Brain MRI Segmentation Using U-Net and SegNet: A Comparative Study Across Modalities with Robust Loss Functions

Gouranga Bala, Hiranmay Mondal, Amit Sethi

2025

Abstract

This paper presents a comprehensive comparative study of brain tumor segmentation using two well-known Convolutional Neural Network (CNN) architectures, U-Net and SegNet, across multiple MRI modalities, specifically T2-weighted and Fluid Attenuated Inversion Recovery (FLAIR) images from the BraTS 2020 dataset. We evaluated the performance of these models using four different loss functions: Dice Loss, Focal Loss, Adaptive Robust Loss, and the novel Robust Dice Loss. Our contributions are twofold: first, we provide a detailed comparison of the performance of U-Net and SegNet for brain tumor segmentation across distinct MRI modalities, offering insights into the role of modality-specific features in segmentation outcomes. Second, we introduce the novel Robust Dice Loss, which significantly improved SegNet’s training efficiency, allowing it to handle challenging segmentation scenarios involving data imbalance and intricate tumor boundaries with much greater ease. Our results indicate that U-Net generally outperforms SegNet in terms of segmentation accuracy, particularly when trained with Adaptive Robust Loss. However, the introduction of Robust Dice Loss enabled SegNet to achieve competitive performance, particularly with the FLAIR modality, demonstrating its potential as an effective alternative. This study emphasizes the importance of selecting appropriate loss functions to handle imbalanced data and enhance model performance, thereby contributing valuable insights for the advancement of automated medical image analysis and its clinical utility in neuro-oncology.

Paper Citation

in Harvard Style

Bala G., Mondal H. and Sethi A. (2025). Brain MRI Segmentation Using U-Net and SegNet: A Comparative Study Across Modalities with Robust Loss Functions. In Proceedings of the 18th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 1: BIOIMAGING; ISBN 978-989-758-731-3, SciTePress, pages 246-254. DOI: 10.5220/0013302900003911

in Bibtex Style

@conference{bioimaging25,
author={Gouranga Bala and Hiranmay Mondal and Amit Sethi},
title={Brain MRI Segmentation Using U-Net and SegNet: A Comparative Study Across Modalities with Robust Loss Functions},
booktitle={Proceedings of the 18th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 1: BIOIMAGING},
year={2025},
pages={246-254},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013302900003911},
isbn={978-989-758-731-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 18th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 1: BIOIMAGING
TI - Brain MRI Segmentation Using U-Net and SegNet: A Comparative Study Across Modalities with Robust Loss Functions
SN - 978-989-758-731-3
AU - Bala G.
AU - Mondal H.
AU - Sethi A.
PY - 2025
SP - 246
EP - 254
DO - 10.5220/0013302900003911
PB - SciTePress