Home

Awesome

MSNet&M2SNet

<p align="center"> <img src="./image/logo.png" alt="Logo" width="150" height="auto"> <h3 align="center">MSNet: Automatic Polyp Segmentation via Multi-scale Subtraction Network</h3> <p align="center"> Xiaoqi Zhao, Lihe Zhang, Huchuan Lu <br /> <a href="https://arxiv.org/pdf/2108.05082.pdf"><strong>⭐ arXiv »</strong></a> <br /> </p> <h3 align="center">M2SNet: Multi-scale in Multi-scale Subtraction Network for Medical Image Segmentation</h3> <p align="center"> Xiaoqi Zhao, Hongpeng Jia, Youwei Pang, Long Lv, Feng Tian, Lihe Zhang, Weibing Sun, Huchuan Lu <br /> <a href="https://arxiv.org/pdf/2303.10894.pdf"><strong>⭐ arXiv »</strong></a> <br /> </p> </p> <p align="center"> <img src="./image/MICCAI_2022_GOALS_award.jpg"/> <br /> </p>

Datasets

Results

Trained Model

Highlight

Novel Segmentation Architectures

<p align="center"> <img src="./image/network_structure_compare.png"/> <br /> </p>

Efficient Intra-Layer Multi-scale Subtraction Design

<p align="center"> <img src="./image/intra_layer_mssu.png"/> <br /> </p> <p align="center"> <img src="./image/intra-layer-ms-compare.png"/> <br /> </p>

Efficient Inter-Layer Multi-scale Subtraction Structure

<p align="center"> <img src="./image/inter_layer_ms.png"/> <br /> </p>

Training-free Loss Network

<p align="center"> <img src="./image/lossnet.png"/> <br /> </p>

Low FLOPs (comparisons under the Res2Net-50 backbone)

<p align="center"> <img src="./image/Flops_compare.png"/> <br /> </p>

Prerequisites

Training/Inference/Testing

    Dataset.Config(datapath='', savepath='', mode='train', batch=16, lr=0.05, momen=0.9, decay=5e-4, epoch='')
    %the number of training epochs settings in the polyp segmentation, COVID-19 Lung Infection, breast tumor segmentation and OCT layer segmentation are 50, 200, 100         and 100, respectively.
    python train.py

TODO LIST

BibTex

@inproceedings{MSNet,
  title={Automatic polyp segmentation via multi-scale subtraction network},
  author={Zhao, Xiaoqi and Zhang, Lihe and Lu, Huchuan},
  booktitle={MICCAI},
  pages={120--130},
  year={2021},
  organization={Springer}
}
@article{M2SNet,
  title={M $\^{}$\{$2$\}$ $ SNet: Multi-scale in Multi-scale Subtraction Network for Medical Image Segmentation},
  author={Zhao, Xiaoqi and Jia, Hongpeng and Pang, Youwei and Lv, Long and Tian, Feng and Zhang, Lihe and Sun, Weibing and Lu, Huchuan},
  journal={arXiv preprint arXiv:2303.10894},
  year={2023}
}