A Comprehensive Analysis of Recent Deep Learning Based Methodologies for Brain Tumor Diagnosis

Insha Fiaz; Nadeem Anjum

Authors

Insha Fiaz Department of Software Engineering (Capital University of Science & Technology)
Nadeem Anjum Department of Software Engineering (Capital University of Science & Technology)

Keywords:

Brain Tumor Diagnosis, Deep Learning, CNN, MRI, Medical Imaging

Abstract

Brain tumors are a serious global health challenge because their occurrence is associated with high mortality and difficulties in accurate diagnosis.. Timely and efficient diagnosis is essential to successful treatment and better patient outcomes. This paper is a systematic comparison-based review of the recent deep learning methods of brain tumor detection and classification based on magnetic resonance imaging (MRI). A structured screening process was applied to 523 candidate papers retrieved from IEEE Xplore, Scopus, Google Scholar, and ScienceDirect (2022–2025). Studies were evaluated against four quality criteria: (i) reproducibility of the experimental setup, (ii) completeness of reported metrics, (iii) clarity of architectural description, and (iv) dataset transparency. Of 523 papers, 136 duplicates were removed, leaving 387 for screening. After title-and-abstract screening, 94 full-text papers remained, from which 83 were further excluded for insufficient methodological detail, non-reproducibility, or risk of bias, yielding 11 studies for final inclusion. This paper summarizes the research outcomes of six deep learning models such as ResNet50, Efficient Net, and YOLOv7, U-Net, VGG16 and a CNN-RNN hybrid model in terms of reported metrics, such as accuracy, precision, recall and F1-score. These models were evaluated on different tumor datasets and task types, and results are interpreted accordingly within their respective domains. The reported findings reveal that segmentation-based and hybrid deep learning models are more effective. U-Net has the most accuracy of 99.9%, then Yolov7 with 99.5%. ResNet50 has an accuracy of 98.78%, whereas Efficient Net has 97.8%. The hybrid CNN-RNN model is reported to record 94.7% accuracy and VGG16 is reported to be significantly low at 93.35% accuracy. The paper concludes by identifying future research directions, including privacy-preserving federated learning, integration of multimodal imaging, and the development of deep learning systems suitable for clinical settings.

References

S. Kar and Pawan Kumar Singh, “MBTC-Net: Multimodal brain tumor classification from CT and MRI scans using deep neural network with multi-head attention mechanism,” Med. Nov. Technol. Devices, vol. 27, p. 100382, 2025, [Online]. Available: https://www.sciencedirect.com/science/article/pii/S2590093525000335

C. G. & K. S. Bhuvaneswari, “A novel approach for the detection of brain tumor and its classification via independent component analysis,” Sci. Reports Vol., vol. 15, 2025, [Online]. Available: https://www.nature.com/articles/s41598-025-87934-4

R. B. V. & L. K. Pappala, “Enhanced brain tumor classification framework using deep learning,” Sci. Rep., vol. 15, 2025, [Online]. Available: https://www.nature.com/articles/s41598-025-19882-y

H. Liu, Z. Ni, D. Nie, D. Shen, J. Wang, and Z. Tang, “Multimodal Brain Tumor Segmentation Boosted by Monomodal Normal Brain Images,” IEEE Trans. Image Process., vol. 33, pp. 1199–1210, 2024, doi: 10.1109/TIP.2024.3359815.

A. A. Vikram Verma, “Deep Learning: A Revolutionizing Approach To Brain Tumor Classification Using MRI,” South East. Eur. J. Public Heal., pp. 2955–2965, 2025, [Online]. Available: https://www.seejph.com/index.php/seejph/article/view/5595

Mohammed A Alsuwaiket, Hafar Al Batin, “Feature Extraction of EEG Signals for Seizure Detection Using Machine Learning Algorthims,” Eng. Technol. Appl. Sci. Res., vol. 12, no. 5, 2022, [Online]. Available: https://etasr.com/index.php/ETASR/article/view/5208

B. D. S. & M. A. S. Saravanan Srinivasan, Divya Francis, Sandeep Kumar Mathivanan, Hariharan Rajadurai, “A hybrid deep CNN model for brain tumor image multi-classification,” BMC Med. Imaging, vol. 24, no. 21, 2024, [Online]. Available: https://link.springer.com/article/10.1186/s12880-024-01195-7

N. Rasool and J. I. Bhat, “Brain tumour detection using machine and deep learning: a systematic review,” Multimed. Tools Appl. 2024 8413, vol. 84, no. 13, pp. 11551–11604, May 2024, doi: 10.1007/S11042-024-19333-2.

A. T. Islam et al., “An Efficient Deep Learning Approach to detect Brain Tumor Using MRI Images,” Proc. 2022 25th Int. Conf. Comput. Inf. Technol. ICCIT 2022, pp. 143–147, 2022, doi: 10.1109/ICCIT57492.2022.10054999.

“(PDF) Brain Tumor Segmentation using Deep Learning Architectures like U-NET, V-NET, U-NET.” Accessed: May 30, 2026. [Online]. Available: https://www.researchgate.net/publication/373739521_Brain_Tumor_Segmentation_using_Deep_Learning_Architectures_like_U-NET_V-NET_U-NET

T. Das, D. K. Vishwakarma, and V. Ranga, “A Comparative Study of Deep Learning Models for Brain Tumor Classification,” 2024 4th Int. Conf. Intell. Technol. CONIT 2024, 2024, doi: 10.1109/CONIT61985.2024.10626265.

