Search Results (14)

Image segmentation is one of the key factors in diagnosing glioma patients with brain tumors. It helps doctors identify the types of tumor that a patient is carrying and will lead to a prognosis that will help save the lives of patients. The analysis of medical images is a specialized domain in computer vision and image processing. This process extracts meaningful information from medical images that helps in treatment planning and monitoring the condition of patients. Deep learning models like CNN have shown promising results in image segmentation by identifying complex patterns in the image data. These methods have also shown great results in tumor segmentation and the identification of anomalies, which assist health care professionals in treatment planning. Despite advancements made in the domain of deep learning for medical image segmentation, the precise segmentation of tumors remains challenging because of the complex structures of tumors across patients. Existing models, such as traditional U-Net- and SAM-based architectures, either lack efficiency in handling class-specific segmentation or require extensive computational resources. This study aims to bridge this gap by proposing Segment Anything Model 2-UNetwork, a hybrid model that leverages the strengths of both architectures to improve segmentation accuracy and consumes less computational resources by maintaining efficiency. The proposed model possesses the ability to perform explicitly well on scarce data, and we trained this model on the Brain Tumor Segmentation Challenge 2020 (BraTS) dataset. This architecture is inspired by U-Networks that are based on the encoder and decoder architecture. The Hiera pre-trained model is set as a backbone to this architecture to capture multi-scale features. Adapters are embedded into the encoder to achieve parameter-efficient fine-tuning. The dataset contains four channels of MRI scans of 369 glioma patients as T1, T1ce, T2, and T2-flair and a segmentation mask for each patient consisting of non-tumor (NT), necrotic and non-enhancing tumor (NCR/NET), and peritumoral edema or GD-enhancing tumor (ET) as the ground-truth value. These experiments yielded good segmentation performance and achieved balanced performance based on the metrics discussed next in this paragraph for each tumor region. Our experiments yielded the following results with minimal hardware resources, i.e., 16 GB RAM with 30 epochs: a mean Dice score (mDice) of 0.771, a mean Intersection over Union (mIoU) of 0.569, an $S_{\alpha }$ score of 0.692, a weighted F-beta score ($F_{\beta }^w$) of 0.267, a F-beta score ($F_{\beta }$) of 0.261, an $E_{\varphi }$ score of 0.857, and a Mean Absolute Error (MAE) of 0.04 on the BraTS 2020 dataset. Full article

The integration of artificial intelligence (AI) with additive manufacturing (AM) is driving breakthroughs in personalized rehabilitation and physical therapy solutions, enabling precise customization to individual patient needs. This article presents the current state of knowledge and perspectives of using personalized solutions for rehabilitation and physiotherapy thanks to the introduction of AI to AM. Advanced AI algorithms analyze patient-specific data such as body scans, movement patterns, and medical history to design customized assistive devices, orthoses, and prosthetics. This synergy enables the rapid prototyping and production of highly optimized solutions, improving comfort, functionality, and therapeutic outcomes. Machine learning (ML) models further streamline the process by anticipating biomechanical needs and adapting designs based on feedback, providing iterative refinement. Cutting-edge techniques leverage generative design and topology optimization to create lightweight yet durable structures that are ideally suited to the patient’s anatomy and rehabilitation goals .AI-based AM also facilitates the production of multi-material devices that combine flexibility, strength, and sensory capabilities, enabling improved monitoring and support during physical therapy. New perspectives include integrating smart sensors with printed devices, enabling real-time data collection and feedback loops for adaptive therapy. Additionally, these solutions are becoming increasingly accessible as AM technology lowers costs and improves, democratizing personalized healthcare. Future advances could lead to the widespread use of digital twins for the real-time simulation and customization of rehabilitation devices before production. AI-based virtual reality (VR) and augmented reality (AR) tools are also expected to combine with AM to provide immersive, patient-specific training environments along with physical aids. Collaborative platforms based on federated learning can enable healthcare providers and researchers to securely share AI insights, accelerating innovation. However, challenges such as regulatory approval, data security, and ensuring equity in access to these technologies must be addressed to fully realize their potential. One of the major gaps is the lack of large, diverse datasets to train AI models, which limits their ability to design solutions that span different demographics and conditions. Integration of AI–AM systems into personalized rehabilitation and physical therapy should focus on improving data collection and processing techniques. Full article

