M^{2}SNet: Multi-scale in Multi-scale Subtraction Network for Medical Image Segmentation
Summary
This paper proposes M2SNet, a multi-scale multi-scale subtraction network for medical image segmentation that uses subtraction operations to capture difference features between encoder levels, improving localization and edge sharpness. It achieves state-of-the-art performance on eleven datasets across four medical imaging modalities.
View Cached Full Text
Cached at: 08/13/26, 03:34 PM
Paper page - M^{2}SNet: Multi-scale in Multi-scale Subtraction Network for Medical Image Segmentation
Source: https://huggingface.co/papers/2303.10894 Published on Mar 20, 2023
Abstract
A multi-scale subtraction network (M^\{2\}SNet) enhances medical image segmentation by capturing detailed and structural cues, improving localization and edge sharpness compared to traditional methods.
Accuratemedical image segmentationis critical for early medical diagnosis. Most existing methods are based onU-shape structureand useelement-wise additionorconcatenationto fuse different level features progressively in decoder. However, both the two operations easily generate plenty of redundant information, which will weaken the complementarity between different level features, resulting in inaccurate localization and blurred edges of lesions. To address this challenge, we propose a general multi-scale in multi-scale subtraction network (M^{2}SNet) to finish diverse segmentation from medical image. Specifically, we first design a basicsubtraction unit (SU)to produce the difference features between adjacent levels in encoder. Next, we expand the single-scale SU to theintra-layer multi-scale SU, which can provide the decoder with both pixel-level and structure-level difference information. Then, we pyramidally equip the multi-scale SUs at different levels with varyingreceptive fields, thereby achieving theinter-layer multi-scale feature aggregationand obtaining rich multi-scale difference information. In addition, we build a training-free network ``LossNet’’ to comprehensively supervise thetask-aware featuresfrom bottom layer to top layer, which drives our multi-scale subtraction network to capture the detailed and structural cues simultaneously. Without bells and whistles, our method performs favorably against most state-of-the-art methods under different evaluation metrics on eleven datasets of four differentmedical image segmentationtasks of diverse image modalities, includingcolor colonoscopy imaging,ultrasound imaging,computed tomography (CT), andoptical coherence tomography (OCT). The source code can be available at https://github.com/Xiaoqi-Zhao-DLUT/MSNet.
View arXiv pageView PDFGitHub588autoAdd to collection
Get this paper in your agent:
hf papers read 2303\.10894
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2303.10894 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2303.10894 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2303.10894 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
MSAIC-Net: A Multi-Scale Attention and Imbalance-Aware Contrastive Network for ECG-Based Myocardial Substrate Abnormality Detection
Proposes MSAIC-Net, a multi-scale attention-enhanced convolutional network for detecting myocardial substrate abnormalities from ECG signals, using imbalance-aware contrastive learning and lead-wise permutation importance for interpretability.
Partial Information Decomposition as a Multi-Contrast 3D MRI Selection Strategy for Resource-Constrained Deep Neural Network Training in Brain Tumor Segmentation
This paper proposes a Partial Information Decomposition framework to select the most informative pair of MRI contrasts for brain tumor segmentation using lightweight 3D U-Nets, reducing computational cost while maintaining performance.
M2Retinexformer: Multi-Modal Retinexformer for Low-Light Image Enhancement
M2Retinexformer extends the Retinexformer framework for low-light image enhancement by incorporating depth, luminance, and semantic cues via cross-attention and adaptive gating, achieving state-of-the-art results on multiple benchmarks.
Better, Stronger, Faster, and Broader: Structured All-Mask Prediction for MLLM-Based Segmentation
This paper introduces Structured All-Mask Prediction and STAMPlus, a method for MLLM-based segmentation that jointly predicts all target masks in one non-autoregressive pass, resolving the trilemma of high segmentation performance, preserved dialogue ability, and fast inference.
Hierarchical Multi-Scale Graph Neural Networks: Scalable Heterophilous Learning with Oversmoothing and Oversquashing Mitigation
This paper introduces HMH, a hierarchical multi-scale Graph Neural Network framework designed to address oversmoothing and oversquashing in heterophilous graphs. It utilizes spectral filters with Haar bases to achieve scalable learning and improved performance on node and graph classification tasks.