Enhanced AI-Based Diagnostic Framework: Ensemble Modeling for Multi-Orientation MRI Classification of Brain Tumors and Multiple Sclerosis

• Muthuramalingam Sivakumar

  Thiagarjar College of Engineering, Madurai, Tamilnadu, India

• Padmapriya Thiyagarajan

  Thiagarjar College of Engineering, Madurai, Tamilnadu, India

Brain tumors and multiple sclerosis (MS) are complex medical conditions characterized by overlapping clinical and imaging features, posing significant challenges in accurate diagnosis. Building upon our previous work, which utilized axial MRI images for classification into three categories—normal, brain tumor, and MS—this study extends the methodology to incorporate sagittal and coronal orientations. Individual convolutional neural network (CNN) models are trained for each orientation, and their outputs are integrated using an ensemble framework with a voting mechanism. This approach leverages the complementary spatial information provided by multi-orientation analysis to enhance diagnostic precision. Experimental evaluations demonstrate that the ensemble model achieves superior classification accuracy and robustness in contrast to the single-orientation approach. This piece emphasizes the vital role that multi-orientation MRI analysis plays in mitigating diagnostic ambiguities and advancing the reliability of AI-driven medical imaging frameworks.

[1] Thompson AJ, Banwell BL, Barkhof F, Carroll WM, Coetzee T, Comi G, et al. Diagnosis of multiple sclerosis: 2017 revisions of the McDonald criteria. The Lancet Neurology 2018; 17(2): 162-173.

[2] Lee DY. Roles of mTOR signaling in brain development. Experimental Neurobiology 2015; 24(3): 177-185.

[3] Rudick RA, Cohen JA, Weinstock-Guttman B, Kinkel RP, Ransohoff RM. Management of multiple sclerosis. New England Journal of Medicine 1997; 337(22): 1604-1611.

[4] Sirko AH, Dzyak LA, Chekha EV. Coexistence of multiple sclerosis and brain tumors: A Literature Review 2020; 25(2): 30-36.

[5] Iwamoto K, Oka H, Utsuki S, Ozawa T, Fujii K. Late-onset multiple sclerosis mimicking brain tumor: a case report. Brain Tumor Pathology 2004; 21: 83-86.

[6] Narmatha C, Eljack SM, Tuka AARM, Manimurugan S, Mustafa M. A hybrid fuzzy brain-storm optimization algorithm for the classification of brain tumor MRI images. Journal of Ambient Intelligence and Humanized Computing 2020; 1-9.

[7] Lamrani D, Cherradi B, El Gannour O, Bouqentar MA, Ba Hatti L. Brain tumor detection using MRI images and convolutional neural network. International Journal of Advanced Computer Science and Applications 2022; 13(7).

[8] Toğaçar M, Ergen B, Cömert Z. BrainMRNet: Brain tumor detection using magnetic resonance images with a novel convolutional neural network model. Medical Hypotheses 2020; 134: 109531.

[9] Shah HA, Saeed F, Yun S, Park JH, Paul A, Kang JM. A robust approach for brain tumor detection in magnetic resonance images using finetuned EfficientNet. IEEE Access 2022; 10: 65426-65438.

[10] Dipu NM, Shohan SA, Salam KMA. Deep learning based brain tumor detection and classification. In 2021 International Conference on Intelligent Technologies (CONIT) 2021; 1-6.

[11] Abdusalomov AB, Mukhiddinov M, Whangbo TK. Brain tumor detection based on deep learning approaches and magnetic resonance imaging. Cancers 2023; 15(16): 4172.

[12] Amin J, Sharif M, Yasmin M, Fernandes SL. A distinct approach in brain tumor detection and classification using MRI. Pattern Recognition Letters 2020; 139: 118-127.

[13] Deb D, Roy S. Brain tumor detection based on a hybrid deep neural network in MRI by adaptive squirrel search optimization. Multimedia Tools and Applications 2021; 80(2): 2621-2645.

[14] Sadad T, Rehman A, Munir A, Saba T, Tariq U, Ayesha N, Abbasi R. Brain tumor detection and multi-classification using advanced deep learning techniques. Microscopy Research and Technique 2021; 84(6): 1296-1308.

[15] Menze BH, Jakab A, Bauer S, Kalpathy-Cramer J, Farahani K, Kirby J, et al. The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS). IEEE Transactions on Medical Imaging 2015; 34(10): 1993-2024.

• PDF

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.