Google Scholar] [CrossRef]
  134. Rhodes, C.S.; Zhang, H.; Patel, K.; Mistry, N.; Kwok, Y.; D’Souza, W.D.; Regine, W.F.; Gullapalli, R.P. The feasibility of integrating resting-state fmri networks into radiotherapy treatment planning. J. Med. Imaging Rad. Sci. 2019, 50, 119–128. [Google Scholar] [CrossRef] [Green Version]
  135. Apostolova, I.; Wedel, F.; Brenner, W. Imaging of tumor metabolism using positron emission tomography (pet). recent results in cancer research. Recent Results Cancer Res. 2016, 207, 177–205. [Google Scholar] [CrossRef]
  136. Herholz, K.; Langen, K.J.; Schiepers, C.; Mountz, J.M. Brain Tumors. Semin. Nucl. Med. 2012, 42, 356–370. [Google Scholar] [CrossRef] [Green Version]
  137. Blanc-Durand, P.; Gucht, A.V.D.; Schaefer, N.; Itti, E.; Prior, J.O. Automatic lesion detection and segmentation of 18F-FET PET in gliomas: A full 3D U-Net convolutional neural network study. PLoS ONE 2018, 13, e0195798. [Google Scholar] [CrossRef] [PubMed]
  138. Joe, N.S.; Hodgdon, C.; Kraemer, L.; Redmond, K.J.; Stearns, V.; Gilkes, D.M. A common goal to CARE: Cancer advocates, researchers, and clinicians explore current treatments and clinical trials for breast cancer brain metastases. NPJ Breast Cancer 2021, 7, 121. [Google Scholar] [CrossRef] [PubMed]
  139. Bhanumurthy, M.Y.; Anne, K. An automated detection and segmentation of tumor in brain MRI using artificial intelligence. In Proceedings of the 2014 IEEE International Conference on Computational Intelligence and Computing Research, Coimbatore, India, 18–20 December 2014; pp. 1–6. [Google Scholar] [CrossRef]
  140. Amero, P.; Khatua, S.; Rodriguez-Aguayo, C.; Lopez-Berestein, G. Aptamers: Novel therapeutics and potential role in neuro-oncology. Cancers 2020, 12, 2889. [Google Scholar] [CrossRef] [PubMed]
  141. Goujon, D.; Zellweger, M.; Radu, A.; Grosjean, P.; Weber, B.C.; van den Bergh, H.; Monnier, P.; Wagnier`es, G. In vivo autofluorescence imaging of early cancers in the human tracheobronchial tree with a spectrally optimized system. J. Biomed. Opt. 2003, 8, 17. [Google Scholar] [CrossRef]
  142. Majd, S.; Power, J.; Majd, Z. Alzheimer’s disease and cancer: When two monsters cannot be together. Front. Neurosci. 2019, 13, 155. [Google Scholar] [CrossRef] [PubMed] [Green Version]
  143. Hudáá, M.; Hamuá, S.; Konkoá, E.; Jendý, R.; Vargová, J.; Ševc, J.; Fedoro, P.; Soukup, O.; Janoá, J.; Ihnatova, V.; et al. Synthesis of new biscoumarin derivatives, in vitro cholinesterase inhibition, molecular modelling and antiproliferative effect in a549 human lung carcinoma cells. Int. J. Mol. Sci. 2021, 22, 3830. [Google Scholar] [CrossRef]
  144. Attia, N.M.; Sayed, S.A.A.; Riad, K.F.; Korany, G.M. Magnetic resonance spectroscopy in pediatric brain tumors: How to make a more confident diagnosis. Egypt. J. Rad. Nuc. Med. 2020, 51, 14. [Google Scholar] [CrossRef]
  145. Akatsuka, J.; Numata, Y.; Morikawa, H.; Sekine, T.; Kayama, S.; Mikami, H.; Yanagi, M.; Endo, Y.; Takeda, H.; Toyama, Y.; et al. A data-driven ultrasound approach discriminates pathological high grade prostate cancer. Sci. Rep. 2022, 12, 860. [Google Scholar] [CrossRef]
  146. Bulten, W.; Pinckaers, H.; van Boven, H.; Vink, R.; de Bel, T.; van Ginneken, B.; van der Laak, J.; Hulsbergen-van de Kaa, C.; Litjens, G. Automated deep-learning system for gleason grading of prostate cancer using biopsies: A diagnostic study. Lancet Oncol. 2020, 21, 233–241. [Google Scholar] [CrossRef] [Green Version]
