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

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

7 Jan 2025arXiv:2501.03838archive 2025-07-28

Zhenkun Lu, Chaoyin She, Wei Wang, Qinghua Huang

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.

Paper PDF Code

Code

Asunatan/LM-Net officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image Segmentation Medical Image Segmentation Segmentation Semantic Segmentation

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Medical Image Segmentation	Kvasir-SEG	LM-Net	Precision	0.8964	#8 of 58	Archive leaderboard	report
Medical Image Segmentation	Kvasir-SEG	LM-Net	Recall	0.9038	#8 of 58	Archive leaderboard	report
Medical Image Segmentation	Kvasir-SEG	LM-Net	mIoU	0.8912	#8 of 58	Archive leaderboard	report
Medical Image Segmentation	Kvasir-SEG	LM-Net	mean Dice	0.9409	#8 of 58	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position Encodings Adam Attention BPE Dense Connections Dropout Label Smoothing Layer Normalization Linear Layer Multi-Head Attention Position-Wise Feed-Forward Layer Residual Connection Softmax Transformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections