LATUP-Net: A Lightweight 3D Attention U-Net with Parallel Convolutions for Brain Tumor Segmentation

TL;DR

Investigations into the model's interpretability reveal that while attention mechanisms enhance the segmentation of small regions, their impact is nuanced, which makes it a promising solution for real-world clinical applications, particularly in settings with limited resources.

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 3.07M parameters, about 59 times fewer than other state-of-the-art models, and running on a single NVIDIA GeForce RTX3060 12GB 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 [...]. The code is available at https://qyber.black/ca/code-bca.

Figures (11)

• Figure 1: The LATUP-Net architecture.
• Figure 2: Proposed parallel convolutions.
• Figure 3: Squeeze and Excitation Block.
• Figure 4: MRI scan of a brain tumor featuring ground truth segmentation masks: blue represents necrotic and non-enhancing tumor areas (NCR/NET, Label 1), green highlights edema regions (ED, Label 2), and red indicates areas of enhancing tumor (ET, Label 4).
• Figure 5: Segmentation results from the test set that are typical of those produced by the various networks. The results for a single patient from each network are shown in each row. The enhancing tumor is depicted in blue, the necrotic and non-enhancing tumor in red, and the edema in green (after extracting the distinct regions from the partially overlapping segmentation results).