  147. Khazaee, Z.; Langarizadeh, M.; Shiri Ahmadabadi, M.E. Developing an artificial intelligence model for tumor grading and classification, based on mri sequences of human brain gliomas. Int. J. Cancer Manag. 2022, 15, e120638. [Google Scholar] [CrossRef]
  148. Tandel, G.S.; Biswas, M.; Kakde, O.G.; Tiwari, A.; Suri, H.S.; Turk, M.; Laird, J.; Asare, C.; Ankrah, A.A.; Khanna, N.N.; et al. A review on a deep learning perspective in brain cancer classification. Cancers 2019, 11, 111. [Google Scholar] [CrossRef] [PubMed] [Green Version]
  149. Abdel Razek, A.A.K.; Alksas, A.; Shehata, M.; AbdelKhalek, A.; Abdel Baky, K.; El-Baz, A.; Helmy, E. Clinical applications of artificial intelligence and radiomics in neuro-oncology imaging. Insights Imaging 2021, 12, 152. [Google Scholar] [CrossRef] [PubMed]
  150. Cho, H.-H.; Park, H. Classification of low-grade and high-grade glioma using multi-modal image radiomics features. Annu. Int. Conf. IEEE Eng. Med. Biol. Soc. 2017, 2017, 3081–3084. [Google Scholar] [CrossRef]
  151. Bi, W.L.; Hosny, A.; Schabath, M.B.; Giger, M.L.; Birkbak, N.J.; Mehrtash, A.; Allison, T.; Arnaout, O.; Abbosh, C.; Dunn, I.F.; et al. Artificial Intelligence in Cancer Imaging: Clinical Challenges and Applications. CA Cancer J. Clin. 2019, 69, 127–157. [Google Scholar] [CrossRef] [Green Version]
  152. Spraker, M.B.; Wootton, L.S.; Hippe, D.S.; Ball, K.C.; Peeken, J.C.; Macomber, M.W.; Chapman, T.R.; Hoff, M.N.; Kim, E.Y.; Pollack, S.M.; et al. MRI radiomic features are independently associated with overall survival in soft tissue sarcoma. Adv. Radiat. Oncol. 2019, 4, 413–421. [Google Scholar] [CrossRef] [Green Version]
  153. Lambin, P.; Leijenaar, R.T.H.; Deist, T.M.; Peerlings, J.; de Jong, E.E.C.; van Timmeren, J.; Sanduleanu, S.; Larue, R.T.H.M.; Even, A.J.G.; Jochems, A.; et al. Radiomics: The bridge between medical imaging and personalized medicine. Nat. Rev. Clin. Oncol. 2017, 14, 749–762. [Google Scholar] [CrossRef]
  154. Gaddamanugu, S.; Shafaat, O.; Sotoudeh, H.; Sarrami, A.H.; Rezaei, A.; Saadatpour, Z.; Singhal, A. Clinical applications of diffusion-weighted sequence in brain imaging: Beyond stroke. Neuroradiology 2022, 64, 15–30. [Google Scholar] [CrossRef]
  155. Chaddad, A.; Zhang, M.; Desrosiers, C.; Niazi, T. Deep radiomic features from mri scans predict survival outcome of recurrent glioblastoma. In Proceedings of the Radiomics and Radiogenomics in Neurooncology; Mohy-ud-Din, H., Rathore, S., Eds.; Springer International Publishing: Cham, Switzerland, 2020; pp. 36–43. [Google Scholar] [CrossRef] [Green Version]
  156. Kickingereder, P.; Burth, S.; Wick, A.; Götz, M.; Eidel, O.; Schlemmer, H.P.; Maier-Hein, K.H.; Wick, W.; Bendszus, M.; Radbruch, A.; et al. Radiomic profiling of glioblastoma: Identifying an imaging predictor of patient survival with improved performance over established clinical and radiologic risk models. Radiology 2016, 280, 880–889. [Google Scholar] [CrossRef] [Green Version]
  157. Liu, Z.; Wang, S.; Dong, D.; Wei, J.; Fang, C.; Zhou, X.; Sun, K.; Li, L.; Li, B.; Wang, M.; et al. The applications of radiomics in precision diagnosis and treatment of oncology: Opportunities and challenges. Theranostics 2019, 9, 1303–1322. [Google Scholar] [CrossRef]
  158. Singh, G.; Manjila, S.; Sakla, N.; True, A.; Wardeh, A.H.; Beig, N.; Vaysberg, A.; Matthews, J.; Prasanna, P.; Spektor, V. Radiomics and radiogenomics in gliomas: A contemporary update. Br. J. Cancer 2021, 125, 641–657. [Google Scholar] [CrossRef]
