LATUP-Net: A lightweight 3D attention U-Net with parallel convolutions for brain tumor segmentation

Alwadee, Ebtihal J., Sun, Xianfang ORCID: https://orcid.org/0000-0002-6114-0766, Qin, Yipeng ORCID: https://orcid.org/0000-0002-1551-9126 and Langbein, Frank C. ORCID: https://orcid.org/0000-0002-3379-0323 2025. LATUP-Net: A lightweight 3D attention U-Net with parallel convolutions for brain tumor segmentation. Computers in Biology and Medicine 184 , 109353. 10.1016/j.compbiomed.2024.109353

PDF - Published Version Available under License Creative Commons Attribution Non-commercial. Download (4MB)

Abstract

Early-stage 3D brain tumor segmentation from magnetic resonance imaging (MRI) scans is crucial for prompt and effective treatment. However, this process faces the challenge of precise delineation due to the tumors’ complex heterogeneity. Moreover, energy sustainability targets and resource limitations, especially in developing countries, require efficient and accessible medical imaging solutions. The proposed architecture, a Lightweight 3D ATtention U-Net with Parallel convolutions, LATUP-Net, addresses these issues. It is specifically designed to reduce computational requirements significantly while maintaining high segmentation performance. By incorporating parallel convolutions, it enhances feature representation by capturing multi-scale information. It further integrates an attention mechanism to refine segmentation through selective feature recalibration. LATUP-Net achieves promising segmentation performance: the average Dice scores for the whole tumor, tumor core, and enhancing tumor on the BraTS 2020 dataset are 88.41%, 83.82%, and 73.67%, and on the BraTS 2021 dataset, they are 90.29%, 89.54%, and 83.92%, respectively. Hausdorff distance metrics further indicate its improved ability to delineate tumor boundaries. With its significantly reduced computational demand using only 3.07 M parameters, about 59 times fewer than other state-of-the-art models, and running on a single NVIDIA GeForce RTX3060 12 GB GPU, LATUP-Net requires just 15.79 GFLOPs. This makes it a promising solution for real-world clinical applications, particularly in settings with limited resources. Investigations into the model’s interpretability, utilizing gradient-weighted class activation mapping and confusion matrices, reveal that while attention mechanisms enhance the segmentation of small regions, their impact is nuanced. Achieving the most accurate tumor delineation requires carefully balancing local and global features. The code is available at https://qyber.black/ca/code-bca

Item Type:	Article
Date Type:	Publication
Status:	Published
Schools:	Computer Science & Informatics
Publisher:	Elsevier
ISSN:	0010-4825
Date of First Compliant Deposit:	25 November 2024
Date of Acceptance:	31 October 2024
Last Modified:	26 Nov 2024 11:45
URI:	https://orca.cardiff.ac.uk/id/eprint/174293

Actions (repository staff only)

Edit Item