Depression poses significant challenges to global healthcare systems and impacts the quality of life of individuals and their family members. Recent advancements in artificial intelligence (AI) have had a transformative impact on the diagnosis and treatment of depression. These innovations have the potential to significantly enhance clinical decision-making processes and improve patient outcomes in healthcare settings. AI-powered tools can analyze extensive patient data—including medical records, genetic information, and behavioral patterns—to identify early warning signs of depression, thereby enhancing diagnostic accuracy. By recognizing subtle indicators that traditional assessments may overlook, these tools enable healthcare providers to make timely and precise diagnostic decisions that are crucial in preventing the onset or escalation of depressive episodes. In terms of treatment, AI algorithms can assist in personalizing therapeutic interventions by predicting the effectiveness of various approaches for individual patients based on their unique characteristics and medical history. This includes recommending tailored treatment plans that consider the patient’s specific symptoms. Such personalized strategies aim to optimize therapeutic outcomes and improve the overall efficiency of healthcare. This theoretical review uniquely synthesizes current evidence on AI applications in primary care depression management, offering a comprehensive analysis of both diagnostic and treatment personalization capabilities. Alongside these advancements, we also address the conflicting findings in the field and the presence of biases that necessitate important limitations. Full article

Depression is one of the most common mental health disorders in the world, affecting millions of people. Early detection of depression is crucial for effective medical intervention. Multimodal networks can greatly assist in the detection of depression, especially in situations where in patients are not always aware of or able to express their symptoms. By analyzing text and audio data, such networks are able to automatically identify patterns in speech and behavior that indicate a depressive state. In this study, we propose two multimodal information fusion networks: early and late fusion. These networks were developed using convolutional neural network (CNN) layers to learn local patterns, a bidirectional LSTM (Bi-LSTM) to process sequences, and a self-attention mechanism to improve focus on key parts of the data. The DAIC-WOZ and EDAIC-WOZ datasets were used for the experiments. The experiments compared the precision, recall, f1-score, and accuracy metrics for the cases of using early and late multimodal data fusion and found that the early information fusion multimodal network achieved higher classification accuracy results. On the test dataset, this network achieved an f1-score of 0.79 and an overall classification accuracy of 0.86, indicating its effectiveness in detecting depression. Full article

The present review discusses the transformative role of AI in the diagnosis and management of head and neck cancers (HNCs). Methods: It explores how AI technologies, including ML, DL, and CNNs, are applied in various diagnostic tasks, such as medical imaging, molecular profiling, and predictive modeling. Results: This review highlights AI’s ability to improve diagnostic accuracy and efficiency, particularly in analyzing medical images like CT, MRI, and PET scans, where AI sometimes outperforms human radiologists. This paper also emphasizes AI’s application in histopathology, where algorithms assist in whole-slide image (WSI) analysis, tumor-infiltrating lymphocytes (TILs) quantification, and tumor segmentation. AI shows promise in identifying subtle or rare histopathological patterns and enhancing the precision of tumor grading and treatment planning. Furthermore, the integration of AI with molecular and genomic data aids in mutation analysis, prognosis, and personalized treatment strategies. Conclusions: Despite these advancements, the review identifies challenges in AI adoption, such as data standardization and model interpretability, and calls for further research to fully integrate AI into clinical practice for improved patient outcomes. Full article