M. T. Y. Usman Humayun, “Deep Learning Approaches for Brain Tumor Detection and Segmentation in MRI Imaging | Journal of Computing & Biomedical Informatics,” Journal of Computing & Biomedical Informatics. Accessed: Jan. 08, 2026. [Online]. Available: https://jcbi.org/index.php/Main/article/view/738

M. M. Carlos Aumente-Maestro, “AUDIT: An open-source Python library for AI model evaluation with use cases in MRI brain tumor segmentation,” Comput. Methods Programs Biomed., vol. 271, p. 108991, 2025, [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0169260725004080

K. V. K. M. Vinitha, “Integrated U-Net 3+ with Decomposed Multi head Self-Attention Block and Filter Response Normalization for Brain Lesion Localization and Tracking using 3D MRI,” ITM Web Conf., 2025, [Online]. Available: https://www.itm-conferences.org/articles/itmconf/ref/2025/10/itmconf_keis2025_01057/itmconf_keis2025_01057.html

E. K. Rutoh, Q. ZhiGuang, J. C. Bore-Norton and N. Bahadar, “ABI-Net: Attention-Based Inception U-Net for Brain Tumor Segmentation From Multimodal MRI Images,” IEEE Access, vol. 3, pp. 134898–134916, 20251, [Online]. Available: https://ieeexplore.ieee.org/document/11071545

A. N. Mohammed Rasool, “Brain Tumor Classification using Deep Learning: A State-of-the-Art Review,” Eng. Technol. Appl. Sci. Res., vol. 14, no. 5, pp. 16586–16594, 2024, [Online]. Available: https://etasr.com/index.php/ETASR/article/view/8298

N. A. I. Mohammed Rasool, “A Novel Approach for Classifying Brain Tumours Combining a SqueezeNet Model with SVM and Fine-Tuning,” Electronics, vol. 12, no. 1, p. 149, 2023, doi: https://doi.org/10.3390/electronics12010149.

H. K. & S. R. N. K. Soheila Saeedi, Sorayya Rezayi, “MRI-based brain tumor detection using convolutional deep learning methods and chosen machine learning techniques,” BMC Med. Inform. Decis. Mak., vol. 23, no. 16, 2023, [Online]. Available: https://link.springer.com/article/10.1186/s12911-023-02114-6

M. U. A. Muhannad Faleh Alanazi, “Brain Tumor/Mass Classification Framework Using Magnetic-Resonance-Imaging-Based Isolated and Developed Transfer Deep-Learning Model,” Sensors, vol. 22, no. 1, p. 372, 2022, doi: https://doi.org/10.3390/s22010372.

S. H. K. Mirza Mumtaz Zahoor, “Brain Tumor MRI Classification Using a Novel Deep Residual and Regional CNN,” Biomedicines, vol. 12, no. 7, p. 1395, 2024, doi: https://doi.org/10.3390/biomedicines12071395.

S. Tummala, S. Kadry, S. A. C. Bukhari, and H. T. Rauf, “Classification of Brain Tumor from Magnetic Resonance Imaging Using Vision Transformers Ensembling,” Curr. Oncol. 2022, Vol. 29, Pages 7498-7511, vol. 29, no. 10, pp. 7498–7511, Oct. 2022, doi: 10.3390/CURRONCOL29100590.

M. A. M. Shaimaa E. Nassar, Ibrahim Yasser, Hanan M. Amer, “Comparative analysis of vision transformers and fine-tuned transfer learning models for brain tumor classification,” Imaging Radiat. Res., 2024, [Online]. Available: https://systems.enpress-publisher.com/index.php/IRR/article/view/8514

M. G. J. Nivea Kesav, “Efficient and low complex architecture for detection and classification of Brain Tumor using RCNN with Two Channel CNN,” J. King Saud Univ. - Comput. Inf. Sci., vol. 34, no. 8, pp. 6229–6242, 2022, [Online]. Available: https://www.sciencedirect.com/science/article/pii/S1319157821001221

Akmalbek Bobomirzaevich Abdusalomov, “Brain Tumor Detection Based on Deep Learning Approaches and Magnetic Resonance Imaging,” Cancers (Basel)., vol. 15, no. 16, p. 4172, 2023, doi: 10.3390/cancers15164172.

W. Zhang, W. Jin, S. Rho, F. Jiang, and C. fu Yang, “A Federated Learning Framework for Brain Tumor Segmentation Without Sharing Patient Data,” Int. J. Imaging Syst. Technol., vol. 34, no. 4, Jul. 2024, doi: 10.1002/IMA.23147.

B. Kadirvelu, L. Stumpf, S. Waibel, and A. A. Faisal, “Speaker-independent dysarthria severity classification using self-supervised transformers and multi-task learning,” PLOS Digit. Heal., vol. 4, no. 11, p. e0001076, Nov. 2025, doi: 10.1371/JOURNAL.PDIG.0001076.

Chengcheng Jin, Nor Safira Elaina Mohd Noor, “Transformer-based architectures in MRI brain tumor segmentation: A review,” Comput. Med. Imaging Graph., vol. 129, p. 102729, 2026, doi: https://doi.org/10.1016/j.compmedimag.2026.102729.