Automated Brain Tumor Segmentation from MRI Scans Using U-Net Architecture
International Journal of Scientific Research in Science, Engineering and Technology · 10.06.2026 · 13 (3) · 356-364
DOI: 10.32628/ijsrset2613347 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Scientific Research in Science, Engineering and Technology, online erschienen am 10.06.2026. Verfasst von Gudipati Veena und 4 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Brain tumors are among the most aggressive and life-threatening diseases, requiring prompt and accurate diagnosis for effective treatment planning. Magnetic Resonance Imaging (MRI) is the standard modality for assessing brain anatomy; however, manual segmentation of tumor regions is a labor-intensive, time-consuming process subject to inter-observer variability. This paper presents an automated approach for brain tumor segmentation utilizing the U-Net deep learning architecture. The proposed methodology leverages the BraTS (Brain Tumor Segmentation Challenge) dataset to train a convolutional neural network designed for semantic segmentation. The system employs Dice Loss to handle class imbalance and incorporates morphological post-processing to refine segmentation masks. Experimental results demonstrate that the U-Net model achieves a high Dice Similarity Coefficient, proving its efficacy in distinguishing tumor regions from healthy brain tissue. This research contributes to the development of computer-aided diagnostic tools that assist radiologists in clinical workflows.
Zitieren
APA
Veena, G., Indumathi, K., Mamatha, P., Akshaya, P., & Veeresha, D. M. (2026). Automated Brain Tumor Segmentation from MRI Scans Using U-Net Architecture. International Journal of Scientific Research in Science, Engineering and Technology, 13(3), 356-364. https://doi.org/10.32628/ijsrset2613347
Vancouver
Veena G, Indumathi K, Mamatha P, Akshaya P, Veeresha DM. Automated Brain Tumor Segmentation from MRI Scans Using U-Net Architecture. International Journal of Scientific Research in Science, Engineering and Technology. 2026;13(3):356-364. doi:10.32628/ijsrset2613347
BibTeX
@article{Veena2026,
author = {Veena, Gudipati and Indumathi, Kanipogu and Mamatha, P. and Akshaya, Pasupala and Veeresha, Dr M},
title = {Automated Brain Tumor Segmentation from MRI Scans Using U-Net Architecture},
journal = {International Journal of Scientific Research in Science, Engineering and Technology},
year = {2026},
volume = {13},
number = {3},
pages = {356--364},
doi = {10.32628/ijsrset2613347}
}
EUVIMED