Deep Learning–Driven Brain Tumour Diagnosis: Training ResNet18 from Scratch on MRI for Real-Time Clinical Use

This paperthen provided a deep learning pipeline forbrat classification that was end to end: It introduced a di!erent model, but trained it end to end for the whole task, using the resNet18 implementation byAsi et. By properly preprocessing the data, making clever augmentation, and training the model with attention to detail, the model managed to achieve near-perfect accuracy and generalization score, and by only misclassifying a few of the tumor and human ones. The results show that the proposed model is accurate and speedy, with high-sensitivity in identifying the tumor and strong specificity for the healthy cases. The implications of these findings suggest that deep residual learning has the potential to be a useful tool in the hands of clinicians for the early and accurate diagnosis of brain tumors. Our ongoing and future work here could involve extension of the approach to multi-class tumor grading, larger dataset cohorts, and real-time deployment within a clinical context.

1.                Neamah, K., Mohamed, F., Waheed, S. R., Kurdi, W. H. M., Taha, A. Y., &Kadhim, K. A. (2024). Utilizing deep improved resnet50 for brain tumor classification based MRI. IEEE Open Journal of the Computer Society, 5, 446-456. 2.                Abdusalomov, A. B., Mukhiddinov, M., &Whangbo, T. K. (2023). Brain tumor detection based on deep learning approaches and magnetic resonance imaging. Cancers, 15(16), 4172. 3.                Abdulrahman, S. (2024). ENHANCING BRAIN TUMOUR DIAGNOSIS WITH AI: A COMPARATIVE ANALYSIS OF RESNET AND YOLO ALGORITHM FOR TUMOUR CLASSIFICATION IN MRI SCANS. 4.                Rath, A., Mishra, B. S. P., &Bagal, D. K. (2025). ResNet50-based Deep Learning model for accurate brain tumor detection in MRI scans. Next Research, 2(1), 100104. 5.                Li, Z., & Dib, O. (2024). Empowering brain tumor diagnosis through explainable deep learning. Machine Learning and Knowledge Extraction, 6(4), 2248-2281. 6.                Ashimgaliyev, M., Matkarimov, B., Barlybayev, A., Li, R. Y. M., &Zhumadillayeva, A. (2024). Accurate MRI-based brain tumor diagnosis: integrating segmentation and deep learning approaches. Applied Sciences, 14(16), 7281. 7.                Rastogi, D., Johri, P., Donelli, M., Kumar, L., Bindewari, S., Raghav, A., & Khatri, S. K. (2025). Brain tumor detection and prediction in MRI images utilizing a Fine-Tuned transfer learning model integrated within deep learning frameworks. Life, 15(3), 327. 8.                Gorenshtein, A., Liba, T., & Goren, A. (2025). Lightweight Transfer Learning Models for Multi-Class Brain Tumor Classification: Glioma, Meningioma, Pituitary Tumors, and No Tumor MRI Screening. Journal of Imaging Informatics in Medicine, 1-10. 9.                Awad, S. R., Daood, A. I., & Dawood, A. A. (2025). Scalable and Efficient Multi-Class Brain Tumor Classification with a Compact Hybrid Deep Learning Model for Real-Time Applications. ARO-THE SCIENTIFIC JOURNAL OF KOYA UNIVERSITY, 13(1), 162-174. 10.             Arabahmadi, M., Farahbakhsh, R., &Rezazadeh, J. (2022). Deep learning for smart Healthcare—A survey on brain tumor detection from medical imaging. Sensors, 22(5), 1960.