The rapid advancement of medical imaging technologies has propelled the development of automated systems for the identification and classification of lung diseases. This study presents the design and implementation of an innovative image retrieval system utilizing artificial neural networks (ANNs) to enhance the accuracy and efficiency of diagnosing lung diseases. The proposed system focuses on addressing the challenges associated with the accurate recognition and classification of lung diseases from medical images, such as X-rays and CT scans. Leveraging the capabilities of ANNs, specifically convolutional neural networks (CNNs), the system aims to capture intricate patterns and features within images that are often imperceptible to human observers. This enables the system to learn discriminative representations of normal lung anatomy and various disease manifestations. The design of the system involves multiple stages. Initially, a robust dataset of annotated lung images is curated, encompassing a diverse range of lung diseases and their corresponding healthy states. Subsequently, a pre-processing pipeline is implemented to standardize the images, ensuring consistent quality and facilitating feature extraction. The CNN architecture is then meticulously constructed, with attention to layer configurations, activation functions, and optimization algorithms to facilitate effective learning and classification. The system also incorporates image retrieval techniques, enabling the efficient searching and retrieval of relevant medical images from the database based on query inputs. This retrieval functionality assists medical practitioners in accessing similar cases for comparative analysis and reference, ultimately supporting accurate diagnosis and treatment planning. To evaluate the system’s performance, comprehensive experiments are conducted using benchmark datasets, and performance metrics such as accuracy, precision, recall, and F1-score are measured. The experimental results demonstrate the system’s capability to distinguish between various lung diseases and healthy states with a high degree of accuracy and reliability. The proposed system exhibits substantial potential in revolutionizing lung disease diagnosis by assisting medical professionals in making informed decisions and improving patient outcomes. This study presents a novel image retrieval system empowered by artificial neural networks for the identification and classification of lung diseases. By leveraging advanced deep learning techniques, the system showcases promising results in automating the diagnosis process, facilitating the efficient retrieval of relevant medical images, and thereby contributing to the advancement of pulmonary healthcare practices. Full article

With the rapidly increasing reliance on advances in IoT, we persist towards pushing technology to new heights. From ordering food online to gene editing-based personalized healthcare, disruptive technologies like ML and AI continue to grow beyond our wildest dreams. Early detection and treatment through AI-assisted diagnostic models have outperformed human intelligence. In many cases, these tools can act upon the structured data containing probable symptoms, offer medication schedules based on the appropriate code related to diagnosis conventions, and predict adverse drug effects, if any, in accordance with medications. Utilizing AI and IoT in healthcare has facilitated innumerable benefits like minimizing cost, reducing hospital-obtained infections, decreasing mortality and morbidity etc. DL algorithms have opened up several frontiers by contributing towards healthcare opportunities through their ability to understand and learn from different levels of demonstration and generalization, which is significant in data analysis and interpretation. In contrast to ML which relies more on structured, labeled data and domain expertise to facilitate feature extractions, DL employs human-like cognitive abilities to extract hidden relationships and patterns from uncategorized data. Through the efficient application of DL techniques on the medical dataset, precise prediction, and classification of infectious/rare diseases, avoiding surgeries that can be preventable, minimization of over-dosage of harmful contrast agents for scans and biopsies can be reduced to a greater extent in future. Our study is focused on deploying ensemble deep learning algorithms and IoT devices to design and develop a diagnostic model that can effectively analyze medical Big Data and diagnose diseases by identifying abnormalities in early stages through medical images provided as input. This AI-assisted diagnostic model based on Ensemble Deep learning aims to be a valuable tool for healthcare systems and patients through its ability to diagnose diseases in the initial stages and present valuable insights to facilitate personalized treatment by aggregating the prediction of each base model and generating a final prediction. Full article

Primary care has the potential to be transformed by artificial intelligence (AI) and, in particular, machine learning (ML). This review summarizes the potential of ML and its subsets in influencing two domains of primary care: pre-operative care and screening. ML can be utilized in preoperative treatment to forecast postoperative results and assist physicians in selecting surgical interventions. Clinicians can modify their strategy to reduce risk and enhance outcomes using ML algorithms to examine patient data and discover factors that increase the risk of worsened health outcomes. ML can also enhance the precision and effectiveness of screening tests. Healthcare professionals can identify diseases at an early and curable stage by using ML models to examine medical pictures, diagnostic modalities, and spot patterns that may suggest disease or anomalies. Before the onset of symptoms, ML can be used to identify people at an increased risk of developing specific disorders or diseases. ML algorithms can assess patient data such as medical history, genetics, and lifestyle factors to identify those at higher risk. This enables targeted interventions such as lifestyle adjustments or early screening. In general, using ML in primary care offers the potential to enhance patient outcomes, reduce healthcare costs, and boost productivity. Full article

Recently, robots have assisted and contributed to the biomedical field. Scaling down the size of robots to micro/nanoscale can increase the accuracy of targeted medications and decrease the danger of invasive operations in human surgery. Inspired by the motion pattern and collective behaviors of the tiny biological motors in nature, various kinds of sophisticated and programmable microrobots are fabricated with the ability for cargo delivery, bio-imaging, precise operation, etc. In this review, four types of propulsion—magnetically, acoustically, chemically/optically and hybrid driven—and their corresponding features have been outlined and categorized. In particular, the locomotion of these micro/nanorobots, as well as the requirement of biocompatibility, transportation efficiency, and controllable motion for applications in the complex human body environment should be considered. We discuss applications of different propulsion mechanisms in the biomedical field, list their individual benefits, and suggest their potential growth paths. Full article

Hydatid disease is one of the 17 neglected tropical diseases recognized by WHO and causes a huge global disease burden. Hydatid disease poses a great threat to local medical poverty alleviation. In efforts to break the vicious circle of poverty, Hydatid disease has been widely concerned and discussed. In the practice of poverty alleviation in China, medical poverty alleviation is regarded as the double goal of getting rid of poverty and promoting the construction of a healthy China. On the basis of on-the-spot investigation in Yushu Prefecture, this paper conducts a follow up study on the poverty-causing effect of Hydatid disease and the precision medical assistance pattern of government using a field investigation method. The results show that Hydatid disease led to the increase of poverty in the population in Yushu Prefecture, precision medical assistance played an obvious role in treating Hydatid disease and poverty alleviation, the health service in the study area continues to improve and the medical backbone team further expanded. The main conclusion is that the three-level diagnosis and treatment framework can effectively reduce local poverty and improve people’s living environment. Full article

The identification of vascular network structures is one of the key fields of research in medical imaging. The segmentation of dorsal hand vein patterns form NIR images is not only the basis for reliable biometric identification, but would also provide a significant tool in assisting medical intervention. Precise vein extraction would help medical workers to exactly determine the needle entry point to efficiently gain intravenous access for different clinical purposes, such as intravenous therapy, parenteral nutrition, blood analysis and so on. It would also eliminate repeated attempts at needle pricks and even facilitate an automatic injection procedure in the near future. In this paper, we present a combination of unsupervised and supervised dorsal hand vein segmentation from near-infrared images in the NCUT database. This method is convenient due to the lack of expert annotations of publicly available vein image databases. The novelty of our work is the automatic extraction of the veins in two phases. First, a geometrical approach identifies tubular structures corresponding to veins in the image. This step is considered gross segmentation and provides labels (Label I) for the second CNN-based segmentation phase. We visually observe that different CNNs obtain better segmentation on the test set. This is the reason for building an ensemble segmentor based on majority voting by nine different network architectures (U-Net, U-Net++ and U-Net3+, all trained with BCE, Dice and focal losses). The segmentation result of the ensemble is considered the second label (Label II). In our opinion, the new Label II is a better annotation of the NCUT database than the Label I obtained in the first step. The efficiency of computer vision algorithms based on artificial intelligence algorithms is determined by the quality and quantity of the labeled data used. Furthermore, we prove this statement by training ResNet–UNet in the same manner with the two different label sets. In our experiments, the Dice scores, sensitivity and specificity with ResNet–UNet trained on Label II are superior to the same classifier trained on Label I. The measured Dice scores of ResNet–UNet on the test set increase from 90.65% to 95.11%. It is worth mentioning that this article is one of very few in the domain of dorsal hand vein segmentation; moreover, it presents a general pipeline that may be applied for different medical image segmentation purposes. Full article

Mammography is a first-line imaging examination that employs low-dose X-rays to rapidly screen breast tumors, cysts, and calcifications. This study proposes a two-dimensional (2D) spatial and one-dimensional (1D) convolutional neural network (CNN) to early detect possible breast lesions (tumors) to reduce patients’ mortality rates and to develop a classifier for use in mammographic images on regions of interest where breast lesions (tumors) may likely occur. The 2D spatial fractional-order convolutional processes are used to strengthen and sharpen the lesions’ features, denoise, and improve the feature extraction processes. Then, an automatic extraction task is performed using a specific bounding box to sequentially pick out feature patterns from each mammographic image. The multi-round 1D kernel convolutional processes can also strengthen and denoise 1D feature signals and assist in the identification of the differentiation levels of normality and abnormality signals. In the classification layer, a gray relational analysis-based classifier is used to screen the possible lesions, including normal (Nor), benign (B), and malignant (M) classes. The classifier development for clinical applications can reduce classifier’s training time, computational complexity level, computational time, and achieve a more accurate rate for meeting clinical/medical purpose. Mammographic images were selected from the mammographic image analysis society image database for experimental tests on breast lesions screening and K-fold cross-validations were performed. The experimental results showed promising performance in quantifying the classifier’s outcome for medical purpose evaluation in terms of recall (%), precision (%), accuracy (%), and F1 score. Full article

Augmented reality (AR) surgical navigation systems have attracted considerable attention as they assist medical professionals in visualizing the location of ailments within the human body that are not readily seen with the naked eye. Taking medical imaging with a parallel C-shaped arm (C-arm) as an example, surgical sites are typically targeted using an optical tracking device and a fiducial marker in real-time. These markers then guide operators who are using a multifunctional endoscope apparatus by signaling the direction or distance needed to reach the affected parts of the body. In this way, fiducial markers are used to accurately protect the vessels and nerves exposed during the surgical process. Although these systems have already shown potential for precision implantation, delamination of the fiducial marker, which is a critical component of the system, from human skin remains a challenge due to a mechanical mismatch between the marker and skin, causing registration problems that lead to poor position alignments and surgical degradation. To overcome this challenge, the mechanical modulus and stiffness of the marker patch should be lowered to approximately 150 kPa, which is comparable to that of the epidermis, while improving functionality. Herein, we present a skin-conformal, stretchable yet breathable fiducial marker for the application in AR-based surgical navigation systems. By adopting pore patterns, we were able to create a fiducial marker with a skin-like low modulus and breathability. When attached to the skin, the fiducial marker was easily identified using optical recognition equipment and showed skin-conformal adhesion when stretched and shrunk repeatedly. As such, we believe the marker would be a good fiducial marker candidate for patients under surgical navigation systems. Full article

The applications of stable isotopes in metabolomics have facilitated the study of cell metabolisms. Stable isotope-assisted metabolomics requires: (1) properly designed tracer experiments; (2) stringent sampling and quenching protocols to minimize isotopic alternations; (3) efficient metabolite separations; (4) high resolution mass spectrometry to resolve overlapping peaks and background noises; and (5) data analysis methods and databases to decipher isotopic clusters over a broad m/z range (mass-to-charge ratio). This paper overviews mass spectrometry based techniques for precise determination of metabolites and their isotopologues. It also discusses applications of isotopic approaches to track substrate utilization, identify unknown metabolites and their chemical formulas, measure metabolite concentrations, determine putative metabolic pathways, and investigate microbial community populations and their carbon assimilation patterns. In addition, ¹³C-metabolite fingerprinting and metabolic models can be integrated to quantify carbon fluxes (enzyme reaction rates). The fluxome, in combination with other “omics” analyses, may give systems-level insights into regulatory mechanisms underlying gene functions. More importantly, ¹³C-tracer experiments significantly improve the potential of low-resolution gas chromatography-mass spectrometry (GC-MS) for broad-scope metabolism studies. We foresee the isotope-assisted metabolomics to be an indispensable tool in industrial biotechnology, environmental microbiology, and medical research. Full article