A Comparative Deep Learning Framework for Brain Tumour Detection and Sub-Region Segmentation in MRI
Global Journal of Engineering Innovations and Interdisciplinary Research · 01.05.2026 · 6 (3)
DOI: 10.33425/3066-1226.1273 ↗Kurz gefasst
Fachartikel in der Zeitschrift Global Journal of Engineering Innovations and Interdisciplinary Research, online erschienen am 01.05.2026. Verfasst von Dr. Mungara Kiran Kumar und 4 weiteren Autor:innen.
Abstract (Originalsprache)
This study introduces a step-by-step upgrade path for segmenting three brain tumor classes on BraTS 2023 GLI magnetic resonance images, an expansion of the standard BraTS reference set. The first version is a plain U-Net. The pipeline then adds one upgrade at a time - a deeper encoder to extract richer features, a hybrid Dice-cross-entropy loss to counter class skew and attention gates to sharpen spatial focus. Every stage is tested under an identical protocol so that the gain from each change is measured in isolation. After all stages, the model records a higher Dice score and a higher Intersection over Union value. The final Attention U-Net with hybrid loss draws crisper borders and finds the smallest tumor zones more often, which supports the value of the sequential refinement plan.
Zitieren
APA
Kumar, D. M. K., Nivas, B. L., Jaswant, D., Himabindu, K., & Nigam, S. (2026). A Comparative Deep Learning Framework for Brain Tumour Detection and Sub-Region Segmentation in MRI. Global Journal of Engineering Innovations and Interdisciplinary Research, 6(3). https://doi.org/10.33425/3066-1226.1273
Vancouver
Kumar DMK, Nivas BL, Jaswant D, Himabindu K, Nigam S. A Comparative Deep Learning Framework for Brain Tumour Detection and Sub-Region Segmentation in MRI. Global Journal of Engineering Innovations and Interdisciplinary Research. 2026;6(3). doi:10.33425/3066-1226.1273
BibTeX
@article{Kumar2026,
author = {Kumar, Dr. Mungara Kiran and Nivas, B Lakshmi and Jaswant, D and Himabindu, K and Nigam, Shubh},
title = {A Comparative Deep Learning Framework for Brain Tumour Detection and Sub-Region Segmentation in MRI},
journal = {Global Journal of Engineering Innovations and Interdisciplinary Research},
year = {2026},
volume = {6},
number = {3},
doi = {10.33425/3066-1226.1273}
}
EUVIMED