  159. Sotoudeh, H.; Shafaat, O.; Bernstock, J.D.; Brooks, M.D.; Elsayed, G.A.; Chen, J.A.; Szerip, P.; Chagoya, G.; Gessler, F.; Sotoudeh, E.; et al. Artificial intelligence in the management of glioma: Era of personalized medicine. Front. Oncol. 2019, 9, 768. [Google Scholar] [CrossRef] [PubMed]
  160. Aytac, U.C.; Gunes, A.; Ajlouni, N. A novel adaptive momentum method for medical image classification using convolutional neural network. BMC Med. Imaging 2022, 22, 34. [Google Scholar] [CrossRef] [PubMed]
  161. Gao, J.; Jiang, Q.; Zhou, B.; Chen, D. Convolutional neural networks for computer-aided detection or diagnosis in medical image analysis: An overview. Math. Biosci. Eng. 2019, 16, 6536–6561. [Google Scholar] [CrossRef] [PubMed]
  162. Ker, J.; Bai, Y.; Lee, H.Y.; Rao, J.; Wang, L. Automated brain histology classification using machine learning. J. Clin. Neurosci. 2019, 66, 239–245. [Google Scholar] [CrossRef]
  163. Yonekura, A.; Kawanaka, H.; Prasath, V.B.S.; Aronow, B.J.; Takase, H. Automatic disease stage classification of glioblastoma multiforme histopathological images using deep convolutional neural network. Biomed. Eng. Lett. 2018, 8, 321–327. [Google Scholar] [CrossRef]
  164. Jermyn, M.; Mok, K.; Mercier, J.; Desroches, J.; Pichette, J.; Saint-Arnaud, K.; Bernstein, L.; Guiot, M.C.; Petrecca, K.; Leblond, F. Intraoperative brain cancer detection with raman spectroscopy in humans. Sci. Transl. Med. 2015, 7, 274ra219. [Google Scholar] [CrossRef]
  165. Shabestri, B.; Anastasio, M.A.; Fei, B.; Leblond, F. Special series guest editorial: Artificial intelligence and machine learning in biomedical optics. J. Biomed. Opt. 2021, 26, 052901. [Google Scholar] [CrossRef]
  166. Iakab, S.A.; Ràfols, P.; Correig-Blanchar, X.; García-Altares, M. Perspective on multimodal imaging techniques coupling mass spectrometry and vibrational spectroscopy: Picturing the best of both worlds. Anal. Chem. 2021, 93, 6301–6310. [Google Scholar] [CrossRef]
  167. Mzoughi, H.; Njeh, I.; Wali, A.; Slima, M.B.; BenHamida, A.; Mhiri, C.; Mahfoudhe, K.B. Deep multi-scale 3d convolutional neural network (cnn) for mri gliomas brain tumor classification. J. Digit. Imaging 2020, 33, 903–915. [Google Scholar] [CrossRef]
  168. Abd-Ellah, M.K.; Awad, A.I.; Khalaf, A.A.M.; Hamed, H.F.A. A review on brain tumor diagnosis from MRI images: Practical implications, key achievements, and lessons learned. Magn. Reason. Imaging 2019, 61, 300–318. [Google Scholar] [CrossRef]
  169. Juluru, K.; Shih, H.H.; Keshava Murthy, K.N.; Elnajjar, P.; El-Rowmeim, A.; Roth, C.; Genereaux, B.; Fox, J.; Siegel, E.; Rubin, D.L. Integrating Al algorithms into the clinical workflow. Radiol. Artif. Intell. 2021, 3, e210013. [Google Scholar] [CrossRef] [PubMed]
  170. Parker, A.L.; Benguigui, M.; Fornetti, J.; Goddard, E.; Lucotti, S.; Insua-Rodriguez, J.; Wiegmans, A.P. Current challenges in metastasis research and future innovation for clinical translation. Clin. Exp. Metastasis 2022, 39, 263–277. [Google Scholar] [CrossRef] [PubMed]
  171. Huang, Y.J.; Liu, W.; Wang, X.; Fang, Q.; Wang, R.; Wang, Y.; Chen, H.; Chen, H.; Meng, D.; Wang, L. Rectifying supporting regions with mixed and active supervision for rib fracture recognition. IEEE Trans. Med. Imaging 2020, 39, 3843–3854. [Google Scholar] [CrossRef] [PubMed]
  172. Abbasi, B.; Goldenholz, D.M. Machine learning applications in epilepsy. Epilepsia 2019, 60, 2037–2047. [Google Scholar] [CrossRef]
  173. Kocher, M.; Ruge, M.I.; Galldiks, N.; Lohmann, P. Applications of radiomics and machine learning for radiotherapy of malignant brain tumors. Strahlenther. Onkol. 2020, 196, 856–867. [Google Scholar] [CrossRef]
  174. Mlynarski, P.; Delingette, H.; Criminisi, A.; Ayache, N. Deep learning with mixed supervision for brain tumor segmentation. J. Med. Imaging 2019, 6, 1. [Google Scholar] [CrossRef]
  175. Ryu, J.Y.; Chung, H.Y.; Choi, K.Y. Potential role of artificial intelligence in craniofacial surgery. Arch. Craniofac. Surg. 2021, 22, 223–231. [Google Scholar] [CrossRef]
  176. Chen, H.; Qin, Z.; Ding, Y.; Tian, L.; Qin, Z. Brain tumor segmentation with deep convolutional symmetric neural network. Neurocomputing 2020, 392, 305–313. [Google Scholar] [CrossRef]
  177. Hyysalo, J.; Dasanayake, S.; Hannu, J.; Schuss, C.; Rajanen, M.; Leppänen, T.; Doermann, D.; Sauvola, J. Smart Mask—Wearable IoT Solution for Improved Protection and Personal Health. Internet Things 2022, 18, 100511. [Google Scholar] [CrossRef]
  178. Tedeschini, B.C.; Savazzi, S.; Stoklasa, R.; Barbieri, L.; Stathopoulos, I.; Nicoli, M.; Serio, L. Decentralized federated learning for healthcare networks: A case study on tumor segmentation. IEEE Access 2022, 10, 8693–8708. [Google Scholar] [CrossRef]
  179. Okal, C.O.; Loice, H.T. Usability of big data analytics within clinical decision support systems. Int. J. Eng. Appl. Sci. Technol. 2019, 4, 64–73. [Google Scholar] [CrossRef]
  180. Khawaldeh, S.; Pervaiz, U.; Rafiq, A.; Alkhawaldeh, R. Noninvasive grading of glioma tumor using magnetic resonance imaging with convolutional neural networks. Appl. Sci. 2018, 8, 27. [Google Scholar] [CrossRef]
Figure 1. Attrition of patients during the process of recruiting the patient to trial matching. Adapted from reference [78], under creative common license.
Figure 1. Attrition of patients during the process of recruiting the patient to trial matching. Adapted from reference [78], under creative common license.
Life 13 00024 g001
Table 1. Relevant studies in relation to the role of miRNAs in the oncogenesis of malignant primary brain tumors.
Table 1. Relevant studies in relation to the role of miRNAs in the oncogenesis of malignant primary brain tumors.
Tumor TypemiRNAGene-TargetBiological Function Signalling PathwayReferences
GlioblastomamiR-128-3pplatelet-derived growth factor alpha receptorpromotes glioblastomaDownreceptor tyrosine kinase[109]
GlioblastomamiR-218hypoxia-inducible factor 2 alphapromotes glioblastomaDownreceptor tyrosine kinase[110]
GlioblastomamiR-95Hepatocyte Growth Factor and Mitogen-Activated Protein Kinase Kinase 3 improved clinical outcome in the neural subtypeDownSignal transducer and activator of transcription 3 [111]
GlioblastomamiR-21Integrin b8 [112]improved clinical outcome in the neural subtypeUpSignal Transducer and Activator of Transcription [113][111]
GlioblastomamiR-381lymphoid enhancer-Inhibits metastases DownWnt[114]
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.

Share and Cite

MDPI and ACS Style

Philip, A.K.; Samuel, B.A.; Bhatia, S.; Khalifa, S.A.M.; El-Seedi, H.R. Artificial Intelligence and Precision Medicine: A New Frontier for the Treatment of Brain Tumors. Life 2023, 13, 24.

AMA Style

Philip AK, Samuel BA, Bhatia S, Khalifa SAM, El-Seedi HR. Artificial Intelligence and Precision Medicine: A New Frontier for the Treatment of Brain Tumors. Life. 2023; 13(1):24.

Chicago/Turabian Style

Philip, Anil K., Betty Annie Samuel, Saurabh Bhatia, Shaden A. M. Khalifa, and Hesham R. El-Seedi. 2023. "Artificial Intelligence and Precision Medicine: A New Frontier for the Treatment of Brain Tumors" Life 13, no. 1: 24.

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop