Home

Awesome

S<sup>2</sup>ME

Introduction

S<sup>2</sup>ME: Spatial-Spectral Mutual Teaching and Ensemble Learning for Scribble-supervised Polyp Segmentation

PDF: arXiv Springer

An Wang, Mengya Xu, Yang Zhang, Mobarakol Islam, and Hongliang Ren

Medical Image Computing and Computer-Assisted Intervention (MICCAI) - 2023

Early Accepted (Top 14% of 2253 manuscripts)

To our best knowledge, we propose the first spatial-spectral dual-branch network structure for weakly-supervised medical image segmentation that efficiently leverages cross-domain patterns with collaborative mutual teaching and ensemble learning. Our pixel-level entropy-guided fusion strategy advances the reliability of the aggregated pseudo labels, which provides valuable supplementary supervision signals. Moreover, we optimize the segmentation model with the hybrid mode of loss supervision from scribbles and pseudo labels in a holistic manner and witness improved outcomes. With extensive in-domain and out-ofdomain evaluation on four public datasets, our method shows superior accuracy, generalization, and robustness, indicating its clinical significance in alleviating data-related issues such as data shift and corruption which are commonly encountered in the medical field.

s2me

Environment

Usage

  1. Dataset

    • SUN-SEG: Download from SUN-SEG, then follow the json files in the folder data/polyp for splits.
    • Kvasir-SEG: Download from Kvasir-SEG.
    • CVC-ClinicDB: Download from CVC-ClinicDB.
    • PolypGen: Download from PolypGen.
  2. Training and Testing

  1. Test Result

    • In-domain quantitative performance
    <div align=center> <img src=Image/Table1.png width=600 height=250> <div align=left>
    • In-domain qualitative performance
    <div align=center> <img src=Image/Fig2.png width=500 height=140> <div align=left>
    • Generalization performance
    <div align=center> <img src=Image/TableGen1.png width=450 height=190> <div align=left> <div align=center> <img src=Image/TableGen2.png width=450 height=190> <div align=left> <div align=center> <img src=Image/TableGen3.png width=450 height=190> <div align=left>
    • Ablation Studies
    <div align=center> <img src=Image/Table3.png width=550 height=110> <div align=left> <div align=center> <img src=Image/Table45.png width=550 height=140> <div align=left>

Citation

@InProceedings{Wang2023s2me,
author="Wang, An
and Xu, Mengya
and Zhang, Yang
and Islam, Mobarakol
and Ren, Hongliang",
title="S{\$}{\$}^2{\$}{\$}ME: Spatial-Spectral Mutual Teaching and Ensemble Learning for Scribble-Supervised Polyp Segmentation",
booktitle="Medical Image Computing and Computer Assisted Intervention -- MICCAI 2023",
year="2023",
publisher="Springer Nature Switzerland",
address="Cham",
pages="35--45",
}

Acknowledgement

Some of the codes are borrowed/refer from below repositories: