Skip to Content
  • Review
  • Open Access

24 December 2024

52 Pages

The Neural Frontier of Future Medical Imaging: A Review of Deep Learning for Brain Tumor Detection

Laboratory of Automation and Manufacturing Engineering, Department of Industrial Engineering, Batna 2 University, Batna 05000, Algeria

Abstract

Brain tumor detection is crucial in medical research due to high mortality rates and treatment challenges. Early and accurate diagnosis is vital for improving patient outcomes, however, traditional methods, such as manual Magnetic Resonance Imaging (MRI) analysis, are often time-consuming and error-prone. The rise of deep learning has led to advanced models for automated brain tumor feature extraction, segmentation, and classification. Despite these advancements, comprehensive reviews synthesizing recent findings remain scarce. By analyzing over 100 research papers over past half-decade (2019–2024), this review fills that gap, exploring the latest methods and paradigms, summarizing key concepts, challenges, datasets, and offering insights into future directions for brain tumor detection using deep learning. This review also incorporates an analysis of previous reviews and targets three main aspects: feature extraction, segmentation, and classification. The results revealed that research primarily focuses on Convolutional Neural Networks (CNNs) and their variants, with a strong emphasis on transfer learning using pre-trained models. Other methods, such as Generative Adversarial Networks (GANs) and Autoencoders, are used for feature extraction, while Recurrent Neural Networks (RNNs) are employed for time-sequence modeling. Some models integrate with Internet of Things (IoT) frameworks or federated learning for real-time diagnostics and privacy, often paired with optimization algorithms. However, the adoption of eXplainable AI (XAI) remains limited, despite its importance in building trust in medical diagnostics. Finally, this review outlines future opportunities, focusing on image quality, underexplored deep learning techniques, expanding datasets, and exploring deeper learning representations and model behavior such as recurrent expansion to advance medical imaging diagnostics.

1. Introduction

Brain tumors, both benign and malignant, are a major focus of medical research due to their impact on patient health and the need for better diagnostic and therapeutic strategies [1,2,3,4]. These tumors can be classified into primary brain tumors, such as gliomas, meningiomas, and pituitary tumors, and metastatic tumors that spread from other body cancers [5,6,7,8,9,10,11,12,13]. Gliomas, including glioblastomas, are the most aggressive, while meningiomas are typically benign and originate in the meninges [8,9,10,11,12,13]. Symptoms of brain tumors vary depending on size, location, and type, and can include headaches, dizziness, cognitive changes like forgetfulness, and physical impairments such as difficulty with mobility and speech. Emotional and behavioral changes, like mood swings and reduced social engagement, also occur [14]. Figure 1 illustrates these diverse symptoms, emphasizing the complex effects on both physical and psychological well-being [14].
Figure 1. Illustration of changes or symptoms prior to brain tumor diagnosis. This figure, reproduced from [14] under an open-access license permitting non-commercial use, has been edited using a curves adjustment layer. This adjustment was applied to manipulate the visual properties, enhancing clarity and detail.
The causes of brain tumors are not fully understood, but genetic mutations and environmental factors, such as radiation exposure, may play a role [8,9,10,11,12,13]. Diagnosis is typically performed using imaging techniques like MRI or CT scans to determine the tumor’s location and size [1]. Treatment often involves surgery, radiation therapy, and chemotherapy, tailored to the tumor type, location, and patient factors such as age and overall health. Surgery aims to remove as much of the tumor as possible, while radiation therapy and chemotherapy target and destroy tumor cells. Advances in treatment have improved outcomes, but prognosis varies based on tumor characteristics and early detection. Early diagnosis and treatment are critical for better survival rates and quality of life. Figure 2 summarizes the key challenges, causes, treatment options, and diagnostic methods for brain tumors, highlighting their significance in both research and clinical practice due to their high mortality rates and complex treatment [15,16,17,18,19,20,21,22,23,24].
Figure 2. Key aspects of brain tumors: challenges, causes, treatments, and diagnostic methods.
Conventional diagnostic methods, such as manual analysis of MRI scans and histopathological examinations, are often time-consuming, subjective, and prone to human error. These limitations can significantly hinder timely and accurate diagnosis of brain tumors [25,26]. However, in recent years, deep learning has emerged as a leading technology in medical imaging. Deep learning offers promising solutions for automating critical tasks such as brain tumor feature extraction, segmentation, and classification, potentially improving both the speed and accuracy of diagnosis [27]. Leveraging advanced algorithms and vast datasets, deep learning models can enhance diagnostic accuracy and efficiency, providing critical support in clinical decision-making. Given the abundance of studies exploring deep learning applications in brain tumor detection, a comprehensive overview is essential to synthesize findings and identify research gaps [28,29,30,31,32,33,34,35,36].
This introduction is dedicated to three key subsections. The Section 1.1 will delve into the methodologies used in selecting and analyzing relevant papers, highlighting the criteria for analysis and the approaches employed to derive meaningful insights. The Section 1.2 will express the significant contributions of this review, emphasizing how it synthesizes existing research to identify gaps and propose future directions in brain tumor detection. Finally, the Section 1.3 will provide an overview of the paper’s structure, detailing the main sections and presenting a hierarchical classification of the methodologies and findings discussed throughout the review. Through this organized approach, we aim to clarify the critical role of deep learning in advancing brain tumor detection and address the pressing need for continued innovation in this field.

1.1. Paper Collections Methodologies and Analysis Criteria

The paper collection process follows a well-defined and organized methodology. Specific keywords have been established to ensure their presence in the metadata of the research papers, primarily including terms like “image processing”, “medical”, “deep learning”, “tumors”, “machine learning”, “diagnosis”, and “neural networks”. To enhance the accuracy of search results, the terms “tumor + brain” or “brain” are required to be present in the title. To streamline the search mechanism, a “Publish or Perish” software v8.16.4790.9060 is employed, targeting databases such as Scopus, PubMed, and Google Scholar search engine [37]. Research is conducted on an annual basis, starting from 1 January 2019 to 17 October 2024 (i.e., the day the development of this review paper began), with the aim of covering at least the past half-decade to draw significant conclusions. The search results are saved as “*.csv” files containing comprehensive details such as title, year, source, publisher, etc. Subsequently, a MATLAB script is developed to further clean the collected data and simplify the process of downloading the papers. It begins by filtering the collected dataset of those “*.csv” files to include only entries where the title contains the word “brain”, or “tumor”, irrespective of case. This step ensures that the analysis remains concentrated on relevant studies.
The filtered datasets are then concatenated into a single table, and duplicate entries based on the title are removed. The script also extracts the research types, enabling focused analysis on different categories of research papers. For each unique type, the script creates a separate table. This organization facilitates easier access to the data during subsequent analysis. The individual tables are sorted by publication year in descending order to maintain a consistent format for analysis. The combined dataset, containing all relevant tables, is saved as a “*.mat” file for future use. This step ensures that the data are stored in a structured format, allowing for efficient retrieval and further analysis in later sessions. In the subsequent part of the analysis, statistics regarding the number of research papers by type are calculated. A list of all the types and stores statistics are then generated, including the type name and the corresponding count of research papers.
Figure 3a visualizes the distribution of research papers by type, represented as a pie chart displaying the percentage distribution of various types of research papers. The chart indicates that the majority of the papers are categorized as articles, accounting for 62.8% of the total publications, which corresponds to 81 papers. This highlights a strong emphasis on original research within the field. In contrast, conference papers constitute 25.6% of the total, totaling 33 papers, suggesting significant interest in disseminating research findings through conferences. Book chapters account for a minor segment of the dataset at 3.1%, totaling four papers, possibly reflecting a more specialized or less common avenue for research dissemination.
Figure 3. Distribution of research papers by type: (a) pie chart showing the percentage of publications by type over half a decade; (b) number of research papers per year by type.
Figure 3b visualizes the number of research papers published per year for each type, revealing notable trends in publication output across different research paper types from 2019 to 2024. For articles, there is a significant upward trajectory, starting with four papers in 2019, increasing to six papers in both 2020 and 2021, and then experiencing a substantial surge to 24 papers in 2022. This increase reflects a growing momentum in research activity, continuing with 16 papers published in 2023 and reaching a peak of 25 papers in 2024. This consistent rise suggests a strong focus on original research in recent years. In contrast, the publication of book chapters has been relatively limited, with no publications in 2019, followed by one paper in 2020, and then no further publications until 2022, when two papers were released. In 2023, only one paper was published, and there were no contributions in 2024. This indicates that book chapters are not a primary avenue for research dissemination in this field. Conference papers exhibit a gradual increase over the years, starting with one paper in 2019 and rising to two papers in 2020 and 2021. In 2022, the number increased to seven papers, followed by thirteen papers in 2023, and eight papers in 2024. This suggests that conference presentations have become a more popular method for sharing research findings, particularly in recent years.
According to Figure 3a,b, review articles make up 8.5% of the dataset, represented by 11 papers. This indicates that, while reviews are valuable for synthesizing existing research, they are less common compared to original studies and conference contributions. This trend underscores the need for more review articles in the field to provide comprehensive overviews and identify gaps for future research. In this analysis, we were able to download a total of 55 journal articles and 22 conference papers, which will serve as the primary focus of our study. These papers are divided into three key sections: extraction, segmentation, and classification, with approximately 27 papers dedicated to each section. Important conclusions from these papers will be collected and analyzed to provide a comprehensive overview of the current research landscape. Additionally, we downloaded nine review papers, which will be analyzed separately to identify research gaps and determine the limitations of previous review-based studies. These papers will contribute to a more thorough understanding of the challenges and advancements in the field.
It should be noted that the author did not intentionally exclude papers from any specific publisher during the paper collection process, which was based on the aforementioned criteria. As stated, the filtering process was carried out using a program script designed to minimize human error, such as overlooking certain papers or introducing biases due to lapses in focus. While it is possible that some articles were unintentionally excluded, it is guaranteed that the selected papers are directly relevant to the topic of deep learning and brain tumor detection. Although no methodology is perfect and some exclusions may have occurred, the quantity and quality of the selected papers are deemed sufficient to draw generalized conclusions.
In this work, at the preliminary stage, based solely on the titles of the selected papers, we can conclude that the research carried out in the field of brain tumor detection with topics of classification, feature extraction, and segmentation primarily explores a broad range of methods and paradigms. By “methods”, we refer to algorithms and models used to process medical images, including CNNs, LSTMs, Autoencoders, and GANs, alongside optimization techniques like Bayesian optimization for instance, to improve feature extraction and model accuracy, especially for MRI scans. Similarly, “paradigms” refer to frameworks guiding these methods, such as transfer learning for adapting pre-trained models, reinforcement learning for performance improvement, federated learning for privacy-preserving data usage, and XAI for making model decisions transparent and interpretable for medical professionals. It is noteworthy to mention that this is an author-specified concept that must be taken into consideration throughout the entire review.
In context of methods, the papers adopt advanced deep learning techniques, such as CNNs, LSTM, Gated Recurrent Units (GRUs), and autoencoders, with some leveraging of GANs for synthetic data generation. Several papers incorporate hybrid models combining various networks, such as in the case of hybrid deep learning models using CNNs alongside optimization algorithms like Bayesian optimization. Moreover, optimization techniques such as Particle Swarm Optimization (PSO), Genetic Algorithms (GA), and Ant-Lion Optimization (ALO) are frequently employed to enhance model performance or fine-tune hyperparameters. Other optimization and feature extraction techniques like Principal Component Analysis (PCA) and wavelet transforms are used to enhance brain tumor image data. Statistical tests are less emphasized compared to algorithmic-based solutions but are sometimes applied for validation and performance metrics.
In terms of learning paradigms, several papers explore transfer learning, which allows models to leverage pre-trained architectures, typically from large datasets like ImageNet, to fine-tune for specific tasks in brain tumor classification. Reinforcement learning and its application in medical imaging appear in certain studies, demonstrating its potential to improve model decision-making over time. Federated learning is another emerging approach, enabling the use of distributed data without compromising privacy, particularly in healthcare. There is also a notable focus on XAI and Interpretable AI (IAI), which aim to make deep learning models more transparent and understandable in high-stakes scenarios like medical diagnosis. Additionally, some papers integrate IoT solutions to facilitate real-time data acquisition and processing, improving the connectivity and application of artificial intelligence in clinical settings. Thus, the carried-out research not only focuses on leveraging cutting-edge algorithms and optimization techniques but also explores innovative learning paradigms such as transfer learning and XAI to ensure more robust and interpretable models.
This combination of methods and paradigms reflects the continued push toward enhancing the accuracy and practicality of brain tumor diagnosis through deep learning technologies. Table 1 introduces and summarizes the analysis criteria for brain tumor feature extraction, segmentation, and classification methods, detailing the various algorithms, models, and paradigms adopted in this work.
Table 1. Analysis criteria for brain tumor detection methods.

1.2. Contributions

This paper provides a comprehensive review of trends in brain tumors detection with deep learning by focusing on advancements in image-based feature extraction, segmentation, and classification, with a specific focus on the application of deep learning techniques across these stages. By analyzing methods, trends, and gaps in existing research, this paper aims to bridge critical knowledge gaps and foster innovation in the field of computer vision and clinical diagnosis. The key contributions of this paper are as follows:
  • Exploration of research methodologies and trends: This paper offers a detailed analysis of research methodologies and statistical trends in the field, providing a holistic view of the current scientific landscape (see Section 1.1).
  • Analysis of related review papers: By critically examining related review articles, this study identifies prior contributions and uncovers existing gaps, justifying the need for this review and offering a roadmap for future research efforts in image processing using deep learning.
  • Comprehensive review of deep learning advancements: The paper provides an in-depth overview of recent developments in deep learning techniques for feature extraction, segmentation, and classification, underscoring their effectiveness in automating complex tasks and improving performance in various applications.
  • Integration of feature extraction, segmentation, and classification: This study emphasizes the interconnected nature of feature extraction, segmentation, and classification in the image analysis pipeline, demonstrating how their integration can enhance accuracy and reliability in a wide range of use cases.
  • Critical evaluation of algorithms and methodologies: The paper reviews these modern approaches, analyzing the strengths, weaknesses, and practical implications of various algorithms used in image-based feature extraction and classification.
  • Exploration of datasets and their role in research: An investigation into the datasets used for training and evaluation highlights the importance of diversity, quality, and preprocessing in ensuring robust and generalizable models.
  • Identification of future research directions: The paper outlines pathways for future opportunities, such as image quality and compression, leveraging multimodal data, improving deep learning architectures, and addressing challenges in data accessibility and annotation.

1.3. Outline of Paper Sections

As illustrated in the simplified diagram in Figure 4, this review paper is structured to provide a comprehensive overview of the state of research in brain tumor detection using medical images. Following the introduction in Section 1, Section 2 identifies key gaps in existing literature by analyzing related review papers. The heart of the paper lies in Section 3, Section 4 and Section 5, where we delve into the latest trends and challenges in image-based feature extraction (Section 3), image segmentation (Section 4), and image classification (Section 5). These sections provide detailed overviews of the fundamental concepts, challenges, and advancements in each area, including techniques such as CNNs, GANs, Autoencoders, and optimization algorithms in a simplified way in a sort of illustrative examples. They also explore emerging paradigms like transfer learning, reinforcement learning, and the IoT as they pertain to medical imaging and tumor detection. Finally, Section 6 outlines promising directions for future research, while Section 7 concludes the paper by summarizing the key insights and contributions. This structured approach allows a holistic understanding of the current state of brain tumor detection research, while also paving the way for future advancements in the field.
Figure 4. Simplified diagram of the papers framework for reviewing brain tumor detection related works: incorporating related review analyses, feature extraction, segmentation, and classification using medical images and deep learning, with future opportunities.
In this architecture of the current review paper, it is acknowledged that the long paragraphs discussing the papers may be difficult to read. To address this, we have made efforts to improve readability by introducing subsections. However, we believe the current subsectioning is the most suitable in this case, as it allows for clear presentation of the review results in tables, followed by bar charts. Furthermore, the review is structured around three major axes: classification, extraction, and segmentation. We believe that the inclusion of bar charts and diagrams will greatly assist readers in understanding the recent trends in each subfield and provide valuable insights for drawing meaningful conclusions. We trust that this organization will enhance the clarity of the manuscript while ensuring a comprehensive review of the topic.

6. Discussion and Pathways for Future Opportunities

The state-of-the-art in brain tumor detection using deep learning highlights significant advancements in methodologies, learning paradigms, and datasets, yet key gaps remain in fully leveraging these techniques. While CNNs and transfer learning have become dominant due to their efficiency in feature extraction, tumor segmentation, and classification, their reliance on large, labeled datasets still limits their applicability in diverse real-world settings. A critical gap exists in the generalizability of these models, particularly across different tumor types and patient populations. This issue is compounded by class overlapping, where tumor types exhibit similar features, leading to challenges in distinguishing them accurately. Moreover, while hybrid approaches have gained traction by combining various deep learning techniques for enhanced performance, these methods often lack the adaptability needed to address the complex, dynamic nature of brain tumor imaging. Custom architectures are promising but are frequently underutilized due to the challenge of tailoring solutions for specific datasets or tumor types.
Techniques such as Autoencoders, GANs, and LSTM networks remain less prevalent, despite their potential for addressing unique challenges such as data contextualization, temporal data modeling, and feature refinement. One reason for their underutilization could be the lack of sufficient research focused on their integration with brain tumor detection tasks. These methods could offer solutions to the complexities associated with imaging, such as noise reduction and the handling of varying tumor growth patterns over time. However, they often require more intricate setups and specialized knowledge to implement, which may contribute to their limited use.
Furthermore, datasets like BraTS, Kaggle, and T1-WCEMRI, while comprehensive and standardized, may not fully capture the variability seen in real clinical settings, where imaging techniques, tumor characteristics, and patient demographics can differ significantly. Personal clinical data present an exciting opportunity to bridge this gap, yet the challenges of data privacy, annotation quality, and clinical integration hinder its widespread adoption. Additionally, while supervised learning continues to dominate, there is a need for more research into unsupervised or semi-supervised methods, particularly as these could provide solutions in cases where labeled data are scarce. Finally, while emerging techniques such as ViT, federated learning, and adversarial training represent the field’s drive toward innovation, these advanced methods are often underutilized due to their complexity, computational demand, and the need for specialized infrastructure, further limiting their adoption in mainstream clinical applications.
Despite these hurdles, the continued exploration of these underutilized methods and the resolution of existing gaps offer significant opportunities for advancing brain tumor detection and classification. To drive progress in this field, we propose several future directions categorized into five key areas, as illustrated in the diagram presented in Figure 13.
Figure 13. Diagram of proposed future directions for brain tumors detection with deep learning image classification.

6.1. Discussing and Improving Raw Image Quality

The quality of raw medical images significantly impacts the effectiveness of deep learning models in brain tumor detection [140,141,142,143,144,145,146]. Unfortunately, many studies treat available datasets as perfect representations without considering the effects of image type, acquisition protocols, or compression techniques on model performance [147,148,149]. Image compression, while essential for managing large datasets, often introduces artifacts or reduces critical diagnostic details. Methods like JPEG or JPEG2000 compression have not been adequately studied in this context, nor have adaptive compression techniques that can selectively retain vital image features while minimizing file size [147,148,149]. Furthermore, preprocessing methods aimed at enhancing image clarity and correcting for noise or motion artifacts are underutilized but have the potential to significantly improve data quality. Leveraging artificial intelligence-driven tools for dynamic image quality assessment and enhancement could ensure that inputs to deep learning models are consistent and reliable, even when acquired from diverse clinical settings [150,151]. Addressing these aspects will ensure that models trained on such data are more robust and applicable to real-world diagnostic scenarios.

6.2. Exploration of Underutilized Deep Learning Methods

While CNNs dominate brain tumor detection research, several promising methods remain underexplored. Transformers, for instance, are gaining traction for their ability to model complex relationships in data, making them suitable for handling spatial and temporal dependencies in medical imaging [152,153,154,155,156,157,158]. Graph Neural Networks (GNNs) offer another avenue, as they can represent and analyze relationships between imaging features, which is critical in understanding tumor morphology [159,160,161]. Autoencoders and GANs are also valuable tools for enhancing data augmentation, detecting anomalies, and enabling semi-supervised learning, especially when working with limited datasets. LSTM networks hold promise for capturing temporal changes in patient data, such as tracking tumor progression or response to therapy [162]. Moreover, hybrid approaches combining traditional CNNs with these advanced architectures could unlock new possibilities for improving feature extraction and decision-making processes. By integrating these methods, researchers can tackle unique challenges in brain tumor detection, such as small dataset sizes, complex tumor characteristics, and temporal dynamics.

6.3. Expanding and Diversifying Datasets

The reliance on a few public datasets, such as BraTS and Kaggle, has limited the diversity of data used for training and evaluating brain tumor detection models. Therefore, incorporating fewer common datasets, such as those from TCIA or MICCAI, can provide a broader representation of imaging conditions, tumor types, and patient demographics. Using private clinical datasets would further enhance the variability and realism of training data, ensuring models are better suited to real-world applications. Additionally, the integration of multimodal imaging data, such as combining MRI, CT, PET, and histopathological images, could enable the development of more robust and holistic diagnostic systems. Including non-imaging data, such as genomic, proteomic, and clinical records, could improve diagnostic precision by adding complementary insights into tumor behavior and patient-specific factors. Addressing underrepresented populations and imaging modalities is another crucial step toward creating more inclusive and generalizable models, ultimately enhancing the fairness and applicability of these systems.

6.4. Beyond Deep Learning: Model Behavior Integration

To push the boundaries of deep learning in brain tumor detection, it is essential to go beyond current architectures and incorporate model behavior analysis into the learning process. Techniques like recurrent expansion allow models to iteratively refine their parameters based on both data characteristics and the model’s dynamic responses during training [163,164,165,166]. These approaches enable a deeper understanding of feature mappings and how models behave under different training conditions, leading to more effective parameter tuning and improved performance. In recurrent expansion theories, small-scale machine learning techniques, such as ELMs, can complement deep learning by providing lightweight yet effective alternatives for feature extraction or ensemble learning [163,164,165,166]. Combining domain adaptation with transfer learning can further enhance model adaptability to diverse clinical scenarios, enabling models to handle variations in imaging modalities, patient demographics, and tumor characteristics more effectively.

6.5. Uncertainty Quantification

In clinical applications, particularly in predictions generated by deep learning models, quantifying uncertainty is as crucial as achieving high accuracy. Current brain tumor detection systems, as highlighted in the documented review presented in previous sections, often lack robust mechanisms for providing confidence estimates alongside predictions [167,168]. Techniques such as ensemble learning, confidence intervals, Bayesian deep learning, and Monte Carlo dropout, among others, can address this gap by enabling models to estimate uncertainty in their outputs [167,168]. These methods can be integrated into diagnostic pipelines to identify ambiguous cases that require further review, thereby improving clinical trust in artificial intelligence and learning systems. Additionally, XAI frameworks can enhance the interpretability of models, allowing clinicians to understand and validate predictions, fostering greater adoption of artificial intelligence in practice. Developing tools and methodologies for assessing uncertainty and integrating these into model performance benchmarks is critical for ensuring that artificial intelligence systems meet clinical reliability standards.

6.6. Additional Considerations

The development of standardized benchmarks aligned with specific evaluation methodologies is crucial to ensure consistency and comparability across studies in the field of tumor detection using deep learning. Additionally, integrating real-time and edge computing capabilities into detection systems could significantly enhance the deployment of these models in clinical settings, particularly in resource-constrained environments. In scenarios with limited connectivity or strict privacy requirements, federated learning emerges as a key solution, enabling collaborative model training while maintaining data privacy and addressing these challenges effectively. Lastly, fostering interdisciplinary collaboration among radiologists, computer scientists, and clinical researchers is vital for translating research innovations into practical diagnostic tools. These collaborative efforts will help bridge the gap between theoretical advancements and their application in real-world clinical scenarios, paving the way for more equitable, efficient, and accurate brain tumor detection systems.

7. Conclusions

In conclusion, this paper provided a comprehensive review of state-of-the-art studies in brain tumor detection using deep learning, encompassing over 100 references from the past half-decade. Through an in-depth analysis of related reviews, feature extraction techniques, segmentation methodologies, and classification approaches, it was observed that CNNs and transfer learning remain dominant methodologies across all aspects of tumor detection. However, innovative methods such as hybrid models, GANs, GNNs, and Transformers remain relatively underexplored despite their potential to address complex challenges in tumor detection. Similarly, learning paradigms like XAI and federated learning, which could enhance model interpretability and privacy-preserving collaborative training, have been sparsely discussed. Moreover, key aspects such as the impact of image types and compression, multimodal data integration, and uncertainty quantification have received insufficient attention, despite their critical role in improving model robustness and clinical applicability. The findings suggest that future research should prioritize addressing gaps related to data diversity by incorporating underutilized datasets and ensuring equitable representation of imaging modalities and patient demographics. Enhancing image quality through improved acquisition protocols, adaptive compression techniques, and artifact correction will be critical for maintaining diagnostic fidelity. Additionally, integrating multimodal imaging data with non-imaging data, such as genomic or clinical records, could enable the development of holistic diagnostic systems. Leveraging advanced technologies like federated learning and real-time edge computing would further facilitate the deployment of deep learning models in clinical settings, particularly in resource-constrained environments. By addressing these gaps, future advancements can bridge the divide between theoretical research and practical clinical application, leading to more robust, interpretable, and accessible diagnostic systems. This review provides valuable insights into the current landscape and identifies potential directions for advancing brain tumor detection with deep learning, offering a foundational reference for researchers and practitioners striving to improve patient outcomes. Finally, this review explores methods, paradigms, and datasets for feature extraction, segmentation, and classification, leaving a detailed comparative analysis of performance metrics, such as accuracy, as a valuable direction for future studies to better assess methodological effectiveness.

Funding

This research received no external funding.

Institutional Review Board Statement

Not applicable.

Data Availability Statement

As part of our commitment to scientific advancement, we are sharing the data on downloaded papers along with the corresponding code in this link here: https://doi.org/10.5281/zenodo.14551069. Additionally, the codes for the examples discussed in this review, covering extraction, segmentation, and classification, are available in this link here: https://doi.org/10.5281/zenodo.14551091.

Acknowledgments

I would like to express my heartfelt gratitude to Kamila Jankowska and Wei Hong Lim for their invaluable assistance in collecting essential resources for this study. Their support was indispensable, especially as it was challenging for me to download all the necessary materials independently. I dedicate this work to the one who gives meaning to my life and inspires me to persevere even in moments of frustration, my son, Lokmane. Remembering that he needs me motivates me to keep going and give my best. Lastly, I hope that this review study will serve as a useful resource for students, academics, and researchers, contributing meaningfully to the field.

Conflicts of Interest

The author declares no conflicts of interest.

Abbreviations

ACV-DHOAAdaptive Coefficient Vector-based Deer Hunting Optimization Algorithm
AdamAdaptive Moment Estimation
AFDFAdaptive Fuzzy Deformable Fusion
AFMS-NetAdaptive Feature Medical Segmentation Network
AFSOArtificial Fish Swarm Optimization
AHCN-LNQAdaptive Histogram Contrast Normalization with Learning-based Neural Quantization
ALOAnt-Lion Optimization
ARKFCMAdaptively Regularized Kernel-Based Fuzzy C-Means
ASMEAngular Second Momentum and Entropy
AWFAdaptive Wiener Filtering
BDWCNNBayesian Depth-Wise CNN
BFCBayesianFuzzy Clustering
BiFPNBi-directional Feature Pyramid Network
Bi-MGLCMBi-directional Modified GLCM
BTPBrain-Tumor-Progression
BraTSBrain Tumor Segmentation
CBAMConvolutional Block Attention Module
CDLLCConvolutional Dictionary Learning with Local Constraint
CE-MRIContrast Enhanced Magnetic Resonance Imaging
CLAHEContrast-Limited Adaptive Histogram Equalization
CNNsConvolutional Neural Networks
CWCSOChaotic Whale Cat Swarm Optimization
DNNDeep Neural Network
DWADeep Watershed Autoencoders
DLCRDeep Learning Cascade Regression
DRNDeep Residual Networks
DSCDice Similarity Coefficient
DTDecision Tree
DWTDiscrete Wavelet Transform
ECKCEuropean Cyber-Knife Center
EHDMOHybrid Dwarf Mongoose Optimization
ELMExtreme Learning Machine
ELM-LRFELM with Local Receptive Fields
FESAEFeature Enhanced Stacked Autoencoder
FPFCFractional Probabilistic Fuzzy Clustering
FCFractional Calculus
FCNsFully Convolutional Networks
GANsGenerative Adversarial Networks
GAGenetic Algorithm
GATE-CNNGraph Attention Autoencoder-CNN
GBMGlioblastoma Multiforme
GGLGroup Lasso
GLCMGray-Level Co-occurrence Matrix
GLRGraph Laplacian Regularization
GMCNNGabor-modulated CNN
GNGroup Normalization
GMMGaussian Mixture Model
Grad-CAMGradient-weighted Class Activation Mapping
GRUsGated Recurrent Units
HOGHistogram of Oriented Gradients
IAIInterpretable AI
IoTInternet of Things
IoUIntersection over Union
ISLESIschemic Stroke Lesion Segmentation
JOAJaya Optimization Algorithm
KNNK-Nearest Neighbor
LBPLocal Binary Pattern
LDALinear Discriminant Analysis
LoGLaplacian of Gaussian
LSTMLong Short-Term Memory
MICCAIMedical Image Computing and Computer-Assisted Intervention conference
MRIMagnetic Resonance Imaging
MMGANMulti-Modal Generative Adversarial Network
MS-SSIMMulti-Scale Structural Similarity Index Measure
PCAPrincipal Component Analysis
PSOParticle Swarm Optimization
PODProper Orthogonal Decomposition
QTbMPAQuantum Theory-based Marine Predator Algorithm
RFRandom Forest
ResNetResidual Network architecture
REMBRANDTRepository of Molecular Brain Neoplasia Data
RNNsRecurrent Neural Networks
RPNsRegion Proposal Networks
ROIRegion Of Interest
SAMSegment Anything Model
SAEBSingle Adaptive Encoder Block
SGDMStochastic Gradient Descent Method
SHAPSHapley Additive exPlanations
ShCNNShepherd CNN
SLOOPSignificant Local Optimal Oriented Pattern
SMOTESynthetic Minority Oversampling Technique
SVMSupport Vector Machine
SVM-RBFSVM with Radial Basis Function
SPPF+Spatial Pyramid Pooling Fast+
STScattering Transform
TCGA-GBMThe Cancer Genome Atlas Glioblastoma Multiforme
TCGA-LGGThe Cancer Genome Atlas Low Grade Glioma
T1-WCEMRIT1-weighted contrast-enhanced MRI
VAEsVariational Autoencoders
ViTslightweight Vision Transformers
VGGVisual Geometry Group architecture
WPTEWavelet Packet Tsallis Entropy
XAIeXplainable AI

References

  1. Martucci, M.; Russo, R.; Schimperna, F.; D’Apolito, G.; Panfili, M.; Grimaldi, A.; Perna, A.; Ferranti, A.M.; Varcasia, G.; Giordano, C.; et al. Magnetic Resonance Imaging of Primary Adult Brain Tumors: State of the Art and Future Perspectives. Biomedicines 2023, 11, 364. [Google Scholar] [CrossRef] [Scilit]
  2. Ghandour, F.; Squassina, A.; Karaky, R.; Diab-Assaf, M.; Fadda, P.; Pisanu, C. Presenting Psychiatric and Neurological Symptoms and Signs of Brain Tumors before Diagnosis: A Systematic Review. Brain Sci. 2021, 11, 301. [Google Scholar] [CrossRef] [Scilit]
  3. Chieffo, D.P.R.; Lino, F.; Ferrarese, D.; Belella, D.; Della Pepa, G.M.; Doglietto, F. Brain Tumor at Diagnosis: From Cognition and Behavior to Quality of Life. Diagnostics 2023, 13, 541. [Google Scholar] [CrossRef] [Scilit]
  4. Mukherjee, T.; Pournik, O.; Lim Choi Keung, S.N.; Arvanitis, T.N. Clinical Decision Support Systems for Brain Tumour Diagnosis and Prognosis: A Systematic Review. Cancers 2023, 15, 3523. [Google Scholar] [CrossRef] [Scilit]
  5. Tandel, G.S.; Biswas, M.; Kakde, O.G.; Tiwari, A.; Suri, H.S.; Turk, M.; Laird, J.R.; Asare, C.K.; 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] [Scilit]
  6. Mo, F.; Pellerino, A.; Soffietti, R.; Rudà, R. Blood-Brain Barrier in Brain Tumors: Biology and Clinical Relevance. Int. J. Mol. Sci. 2021, 22, 12654. [Google Scholar] [CrossRef] [Scilit] [PubMed]
  7. Jelski, W.; Mroczko, B. Molecular and Circulating Biomarkers of Brain Tumors. Int. J. Mol. Sci. 2021, 22, 7039. [Google Scholar] [CrossRef] [Scilit] [PubMed]
  8. Yamanaka, R.; Abe, E.; Sato, T.; Hayano, A.; Takashima, Y. Secondary Intracranial Tumors Following Radiotherapy for Pituitary Adenomas: A Systematic Review. Cancers 2017, 8, 103. [Google Scholar] [CrossRef] [Scilit] [PubMed]
  9. Laudicella, R.; Albano, D.; Annunziata, S.; Calabrò, D.; Argiroffi, G.; Abenavoli, E.; Linguanti, F.; Albano, D.; Vento, A.; Bruno, A.; et al. Theragnostic Use of Radiolabelled Dota-Peptides in Meningioma: From Clinical Demand to Future Applications. Cancers 2019, 11, 1412. [Google Scholar] [CrossRef] [Scilit]
  10. Di Nunno, V.; Giannini, C.; Asioli, S.; Conti, A.; Furtner, J.; Balestrini, D.; Tosoni, A. Diagnostic and Therapeutic Strategy in Anaplastic (Malignant) Meningioma, CNS WHO Grade 3. Cancers 2022, 14, 4689. [Google Scholar] [CrossRef] [Scilit]
  11. Crainic, N.; Furtner, J.; Pallud, J.; Bielle, F.; Lombardi, G.; Rudà, R.; Idbaih, A. Rare Neuronal, Glial and Glioneuronal Tumours in Adults. Cancers 2023, 15, 1120. [Google Scholar] [CrossRef] [Scilit]
  12. Toader, C.; Dobrin, N.; Tataru, C.I.; Covache-Busuioc, R.A.; Bratu, B.G.; Costin, H.P.; Corlatescu, A.D.; Dumitrascu, D.I.; Ciurea, A.V. From Genes to Therapy: Pituitary Adenomas in the Era of Precision Medicine. Biomedicines 2023, 12, 23. [Google Scholar] [CrossRef] [Scilit]
  13. Costanzo, R.; Rosetti, V.; Tomassini, A.; Fuschillo, D.; Lofrese, G.; Iacopino, D.G.; Tosatto, L.; D’Andrea, M. Hypothalamic Hemangioma-like Pilocytic Astrocytoma in an Adult Patient: A Systematic Review with a Focus on Differential Diagnosis and Neurological. J. Clin. Med. 2024, 13, 3536. [Google Scholar] [CrossRef] [Scilit]
  14. Walter, F.M.; Penfold, C.; Joannides, A.; Saji, S.; Price, S.J.; Johnson, M.; Watts, C.; Brodbelt, A.; Jenkinson, M.D.; Hamilton, W.; et al. Missed Opportunities for Diagnosing Brain Tumours in Primary Care: A Qualitative Study of Patient Experiences. Br. J. Gen. Pract. 2019, 69, E224–E234. [Google Scholar] [CrossRef] [Scilit] [PubMed]
  15. Gurney, J.G.; Kadan-Lottick, N. Brain and Other Central Nervous System Tumors: Rates, Trends, and Epidemiology. Curr. Opin. Oncol. 2001, 13, 160–166. [Google Scholar] [CrossRef] [Scilit]
  16. Gatto, N.M.; Ogata, P.; Lytle, B. Farming, Pesticides, and Brain Cancer: A 20-Year Updated Systematic Literature Review and Meta-Analysis. Cancers 2021, 13, 4477. [Google Scholar] [CrossRef] [Scilit] [PubMed]
  17. Elshaikh, B.G.; Omer, H.; Sulieman, A.; Garelnabi, M.; Abdella, N.; Algadi, S.; Toufig, H. Incidence, Diagnosis and Treatment of Brain Tumours. Artic. J. Res. Med. Dent. Sci. 2021, 9, 340–347. [Google Scholar]
  18. Raghavapudi, H.; Singroul, P.; Kohila, V. Brain Tumor Causes, Symptoms, Diagnosis and Radiotherapy Treatment. Curr. Med. Imaging Former. Curr. Med. Imaging Rev. 2021, 17, 931–942. [Google Scholar] [CrossRef] [Scilit] [PubMed]
  19. Castro, M.G.; Cowen, R.; Williamson, I.K.; David, A.; Jimenez-Dalmaroni, M.J.; Yuan, X.; Bigliari, A.; Williams, J.C.; Hu, J.; Lowenstein, P.R. Current and Future Strategies for the Treatment of Malignant Brain Tumors. Pharmacol. Ther. 2003, 98, 71–108. [Google Scholar] [CrossRef] [Scilit]
  20. Khatua, S.; Jalali, R. Recent Advances in the Treatment of Childhood Brain Tumors. Pediatr. Hematol. Oncol. 2005, 22, 361–371. [Google Scholar] [CrossRef] [Scilit] [PubMed]
  21. Shahpar, S.; Mhatre, P.V.; Huang, M.E. Update on Brain Tumors: New Developments in Neuro-Oncologic Diagnosis and Treatment, and Impact on Rehabilitation Strategies. PM&R 2016, 8, 678–689. [Google Scholar] [CrossRef] [Scilit]
  22. Curry, W.T.; Barker, F.G. Racial, Ethnic and Socioeconomic Disparities in the Treatment of Brain Tumors. J. Neurooncol. 2009, 93, 25–39. [Google Scholar] [CrossRef] [Scilit] [PubMed]
  23. Lang, F.F.; Sawaya, R. Surgical Treatment of Metastatic Brain Tumors. Semin. Surg. Oncol. 1998, 14, 53–63. [Google Scholar] [CrossRef]
  24. Lang, S.; Beslow, L.A.; Gabel, B.; Judkins, A.R.; Fisher, M.J.; Sutton, L.N.; Storm, P.B. Surgical Treatment of Brain Tumors in Infants Less than 6 Months of Age and Literature Review; d3b.center. World Neurosurg. 2011, 78, 137. [Google Scholar] [CrossRef] [Scilit]
  25. Musina, G.R.; Nikitin, P.V.; Chernomyrdin, N.V.; Dolganova, I.N.; Gavdush, A.A.; Komandin, G.A.; Ponomarev, D.S.; Potapov, A.A.; Reshetov, I.V.; Tuchin, V.V.; et al. Prospects of Terahertz Technology in Diagnosis of Human Brain Tumors—A Review. J. Biomed. Photonics Eng. 2020, 6, 020201. [Google Scholar] [CrossRef] [Scilit]
  26. Soleman, J.; Dvir, R.; Ben-Sira, L.; Yalon, M.; Boop, F.; Constantini, S.; Roth, J. MRI-Based Diagnosis and Treatment of Pediatric Brain Tumors: Is Tissue Sample Always Needed? Child’s Nerv. Syst. 2021, 37, 1449–1459. [Google Scholar] [CrossRef] [Scilit]
  27. Salman, M.; Das, P.K.; Mohanty, S.K. A Systematic Review on Recent Advancements in Deep Learning and Mathematical Modeling for Efficient Detection of Glioblastoma. IEEE Trans. Instrum. Meas. 2024, 73, 2533134. [Google Scholar] [CrossRef] [Scilit]
  28. Song, G.; Xie, G.; Nie, Y.; Majid, M.S.; Yavari, I. Noninvasive Grading of Glioma Brain Tumors Using Magnetic Resonance Imaging and Deep Learning Methods. J. Cancer Res. Clin. Oncol. 2023, 149, 16293–16309. [Google Scholar] [CrossRef] [Scilit] [PubMed]
  29. Zakeri, Y.; Karasfi, B.; Jalalian, A. A Review of Brain Tumor Segmentation Using MRIs from 2019 to 2023 (Statistical Information, Key Achievements, and Limitations). J. Med. Biol. Eng. 2024, 44, 155–180. [Google Scholar] [CrossRef] [Scilit]
  30. Rasool, N.; Bhat, J.I. Brain Tumour Detection Using Machine and Deep Learning: A Systematic Review; Springer: New York, NY, USA, 2024; ISBN 0123456789. [Google Scholar]
  31. Soomro, T.A.; Zheng, L.; Afifi, A.J.; Ali, A.; Soomro, S.; Yin, M.; Gao, J. Image Segmentation for MR Brain Tumor Detection Using Machine Learning: A Review. IEEE Rev. Biomed. Eng. 2023, 16, 70–90. [Google Scholar] [CrossRef] [Scilit]
  32. Sharma, A.K.; Nandal, A.; Dhaka, A.; Dixit, R. A Survey on Machine Learning Based Brain Retrieval Algorithms in Medical Image Analysis. Health Technol. 2020, 10, 1359–1373. [Google Scholar] [CrossRef] [Scilit]
  33. Hameurlaine, M.; Moussaoui, A. Survey of Brain Tumor Segmentation Techniques on Magnetic Resonance Imaging. Nano Biomed. Eng. 2019, 11, 178–191. [Google Scholar] [CrossRef] [Scilit]
  34. Al-Galal, S.A.Y.; Alshaikhli, I.F.T.; Abdulrazzaq, M.M. MRI Brain Tumor Medical Images Analysis Using Deep Learning Techniques: A Systematic Review. Health Technol. 2021, 11, 267–282. [Google Scholar] [CrossRef] [Scilit]
  35. Ranjbarzadeh, R.; Caputo, A.; Tirkolaee, E.B.; Jafarzadeh Ghoushchi, S.; Bendechache, M. Brain Tumor Segmentation of MRI Images: A Comprehensive Review on the Application of Artificial Intelligence Tools. Comput. Biol. Med. 2023, 152, 106405. [Google Scholar] [CrossRef] [Scilit] [PubMed]
  36. Nadeem, M.W.; Ghamdi, M.A.A.; Hussain, M.; Khan, M.A.; Khan, K.M.; Almotiri, S.H.; Butt, S.A. Brain Tumor Analysis Empowered with Deep Learning: A Review, Taxonomy, and Future Challenges. Brain Sci. 2020, 10, 118. [Google Scholar] [CrossRef] [Scilit]
  37. Harzing, A.-W. Publish or Perish. 2007. Available online: https://harzing.com/resources/publish-or-perish (accessed on 17 October 2024).
  38. Menze, B.H.; Jakab, A.; Bauer, S.; Kalpathy-Cramer, J.; Farahani, K.; Kirby, J.; Burren, Y.; Porz, N.; Slotboom, J.; Wiest, R.; et al. The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS). IEEE Trans. Med. Imaging 2015, 34, 1993–2024. [Google Scholar] [CrossRef] [Scilit]
  39. Bakas, S.; Akbari, H.; Sotiras, A.; Bilello, M.; Rozycki, M.; Kirby, J.S.; Freymann, J.B.; Farahani, K.; Davatzikos, C. Advancing The Cancer Genome Atlas Glioma MRI Collections with Expert Segmentation Labels and Radiomic Features. Sci. Data 2017, 4, 170117. [Google Scholar] [CrossRef] [Scilit] [PubMed]
  40. Bakas, S.; Reyes, M.; Jakab, A.; Bauer, S.; Rempfler, M.; Crimi, A.; Shinohara, R.T.; Berger, C.; Ha, S.M.; Rozycki, M.; et al. Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challenge. arXiv 2018, arXiv:1811.02629. [Google Scholar]
  41. Biomedical Image Analysis Group, Imperial College London. IXI Dataset Portal. 2023. Available online: https://brain-development.org/ (accessed on 28 October 2024).
  42. Hernandez Petzsche, M.R.; de la Rosa, E.; Hanning, U.; Wiest, R.; Valenzuela, W.; Reyes, M.; Meyer, M.; Liew, S.-L.; Kofler, F.; Ezhov, I.; et al. ISLES 2022: A Multi-Center Magnetic Resonance Imaging Stroke Lesion Segmentation Dataset. Sci. Data 2022, 9, 762. [Google Scholar] [CrossRef] [Scilit] [PubMed]
  43. Cocosco, C.A.; Kollokian, V.; Kwan, R.K.S.; Evans, A.C. Brain Web: Online Interface to a 3D MRI Simulated Brain Database. Neuroimage 1997, 5. [Google Scholar]
  44. Scarpace, L.; Mikkelsen, T.; Cha, S.; Rao, S.; Tekchandani, S.; Gutman, D.; Saltz, J.H.; Erickson, B.J.; Pedano, N.; Flanders, A.E.; et al. The Cancer Genome Atlas Glioblastoma Multiforme Collection (TCGA-GBM) (Version 5). In The Cancer Imaging Archive; National Cancer Institute: Bethesda, MD, USA, 2016. [Google Scholar] [CrossRef] [Scilit]
  45. Pedano, N.; Flanders, A.E.; Scarpace, L.; Mikkelsen, T.; Eschbacher, J.M.; Hermes, B.; Sisneros, V.; Barnholtz-Sloan, J.; Ostrom, Q. Radiology Data from The Cancer Genome Atlas Low Grade Glioma [TCGA-LGG] Collection. In The Cancer Imaging Archive; National Cancer Institute: Bethesda, MD, USA, 2016. [Google Scholar]
  46. De Souza, D.L.; Coelho, A.M.; Felipe, J.C.; De Freitas Oliveira Baffa, M. Brain Tumor Classification on Multi-Modality MRI Using Radiomic Features. In Proceedings of the 2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), Houston, TX, USA, 9–12 December 2021; pp. 1799–1804. [Google Scholar] [CrossRef] [Scilit]
  47. More, S.S.; Mange, M.A.; Sankhe, M.S.; Sahu, S.S. Convolutional Neural Network Based Brain Tumor Detection. In Proceedings of the 2021 5th International Conference on Intelligent Computing and Control Systems (ICICCS), Madurai, India, 6–8 May 2021; pp. 1532–1538. [Google Scholar] [CrossRef] [Scilit]
  48. Jaisingh, W.; Kavitha, R.K.; Saravanan, S.; Gour, R. Automated Detection of Brain Abnormalities in MRI Images Using Integrated Deep Convolutional Neural Networks with K-Means Algorithm. In Proceedings of the 2022 IEEE 3rd Global Conference for Advancement in Technology (GCAT), Bangalore, India, 7–9 October 2022; pp. 1–4. [Google Scholar] [CrossRef] [Scilit]
  49. Patil, S.; Kirange, D. Ensemble of Deep Learning Models for Brain Tumor Detection. Procedia Comput. Sci. 2022, 218, 2468–2479. [Google Scholar] [CrossRef] [Scilit]
  50. Saini, H.; Ansari, M.A. A Review of Current Trends in Deep Learning Models for Detecting and Segmenting Brain Tumours. AIP Conf. Proc. 2023, 2721, 010001. [Google Scholar] [CrossRef] [Scilit]
  51. Srivastava, U.P. A Comparative Study of Deep Learning Algorithms in Classifying Brain Cancer. In Proceedings of the 2023 14th International Conference on Computing Communication and Networking Technologies (ICCCNT), Delhi, India, 6–8 July 2023; pp. 1–6. [Google Scholar] [CrossRef] [Scilit]
  52. Sneha, Y.; Roopa, Y.M.; Sawant, P.; Rao, M.V.; Padmaja, D.L.; Lalitha, R.V.S. Advancements in Brain Tumor Detection Using Machine Learning Applications from MRI Image Analysis. In Proceedings of the 2023 7th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC), Kirtipur, Nepal, 11–13 October 2023; pp. 809–814. [Google Scholar] [CrossRef] [Scilit]
  53. Bhuvaji, S. Brain Tumor Classification MRI. 2023. Available online: https://www.kaggle.com/datasets/sartajbhuvaji/brain-tumor-classification-mri (accessed on 7 October 2024).
  54. Oliveira, F.H.M.; Machado, A.R.P.; Andrade, A.O. On the Use of T-Distributed Stochastic Neighbor Embedding for Data Visualization and Classification of Individuals with Parkinson’s Disease. Comput. Math Methods Med. 2018, 2018, 8019232. [Google Scholar] [CrossRef] [Scilit] [PubMed]
  55. Li, X.; Li, C.; Rahaman, M.M.; Sun, H.; Li, X.; Wu, J.; Yao, Y.; Grzegorzek, M. A Comprehensive Review of Computer-Aided Whole-Slide Image Analysis: From Datasets to Feature Extraction, Segmentation, Classification and Detection Approaches. Artif. Intell. Rev. 2022, 55, 4809–4878. [Google Scholar] [CrossRef] [Scilit]
  56. Thomas, A.L.; Judith, J.E. A Comprehensive Analysis of Feature Extraction Techniques for Human Activity Recognition Using Deep Learning. In Proceedings of the International Conference on Circuit, Power and Computing Technologies (ICCPCT) 2024, Kollam, India, 8–9 August 2024; pp. 1876–1882. [Google Scholar] [CrossRef] [Scilit]
  57. Pithadia, N.J.; Nimavat, V.D. A Review on Feature Extraction Techniques. Int. J. Innov. Res. Comput. Commun. Eng. 2015, 3, 1263–1268. [Google Scholar]
  58. Jalali, V.; Kaur, D. A Study of Classification and Feature Extraction Techniques for Brain Tumor Detection. Int. J. Multimed. Inf. Retr. 2020, 9, 271–290. [Google Scholar] [CrossRef] [Scilit]
  59. Amin, J.; Sharif, M.; Yasmin, M.; Saba, T.; Anjum, M.A.; Fernandes, S.L. A New Approach for Brain Tumor Segmentation and Classification Based on Score Level Fusion Using Transfer Learning. J. Med. Syst. 2019, 43, 326. [Google Scholar] [CrossRef] [Scilit] [PubMed]
  60. Swati, Z.N.K.; Zhao, Q.; Kabir, M.; Ali, F.; Ali, Z.; Ahmed, S.; Lu, J. Brain Tumor Classification for MR Images Using Transfer Learning and Fine-Tuning. Comput. Med. Imaging Graph. 2019, 75, 34–46. [Google Scholar] [CrossRef] [Scilit]
  61. Towner, R.A.; Smith, N.; Saunders, D.; Van Gordon, S.B.; Wisniewski, A.B.; Tyler, K.R.; Greenwood-Van Meerveld, B.; Hurst, R.E. Contrast Enhanced Magnetic Resonance Imaging as a Diagnostic Tool to Assess Bladder Permeability and Associated Colon Cross Talk: Preclinical Studies in a Rat Model. J. Urol. 2015, 193, 1394–1400. [Google Scholar] [CrossRef] [Scilit] [PubMed]
  62. Murugan, A.; Harsha, R. Detection of Brain Tumor with Cellular Automata and Convolutional Neural Networks. Indian J. Public Health Res. Dev. 2019, 10, 1064–1069. [Google Scholar] [CrossRef] [Scilit]
  63. Kumar, V.V.; Krishna, K.S.; Kusumavathi, S. Genetic Algorithm Based Feature Selection Brain Tumour Segmentation and Classification. Int. J. Intell. Eng. Syst. 2019, 12, 214–223. [Google Scholar] [CrossRef] [Scilit]
  64. Ruba, T.; Tamilselvi, R.; Parisa Beham, M.; Aparna, N. Accurate Classification and Detection of Brain Cancer Cells in MRI and CT Images Using Nano Contrast Agents. Biomed. Pharmacol. J. 2020, 13, 1227–1237. [Google Scholar] [CrossRef] [Scilit]
  65. Dikici, E.; Ryu, J.L.; Demirer, M.; Bigelow, M.; White, R.D.; Slone, W.; Erdal, B.S.; Prevedello, L.M. Automated Brain Metastases Detection Framework for T1-Weighted Contrast-Enhanced 3D MRI. IEEE J. Biomed. Health Inform. 2020, 24, 2883–2893. [Google Scholar] [CrossRef] [Scilit] [PubMed]
  66. Khan, H.A.; Jue, W.; Mushtaq, M.; Mushtaq, M.U. Brain Tumor Classification in MRI Image Using Convolutional Neural Network. Math. Biosci. Eng. 2020, 17, 6203–6216. [Google Scholar] [CrossRef] [Scilit]
  67. Siva Raja, P.M.; Rani, A.V. Brain Tumor Classification Using a Hybrid Deep Autoencoder with Bayesian Fuzzy Clustering-Based Segmentation Approach. Biocybern. Biomed. Eng. 2020, 40, 440–453. [Google Scholar] [CrossRef] [Scilit]
  68. Windisch, P.; Weber, P.; Fürweger, C.; Ehret, F.; Kufeld, M.; Zwahlen, D.; Muacevic, A. Implementation of Model Explainability for a Basic Brain Tumor Detection Using Convolutional Neural Networks on MRI Slices. Neuroradiology 2020, 62, 1515–1518. [Google Scholar] [CrossRef] [Scilit]
  69. Hasan, M.H.; Hasan, H.S.; Hasan, A.M. MRI Brain Scans Classification Using Bi-Directional Modified Gray Level Co-Occurrence Matrix and Long Short-Term Memory. NeuroQuantology 2020, 18, 54–63. [Google Scholar] [CrossRef] [Scilit]
  70. El Kader, I.A.; Xu, G.; Shuai, Z.; Saminu, S. Brain Tumor Detection and Classification by Hybrid CNN-DWA Model Using MR Images. Curr. Med. Imaging Former. Curr. Med. Imaging Rev. 2021, 17, 1248–1255. [Google Scholar] [CrossRef] [Scilit] [PubMed]
  71. Gu, X.; Shen, Z.; Xue, J.; Fan, Y.; Ni, T. Brain Tumor MR Image Classification Using Convolutional Dictionary Learning with Local Constraint. Front. Neurosci. 2021, 15, 679847. [Google Scholar] [CrossRef] [Scilit]
  72. Scarpace, L.; Flanders, A.; Jain, R.; Mikkelsen, T.; Andrews, D. Data from REMBRANDT. Version 1. Cancer Imaging Arch. 2015. [Google Scholar]
  73. Singh, R.; Goel, A.; Raghuvanshi, D.K. Computer-Aided Diagnostic Network for Brain Tumor Classification Employing Modulated Gabor Filter Banks. Vis. Comput. 2021, 37, 2157–2171. [Google Scholar] [CrossRef] [Scilit]
  74. Guo, K.; Li, X.; Hu, X.; Liu, J.; Fan, T. Hahn-PCNN-CNN: An End-to-End Multi-Modal Brain Medical Image Fusion Framework Useful for Clinical Diagnosis. BMC Med. Imaging 2021, 21, 111. [Google Scholar] [CrossRef] [Scilit]
  75. Haq, E.U.; Jianjun, H.; Huarong, X.; Li, K.; Weng, L. A Hybrid Approach Based on Deep CNN and Machine Learning Classifiers for the Tumor Segmentation and Classification in Brain MRI. Comput. Math. Methods Med. 2022, 2022, 6446680. [Google Scholar] [CrossRef] [Scilit] [PubMed]
  76. Ananda Kumar, K.S.; Prasad, A.Y.; Metan, J. A Hybrid Deep CNN-Cov-19-Res-Net Transfer Learning Architype for an Enhanced Brain Tumor Detection and Classification Scheme in Medical Image Processing. Biomed. Signal Process. Control 2022, 76, 103631. [Google Scholar] [CrossRef] [Scilit]
  77. Murthy, M.Y.B.; Koteswararao, A.; Babu, M.S. Adaptive Fuzzy Deformable Fusion and Optimized CNN with Ensemble Classification for Automated Brain Tumor Diagnosis. Biomed. Eng. Lett. 2022, 12, 37–58. [Google Scholar] [CrossRef] [Scilit] [PubMed]
  78. Ekong, F.; Yu, Y.; Patamia, R.A.; Feng, X.; Tang, Q.; Mazumder, P.; Cai, J. Bayesian Depth-Wise Convolutional Neural Network Design for Brain Tumor MRI Classification. Diagnostics 2022, 12, 1657. [Google Scholar] [CrossRef] [Scilit] [PubMed]
  79. Thanuj, M.; Teja, P.R.; Stun, P.J.D.L.; Kranthi Kumar, K.; Sudha Kishore, R. Brain Tumour Detection Using Deep Learning Techniques. In Proceedings of the 5th International Conference on Inventive Research in Computing Applications (ICIRCA 2023), Coimbatore, India, 3–5 August 2023; pp. 487–492. [Google Scholar] [CrossRef] [Scilit]
  80. Potnurwar, A.; Chaudhari, A.; Burbure, N.; Wankhede, K.; Badkhal, K.; Parshatwar, A. Brain Tumor Segmentation on MRI Images. Int. Conf. Emerg. Trends Eng. Technol. ICETET 2023, 2023, 1–6. [Google Scholar] [CrossRef] [Scilit]
  81. Solanki, S.; Singh, U.P.; Chouhan, S.S. Brain Tumor Classification Using ML and DL Approaches. In Proceedings of the 2023 IEEE 5th International Conference on Cybernetics, Cognition and Machine Learning Applications (ICCCMLA), Hamburg, Germany, 7–8 October 2023; pp. 204–208. [Google Scholar] [CrossRef] [Scilit]
  82. Sekar, R.; Harikrishnan, P.R.; Acharjya, K. Brain Image Segmentation via GLCM Features and CNN Classification for Improved Image Retrieval Using Machine Learning. In Proceedings of the 2023 IEEE International Conference on ICT in Business Industry & Government (ICTBIG), Indore, India, 8–9 December 2023; pp. 1–6. [Google Scholar] [CrossRef] [Scilit]
  83. Rajesh, S.M.; Chiranmai, I.; Jayapandian, N. Artificial Intelligence and Deep Learning Based Brain Tumor Detection Using Image Processing. In Proceedings of the 2023 IEEE International Conference on ICT in Business Industry & Government (ICTBIG), Indore, India, 8–9 December 2023; pp. 244–248. [Google Scholar] [CrossRef] [Scilit]
  84. Jayadharshini, P.; Abinaya, N.; Rithanya, G.; Bhavatharini, N.; Balaji, V.; Madhavan, T. Advancing Brain Tumor Diagnosis through Machine Learning and the Power of Combined CNN and RNN in Medical Imaging. In Proceedings of the 2023 IEEE International Conference on ICT in Business Industry & Government (ICTBIG), Indore, India, 8–9 December 2023; pp. 1–8. [Google Scholar] [CrossRef] [Scilit]
  85. Gangadharan, S.M.P.; Dharani, M.; Thapliyal, N.; Yamsani, N.; Singh, J.; Singh, P. Comparative Analysis of Deep Learning-Based Brain Tumor Prediction Models Using MRI Scan. In Proceedings of the 2023 3rd International Conference on Innovative Sustainable Computational Technologies (CISCT), Dehradun, India, 8–9 September 2023; pp. 1–6. [Google Scholar] [CrossRef] [Scilit]
  86. Berghout, T. Dynamic Visualization of ResNet Layer Activations for Brain Health Classification 2024, Version V1; Zenodo: Geneva, Switzerland, 2024. [Google Scholar]
  87. Iqbal, S. Computer-Assisted Brain Tumor Type Discrimination Using Magnetic Resonance Imaging Features. Biomed. Eng. Lett. 2018, 8, 5–28. [Google Scholar] [CrossRef] [Scilit] [PubMed]
  88. Hoopes, A. SynthStrip: Skull-Stripping for Any Brain Image. Neuroimage 2022, 260, 119474. [Google Scholar] [CrossRef] [Scilit] [PubMed]
  89. Chaddad, A. Quantitative Evaluation of Robust Skull Stripping and Tumor Detection Applied to Axial MR Images. Brain Inform. 2016, 3, 53–61. [Google Scholar] [CrossRef] [Scilit] [PubMed]
  90. Basheera, S. Gray Matter Segmentation of Brain MRI Using Hybrid Enhanced Independent Component Analysis. Int. J. Image Graph. 2021, 21, 2150029. [Google Scholar] [CrossRef] [Scilit]
  91. Ahmad, B.; Sun, J.; You, Q.; Palade, V.; Mao, Z. Brain Tumor Classification Using a Combination of Variational Autoencoders and Generative Adversarial Networks. Biomedicines 2022, 10, 223. [Google Scholar] [CrossRef] [Scilit] [PubMed]
  92. Kothari, S.; Chiwhane, S.; Jain, S.; Baghel, M. Cancerous Brain Tumor Detection Using Hybrid Deep Learning Framework. Indones. J. Electr. Eng. Comput. Sci. 2022, 27, 1651–1661. [Google Scholar] [CrossRef] [Scilit]
  93. Kazemi, A.; Shiri, M.E.; Sheikhahmadi, A.; khodamoradi, M. Classifying Tumor Brain Images Using Parallel Deep Learning Algorithms. Comput. Biol. Med. 2022, 148, 105775. [Google Scholar] [CrossRef] [Scilit] [PubMed]
  94. Alqazzaz, S.; Sun, X.; Nokes, L.D.; Yang, H.; Yang, Y.; Xu, R.; Zhang, Y.; Yang, X. Combined Features in Region of Interest for Brain Tumor Segmentation. J. Digit. Imaging 2022, 35, 938–946. [Google Scholar] [CrossRef] [Scilit]
  95. Munir, K.; Frezza, F.; Rizzi, A. Deep Learning Hybrid Techniques for Brain Tumor Segmentation. Sensors 2022, 22, 8201. [Google Scholar] [CrossRef] [Scilit]
  96. Srinivas, C.; Nandini, N.P.; Zakariah, M.; Alothaibi, Y.A.; Shaukat, K.; Partibane, B.; Awal, H. Deep Transfer Learning Approaches in Performance Analysis of Brain Tumor Classification Using MRI Images. J. Healthc. Eng. 2022, 2022, 3264367. [Google Scholar] [CrossRef] [Scilit]
  97. Ramamoorthy, M.; Qamar, S.; Manikandan, R.; Jhanjhi, N.Z.; Masud, M.; Alzain, M.A. Earlier Detection of Brain Tumor by Pre-Processing Based on Histogram Equalization with Neural Network. Healthcare 2022, 10, 1218. [Google Scholar] [CrossRef] [Scilit] [PubMed]
  98. Alsubai, S.; Khan, H.U.; Alqahtani, A.; Sha, M.; Abbas, S.; Mohammad, U.G. Ensemble Deep Learning for Brain Tumor Detection. Front. Comput. Neurosci. 2022, 16, 1005617. [Google Scholar] [CrossRef] [Scilit]
  99. Maqsood, S.; Damaševičius, R.; Maskeliūnas, R. Multi-Modal Brain Tumor Detection Using Deep Neural Network and Multiclass SVM. Medicina 2022, 58, 1090. [Google Scholar] [CrossRef] [Scilit]
  100. Jemimma, T.A.; Raj, Y.J.V. Significant LOOP with Clustering Approach and Optimization Enabled Deep Learning Classifier for the Brain Tumor Segmentation and Classification. Multimed. Tools Appl. 2022, 81, 2365–2391. [Google Scholar] [CrossRef] [Scilit]
  101. Sait, A.R.W.; Ishak, M.K. A Novel Handcrafted with Deep Features Based Brain Tumor Diagnosis Model. Intell. Autom. Soft Comput. 2023, 35, 2057–2070. [Google Scholar] [CrossRef] [Scilit]
  102. Deepak, V.K.; Sarath, R. An Intelligent Brain Tumor Segmentation Using Improved Deep Learning Model Based on Cascade Regression Method. Multimed. Tools Appl. 2023, 82, 20059–20078. [Google Scholar] [CrossRef] [Scilit]
  103. Saha, P.; Das, R.; Das, S.K. BCM-VEMT: Classification of Brain Cancer from MRI Images Using Deep Learning and Ensemble of Machine Learning Techniques. Multimed. Tools Appl. 2023, 82, 44479–44506. [Google Scholar] [CrossRef] [Scilit]
  104. Rasheed, Z.; Ma, Y.K.; Ullah, I.; Ghadi, Y.Y.; Khan, M.Z.; Khan, M.A.; Abdusalomov, A.; Alqahtani, F.; Shehata, A.M. Brain Tumor Classification from MRI Using Image Enhancement and Convolutional Neural Network Techniques. Brain Sci. 2023, 13, 1320. [Google Scholar] [CrossRef] [Scilit]
  105. Abdusalomov, A.B.; Mukhiddinov, M.; Whangbo, T.K. Brain Tumor Detection Based on Deep Learning Approaches and Magnetic Resonance Imaging. Cancers 2023, 15, 4172. [Google Scholar] [CrossRef] [Scilit]
  106. Wu, P.; Shen, J. Brain Tumor Diagnosis Based on Convolutional Neural Network Improved by a New Version of Political Optimizer. Biomed. Signal Process. Control 2023, 85, 104853. [Google Scholar] [CrossRef] [Scilit]
  107. Butt, U.M.; Arif, R.; Letchmunan, S.; Malik, B.H.; Butt, M.A. Feature Enhanced Stacked Auto Encoder for Diseases Detection in Brain MRI. Comput. Mater. Contin. 2023, 76, 2551–2570. [Google Scholar] [CrossRef] [Scilit]
  108. Gao, L.; Li, J.; Zhang, R.; Bekele, H.H.; Wang, J.; Cheng, Y.; Deng, H. MMGan: A Multimodal MR Brain Tumor Image Segmentation Method. Front. Hum. Neurosci. 2023, 17, 1275795. [Google Scholar] [CrossRef] [Scilit] [PubMed]
  109. Zulfiqar, F.; Ijaz Bajwa, U.; Mehmood, Y. Multi-Class Classification of Brain Tumor Types from MR Images Using EfficientNets. Biomed. Signal Process. Control 2023, 84, 104777. [Google Scholar] [CrossRef] [Scilit]
  110. Khawaldeh, S.; Pervaiz, U.; Rafiq, A.; Alkhawaldeh, R.S. Noninvasive Grading of Glioma Tumor Using Magnetic Resonance Imaging with Convolutional Neural Networks. Appl. Sci. 2017, 8, 27. [Google Scholar] [CrossRef] [Scilit]
  111. Shi, X.; Li, Y.; Cheng, J.; Bai, J.; Zhao, G.; Chen, Y.W. Medical SAM: A Glioma Segmentation Fine-Tuning Method for SAM Using Brain MR Images. In Proceedings of the 2024 IEEE International Conference on Consumer Electronics, Las Vegas, NV, USA, 5–8 January 2024; pp. 1–4. [Google Scholar] [CrossRef] [Scilit]
  112. Chain, A.; Coons, L.; Ramos, A.; Richardson, K.; Danyaro, K.U.; Nepal, B.; Abdullahi, M.; Sohrab, H. Evaluation of Classification of Brain Tumors Using Convolutional Neural Network Algorithm. In Proceedings of the 2024 16th International Conference on Computer and Automation Engineering (ICCAE), Melbourne, Australia, 14–16 March 2024; pp. 328–333. [Google Scholar] [CrossRef] [Scilit]
  113. Paul, S.; Soni, B.K.; Baranidharan, B. Brain Tumour Detection Using Deep Learning Techniques. In Proceedings of the 2024 2nd International Conference on Advancement in Computation & Computer Technologies (InCACCT 2024), Gharuan, India, 2–3 May 2024; pp. 722–727. [Google Scholar] [CrossRef] [Scilit]
  114. Helen, R.; Mary Adline Priya, M.; Adhithyan, N.; Praveena, R. Brain Cancer Segmentation in MRI Using Fully Convolutional Network with the U-NET Model. In Proceedings of the 2024 5th International Conference on Innovative Trends in Information Technology (ICITIIT), Kottayam, India, 15–16 March 2024; pp. 1–6. [Google Scholar] [CrossRef] [Scilit]
  115. Montalbo, F.J.P.; Hernandez, L.R.T.; Palad, L.P.; Castillo, R.C.; Alon, A.S.; De Ocampo, A.L.P. Performance Analysis of Lightweight Vision Transformers and Deep Convolutional Neural Networks in Detecting Brain Tumors in MRI Scans: An Empirical Approach. In Proceedings of the 2023 8th International Conference on Biomedical Imaging, Signal Processing, Singapore, 20–22 October 2023; pp. 17–25. [Google Scholar] [CrossRef] [Scilit]
  116. Narang, A.; Rajpoot, A.S.; Jayaraman, R. Effective Brain Tumor Detection Using Convolutional Neural Networks. In Proceedings of the 2023 10th International Conference on Computing for Sustainable Global Development (INDIACom), New Delhi, India, 15–17 March 2023; pp. 756–760. [Google Scholar]
  117. Kim, H.E.; Cosa-Linan, A.; Santhanam, N.; Jannesari, M.; Maros, M.E.; Ganslandt, T. Transfer Learning for Medical Image Classification: A Literature Review. BMC Med. Imaging 2022, 22, 69. [Google Scholar] [CrossRef] [Scilit]
  118. Gupta, A.; Gupta, S.; Kumar, Y. A Review on Recent Deep Learning Techniques, Challenges and Its Applications for Medical Healthcare System. In Proceedings of the 2021 International Conference on Technological Advancements and Innovations (ICTAI), Tashkent, Uzbekistan, 10–12 November 2023; pp. 643–648. [Google Scholar] [CrossRef] [Scilit]
  119. Chen, X.; Wang, X.; Zhang, K.; Fung, K.M.; Thai, T.C.; Moore, K.; Mannel, R.S.; Liu, H.; Zheng, B.; Qiu, Y. Recent Advances and Clinical Applications of Deep Learning in Medical Image Analysis. Med. Image Anal. 2022, 79, 102444. [Google Scholar] [CrossRef] [Scilit] [PubMed]
  120. Kim, J.; Hong, J.; Park, H. Prospects of Deep Learning for Medical Imaging. Precis. Future Med. 2018, 2, 37–52. [Google Scholar] [CrossRef] [Scilit]
  121. Suzuki, K. Overview of Deep Learning in Medical Imaging. Radiol. Phys. Technol. 2017, 10, 257–273. [Google Scholar] [CrossRef] [Scilit] [PubMed]
  122. Ching, T.; Himmelstein, D.S.; Beaulieu-Jones, B.K.; Kalinin, A.A.; Do, B.T.; Way, G.P.; Ferrero, E.; Agapow, P.M.; Zietz, M.; Hoffman, M.M.; et al. Opportunities and Obstacles for Deep Learning in Biology and Medicine. J. R. Soc. Interface 2018, 15, 20170387. [Google Scholar] [CrossRef] [Scilit]
  123. Latif, J.; Xiao, C.; Imran, A.; Tu, S. Medical Imaging Using Machine Learning and Deep Learning Algorithms: A Review. In Proceedings of the 2019 2nd International Conference on Computing, Mathematics and Engineering Technologies (iCoMET), Sukkur, Pakistan, 30–31 January 2019. [Google Scholar] [CrossRef] [Scilit]
  124. Kalejahi, B.K.; Meshgini, S.; Danishvar, S. Segmentation of Brain Tumor Using a 3D Generative Adversarial Network. Diagnostics 2023, 13, 3344. [Google Scholar] [CrossRef] [Scilit] [PubMed]
  125. Kumar, A. Study and Analysis of Different Segmentation Methods for Brain Tumor MRI Application. Multimed. Tools Appl. 2023, 82, 7117–7139. [Google Scholar] [CrossRef] [Scilit]
  126. Papadomanolakis, T.N.; Sergaki, E.S.; Polydorou, A.A.; Krasoudakis, A.G.; Makris-Tsalikis, G.N.; Polydorou, A.A.; Afentakis, N.M.; Athanasiou, S.A.; Vardiambasis, I.O.; Zervakis, M.E. Tumor Diagnosis against Other Brain Diseases Using T2 MRI Brain Images and CNN Binary Classifier and DWT. Brain Sci. 2023, 13, 38. [Google Scholar] [CrossRef] [Scilit] [PubMed]
  127. Zaman, A.; Hassan, H.; Zeng, X.; Khan, R.; Lu, J.; Yang, H.; Miao, X.; Cao, A.; Yang, Y.; Huang, B.; et al. Adaptive Feature Medical Segmentation Network: An Adaptable Deep Learning Paradigm for High-Performance 3D Brain Lesion Segmentation in Medical Imaging. Front. Neurosci. 2024, 18, 1363930. [Google Scholar] [CrossRef] [Scilit]
  128. Ullah, M.S.; Khan, M.A.; Masood, A.; Mzoughi, O.; Saidani, O.; Alturki, N. Brain Tumor Classification from MRI Scans: A Framework of Hybrid Deep Learning Model with Bayesian Optimization and Quantum Theory-Based Marine Predator Algorithm. Front. Oncol. 2024, 14, 1335740. [Google Scholar] [CrossRef] [Scilit] [PubMed]
  129. Güler, M.; Namlı, E. Brain Tumor Detection with Deep Learning Methods’ Classifier Optimization Using Medical Images. Appl. Sci. 2024, 14, 642. [Google Scholar] [CrossRef] [Scilit]
  130. Appiah, R.; Pulletikurthi, V.; Esquivel-Puentes, H.A.; Cabrera, C.; Hasan, N.I.; Dharmarathne, S.; Gomez, L.J.; Castillo, L. Brain Tumor Detection Using Proper Orthogonal Decomposition Integrated with Deep Learning Networks. Comput. Methods Programs Biomed. 2024, 250, 108167. [Google Scholar] [CrossRef] [Scilit]
  131. Al-Otaibi, S.; Rehman, A.; Raza, A.; Alyami, J.; Saba, T. CVG-Net: Novel Transfer Learning Based Deep Features for Diagnosis of Brain Tumors Using MRI Scans. PeerJ Comput. Sci. 2024, 10, 1–24. [Google Scholar] [CrossRef] [Scilit] [PubMed]
  132. Shedbalkar, J.; Prabhushetty, K. Deep Transfer Learning Model for Brain Tumor Segmentation and Classification Using UNet and Chopped VGGNet. Indones. J. Electr. Eng. Comput. Sci. 2024, 33, 1405–1415. [Google Scholar] [CrossRef] [Scilit]
  133. Yang, Y.; Chaoluomeng; Razmjooy, N. Early Detection of Brain Tumors: Harnessing the Power of GRU Networks and Hybrid Dwarf Mongoose Optimization Algorithm. Biomed. Signal Process. Control 2024, 91, 106093. [Google Scholar] [CrossRef] [Scilit]
  134. Albalawi, E.; Mahesh, T.R.; Thakur, A.; Kumar, V.V.; Gupta, M.; Khan, S.B.; Almusharraf, A. Integrated Approach of Federated Learning with Transfer Learning for Classification and Diagnosis of Brain Tumor. BMC Med. Imaging 2024, 24, 110. [Google Scholar] [CrossRef] [Scilit] [PubMed]
  135. Saeed, T.; Khan, M.A.; Hamza, A.; Shabaz, M.; Khan, W.Z.; Alhayan, F.; Jamel, L.; Baili, J. Neuro-XAI: Explainable Deep Learning Framework Based on DeeplabV3+ and Bayesian Optimization for Segmentation and Classification of Brain Tumor in MRI Scans. J. Neurosci. Methods 2024, 410, 110247. [Google Scholar] [CrossRef] [Scilit]
  136. Parashar, B.B.; Chandra, M.; Malhotra, S. Optimizing Brain Tumor Classification Accuracy Through Transfer Learning and Internet of Things Integration. J. Intell. Syst. Internet Things 2024, 13, 151–165. [Google Scholar] [CrossRef] [Scilit]
  137. Alshuhail, A.; Thakur, A.; Chandramma, R.; Mahesh, T.R.; Almusharraf, A.; Vinoth Kumar, V.; Khan, S.B. Refining Neural Network Algorithms for Accurate Brain Tumor Classification in MRI Imagery. BMC Med. Imaging 2024, 24, 118. [Google Scholar] [CrossRef] [Scilit] [PubMed]
  138. Balasubramanian, S.; Mandala, J.; Rao, T.V.M.; Misra, A. RF-ShCNN: A Combination of Two Deep Models for Tumor Detection in Brain Using MRI. Biomed. Signal Process. Control 2024, 88, 105656. [Google Scholar] [CrossRef] [Scilit]
  139. Alhudhaif, A.; Alsubai, S.; Aseeri, A.O.; Nandal, A.; Polat, K. Spectrally Distinct Pixel Extraction and Kernel Filtering for Brain Tumour Diagnosis. Biomed. Signal Process. Control 2024, 98, 106787. [Google Scholar] [CrossRef] [Scilit]
  140. Panda, S.; Jangid, M.; Jain, A. A Comprehensive Review on the Significance and Impact of Deep Learning in Medical Image Analysis. In Proceedings of the 2021 International Conference on Technological Advancements and Innovations (ICTAI), Tashkent, Uzbekistan, 10–12 November 2021; pp. 358–366. [Google Scholar] [CrossRef] [Scilit]
  141. Li, W.; Zhang, M. Advances in Medical Imaging Technologies and Their Impact on Clinical Practices. Med. Insights 2024, 1. [Google Scholar] [CrossRef]
  142. Drabiak, K.; Kyzer, S.; Nemov, V.; El Naqa, I. AI and Machine Learning Ethics, Law, Diversity, and Global Impact. Br. J. Radiol. 2023, 96, 20220934. [Google Scholar] [CrossRef] [Scilit] [PubMed]
  143. Choy, G.; Khalilzadeh, O.; Michalski, M.; Do, S.; Samir, A.E.; Pianykh, O.S.; Geis, J.R.; Pandharipande, P.V.; Brink, J.A.; Dreyer, K.J. Current Applications and Future Impact of Machine Learning in Radiology. Radiology 2018, 288, 318–328. [Google Scholar] [CrossRef] [Scilit] [PubMed]
  144. Katran, L.F.; AlShemmary, E.N.; Al Jawher, W.A. Deep Learning’s Impact on MRI Image Analysis: A Comprehensive Survey. Tex. J. Eng. Technol. 2023, 25, 63–80. [Google Scholar]
  145. Luca, A.R.; Ursuleanu, T.F.; Gheorghe, L.; Grigorovici, R.; Iancu, S.; Hlusneac, M.; Grigorovici, A. Impact of Quality, Type and Volume of Data Used by Deep Learning Models in the Analysis of Medical Images. Inform. Med. Unlocked 2022, 29, 100911. [Google Scholar] [CrossRef] [Scilit]
  146. Salvi, M.; Acharya, U.R.; Molinari, F.; Meiburger, K.M. The Impact of Pre- and Post-Image Processing Techniques on Deep Learning Frameworks: A Comprehensive Review for Digital Pathology Image Analysis. Comput. Biol. Med. 2021, 128, 104129. [Google Scholar] [CrossRef] [Scilit] [PubMed]
  147. Kaur, V.; Goyal, M. A Review: Singly and Doubly Jpeg Compression in The Presence of Image Resizing; Citeseer: Gaithersburg, MD, USA, 2014. [Google Scholar]
  148. Fidler, A.; Likar, B.; Skalerič, U. Lossy JPEG Compression: Easy to Compress, Hard to Compare. Dentomaxillofacial Radiol. 2006, 35, 67–73. [Google Scholar] [CrossRef] [Scilit]
  149. Urbaniak, I.A. Using Compressed JPEG and JPEG2000 Medical Images in Deep Learning: A Review. Appl. Sci. 2024, 14, 12524. [Google Scholar] [CrossRef] [Scilit]
  150. Shubhajit, K.D.; ABIR, C. A Review on Deep Learning of Neural Network Based Image Compression Techniques. I-Manag. J. Image Process. 2019, 6, 33. [Google Scholar] [CrossRef] [Scilit]
  151. Bourai, N.E.H.; Merouani, H.F.; Djebbar, A. Deep Learning-Assisted Medical Image Compression Challenges and Opportunities: Systematic Review. Neural Comput. Appl. 2024, 36, 10067–10108. [Google Scholar] [CrossRef] [Scilit]
  152. Shamshad, F.; Khan, S.; Zamir, S.W.; Khan, M.H.; Hayat, M.; Khan, F.S.; Fu, H. Transformers in Medical Imaging: A Survey. Med. Imag. Anal. 2023, 88, 102802. [Google Scholar] [CrossRef] [Scilit]
  153. He, K.; Gan, C.; Li, Z.; Rekik, I.; Yin, Z.; Ji, W.; Gao, Y.; Wang, Q.; Zhang, J.; Shen, D. Transformers in Medical Image Analysis. Intell. Med. 2022, 3, 59–78. [Google Scholar] [CrossRef] [Scilit]
  154. Li, J.; Chen, J.; Tang, Y.; Wang, C.; Landman, B.A.; Zhou, S.K. Transforming Medical Imaging with Transformers? A Comparative Review of Key Properties, Current Progresses, and Future Perspectives. Med. Image Anal. 2023, 85, 102762. [Google Scholar] [CrossRef] [Scilit] [PubMed]
  155. Xiao, H.; Li, L.; Liu, Q.; Zhu, X.; Zhang, Q. Transformers in Medical Image Segmentation: A Review. Biomed. Signal Process. Control. 2023, 84, 104791. [Google Scholar] [CrossRef] [Scilit]
  156. Springenberg, M.; Frommholz, A.; Wenzel, M.; Weicken, E.; Ma, J.; Strodthoff, N. From Modern CNNs to Vision Transformers: Assessing the Performance, Robustness, and Classification Strategies of Deep Learning Models in Histopathology. Med. Image Anal. 2023, 87, 102809. [Google Scholar] [CrossRef] [Scilit] [PubMed]
  157. Nerella, S.; Bandyopadhyay, S.; Zhang, J.; Contreras, M.; Siegel, S.; Bumin, A.; Silva, B.; Sena, J.; Shickel, B.; Bihorac, A.; et al. Transformers in Healthcare: A Survey. arXiv 2023, arXiv:2307.00067. [Google Scholar]
  158. Xia, K.; Wang, J. Recent Advances of Transformers in Medical Image Analysis: A Comprehensive Review. MedComm Future Med. 2023, 2, 38. [Google Scholar] [CrossRef] [Scilit]
  159. Chen, C.; Wu, Y.; Dai, Q.; Zhou, H.-Y.; Xu, M.; Yang, S.; Han, X.; Yu, Y. A Survey on Graph Neural Networks and Graph Transformers in Computer Vision: A Task-Oriented Perspective. IEEE Trans. Pattern Anal. Mach. Intell. 2024, 46, 10297–10318. [Google Scholar] [CrossRef] [Scilit] [PubMed]
  160. Bessadok, A.; Mahjoub, M.A.; Rekik, I. Graph Neural Networks in Network Neuroscience. IEEE Trans. Pattern Anal. Mach. Intell. 2022, 45, 5833–5848. [Google Scholar] [CrossRef] [Scilit]
  161. Zhang, X.-M.; Liang, L.; Liu, L.; Tang, M.-J. Graph Neural Networks and Their Current Applications in Bioinformatics. Front. Genet. 2021, 12, 690049. [Google Scholar] [CrossRef] [Scilit]
  162. Berghout, T. Joint Image Processing with Learning-Driven Data Representation and Model Behavior for Non-Intrusive Anemia Diagnosis in Pediatric Patients. J. Imaging 2024, 10, 245. [Google Scholar] [CrossRef] [Scilit]
  163. Berghout, T.; Bechhoefer, E.; Djeffal, F.; Lim, W.H. Integrating Learning-Driven Model Behavior and Data Representation for Enhanced Remaining Useful Life Prediction in Rotating Machinery. Machines 2024, 12, 729. [Google Scholar] [CrossRef] [Scilit]
  164. Berghout, T.; Benbouzid, M. Fault Diagnosis in Drones via Multiverse Augmented Extreme Recurrent Expansion of Acoustic Emissions with Uncertainty Bayesian Optimisation. Machines 2024, 12, 504. [Google Scholar] [CrossRef] [Scilit]
  165. Berghout, T.; Benbouzid, M. UBO-EREX: Uncertainty Bayesian-Optimized Extreme Recurrent EXpansion for Degradation Assessment of Wind Turbine Bearings. Electronics 2024, 13, 2419. [Google Scholar] [CrossRef] [Scilit]
  166. Berghout, T.; Benbouzid, M.; Ferrag, M.A. Multiverse Recurrent Expansion with Multiple Repeats: A Representation Learning Algorithm for Electricity Theft Detection in Smart Grids. IEEE Trans. Smart Grid 2023, 14, 4693–4703. [Google Scholar] [CrossRef] [Scilit]
  167. Lambert, B.; Forbes, F.; Doyle, S.; Dehaene, H.; Dojat, M. Trustworthy Clinical AI Solutions: A Unified Review of Uncertainty Quantification in Deep Learning Models for Medical Image Analysis. Artif. Intell. Med. 2024, 150, 102830. [Google Scholar] [CrossRef] [Scilit] [PubMed]
  168. Huang, L.; Ruan, S.; Xing, Y.; Feng, M. A Review of Uncertainty Quantification in Medical Image Analysis: Probabilistic and Non-Probabilistic Methods. Med. Image Anal. 2024, 97, 103223. [Google Scholar] [CrossRef] [Scilit] [PubMed]
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.

Article Metrics

Citations

Article Access Statistics

Multiple requests from the same IP address are counted as one view.