LM-Net: A Light-weight and Multi-scale Network for Medical Image Segmentation

TL;DR

LM-Net is a lightweight, multi-scale neural network that combines CNNs and Vision Transformers to improve medical image segmentation by capturing local details and global context, achieving state-of-the-art results.

Contribution

The paper introduces LM-Net, a novel lightweight architecture that integrates multi-scale features with local and global transformers for enhanced segmentation accuracy.

Findings

Achieves state-of-the-art segmentation results on three datasets.

Requires only 4.66G FLOPs and 5.4M parameters.

Effectively combines local textures and global semantics.

Abstract

Current medical image segmentation approaches have limitations in deeply exploring multi-scale information and effectively combining local detail textures with global contextual semantic information. This results in over-segmentation, under-segmentation, and blurred segmentation boundaries. To tackle these challenges, we explore multi-scale feature representations from different perspectives, proposing a novel, lightweight, and multi-scale architecture (LM-Net) that integrates advantages of both Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) to enhance segmentation accuracy. LM-Net employs a lightweight multi-branch module to capture multi-scale features at the same level. Furthermore, we introduce two modules to concurrently capture local detail textures and global semantics with multi-scale features at different levels: the Local Feature Transformer (LFT) and Global Feature Transformer (GFT). The LFT integrates local window self-attention to capture local detail textures, while the GFT leverages global self-attention to capture global contextual semantics. By combining these modules, our model achieves complementarity between local and global representations, alleviating the problem of blurred segmentation boundaries in medical image segmentation. To evaluate the feasibility of LM-Net, extensive experiments have been conducted on three publicly available datasets with different modalities. Our proposed model achieves state-of-the-art results, surpassing previous methods, while only requiring 4.66G FLOPs and 5.4M parameters. These state-of-the-art results on three datasets with different modalities demonstrate the effectiveness and adaptability of our proposed LM-Net for various medical image segmentation tasks.