• Sunitha N
• Dr.Kumaraswamy S

Abstract : Accurate detection and segmentation of brain tumors from magnetic resonance imaging (MRI) scans play a vital role in clinical diagnosis, treatment planning, and prognosis evaluation. Manual analysis of MRI images by radiologists is often time-consuming and susceptible to subjectivity, particularly when tumor boundaries are complex or ambiguous. To address these challenges, this paper presents a deep learning–based framework for automated brain tumor segmentation using a Residual U-Net (ResUNet) architecture. The proposed model combines the encoder–decoder structure of U-Net with residual learning to improve gradient flow, enhance feature reuse, and preserve spatial details during segmentation. Prior to model training, MRI images are standardized through resizing, normalization, and binary mask generation to ensure consistent data representation. The ResUNet model is trained in a supervised manner using paired MRI images and corresponding ground-truth masks, optimized with binary cross-entropy loss and adaptive learning rate strategies. Experimental results demonstrate stable convergence and reliable segmentation performance across validation samples, with effective delineation of tumor regions. To improve practical usability, the trained model is integrated into a graphical user interface that enables image upload, visualization of segmentation outputs, and quantitative tumor area estimation. Based on the segmented tumor region, the system further provides tumor severity categorization and approximate survival timelines to support preliminary clinical assessment. The proposed framework highlights the effectiveness of ResUNet- based deep learning models for automated brain tumor analysis

-Brain Tumor Segmentation, Residual U- Net, Deep Learning, Magnetic Resonance Imaging, Medical Image Analysis

"Ensemble Technique for Brain Tumor Patient Survival Prediction", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.13, Issue 1, page no.f338-f346, January-2026, Available :http://www.jetir.org/papers/JETIR2601551.pdf

"Ensemble Technique for Brain Tumor Patient Survival Prediction", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.13, Issue 1, page no. ppf338-f346, January-2026, Available at : http://www.jetir.org/papers/JETIR2601551.pdf