medical-3

Semi-supervised Medical Image Segmentation

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in semi-supervised-medical-image-segmentation-3

Trend

Dataset

Best Model

Actions

ACDC 20% labeled data

ACDC 10% labeled data

Libraries

i

Use these libraries to find semi-supervised-medical-image-segmentation-3 models and implementations

HiLab-git/SSL4MIS

9 papers 1,977

Datasets

ACDC

MM-WHS 2017

Subtasks

No subtasks available.

Most implemented papers

Mutual consistency learning for semi-supervised medical image segmentation

Yicheng Wu, Jianfei Cai, Donghao Zhang, Z. Ge, Minfeng Xu, Lei Zhang, Yong Xia•Mon Sep 20 2021

A novel mutual consistency network (MC-Net+) is proposed to effectively exploit the unlabeled data for semi-supervised medical image segmentation to force the model to generate invariant results in such challenging regions, aiming at regularizing the model training.

347

Content

MM-WHS 2017

ACDC 5% labeled data

Lesion Segmentation on ISIC 2018

0

Paper Graph

MisMatch: Calibrated Segmentation via Consistency on Differential Morphological Feature Perturbations With Limited Labels

Joseph Jacob, N. Oxtoby, Chen Jin, Moucheng Xu, Yukun Zhou, M. Groot, Daniel C. Alexander•Fri Oct 22 2021

This paper proposes MisMatch, a semi-supervised segmentation framework based on the consistency between paired predictions which are derived from two differently learnt morphological feature perturbations and develops a 2D U-net based MisMatch framework and performs extensive cross-validation on a CT-based pulmonary vessel segmentation task.

13 0

Paper Graph

Exploring Smoothness and Class-Separation for Semi-supervised Medical Image Segmentation

ZongYuan Ge, Qianyi Wu, Zhonghua Wu, Yicheng Wu, Jianfei Cai•Tue Mar 01 2022

The proposed SS-Net is proposed for semi-supervised medical image segmentation tasks, via exploring the pixel-level smoothness and inter-class separation at the same time and achieving new state-of-the-art (SOTA) performance on both datasets.

229 0

Paper Graph

When CNN Meet with ViT: Towards Semi-Supervised Learning for Multi-Class Medical Image Semantic Segmentation

Baoru Huang, Jian-Qing Zheng, Ziyang Wang, Tianze Li•Thu Aug 11 2022

An advanced consistency-aware pseudo-label-based self-ensembling approach is presented to fully utilize the power of Vision Transformer and Convolutional Neural Network in semi-supervised learning.

50 0

Paper Graph

Pseudo-Label Guided Contrastive Learning for Semi-Supervised Medical Image Segmentation

Hritam Basak•Wed May 31 2023

Although recent works in semi-supervised learning (SemiSL) have accomplished significant success in natural image segmentation, the task of learning discriminative representations from limited annotations has been an open problem in medical images. Contrastive Learning (CL) frameworks use the notion of similarity measure which is useful for classification problems, however, they fail to transfer these quality representations for accurate pixel-level segmentation. To this end, we propose a novel semi-supervised patch-based CL framework for medical image segmentation without using any explicit pretext task. We harness the power of both CL and SemiSL, where the pseudo-labels generated from SemiSL aid CL by providing additional guidance, whereas discriminative class information learned in CL leads to accurate multi-class segmentation. Additionally, we formulate a novel loss that synergistically encourages inter-class separability and intraclass compactness among the learned representations. A new inter-patch semantic disparity mapping using average patch entropy is employed for a guided sampling of positives and negatives in the proposed CL framework. Experimental analysis on three publicly available datasets of multiple modalities reveals the superiority of our proposed method as compared to the state-of-the-art methods. Code is available at: GitHub.

121 0

Paper Graph

ACTION++: Improving Semi-supervised Medical Image Segmentation with Adaptive Anatomical Contrast

Chenyu You, Weicheng Dai, Yifei Min, L. Staib, J. Sekhon, J. Duncan•Tue Apr 04 2023

This work proposes an adaptive supervised contrastive loss, where it is argued that blindly adopting a constant temperature τ in the contrastive loss on long-tailed medical data is not optimal, and proposes to use a dynamic τ via a simple cosine schedule to yield better separation between majority and minority classes.

70 0

Paper Graph

Inherent Consistent Learning for Accurate Semi-supervised Medical Image Segmentation

Jie Yang, Ye Zhu, Ruimao Zhang, Sichen Liu•Thu Mar 23 2023

Experimental results on three public benchmarks show that the proposed ICL method can outperform the state-of-the-art, especially when the number of annotated data is extremely limited.

7 0

Paper Graph

Bidirectional Copy-Paste for Semi-Supervised Medical Image Segmentation

Wei-lei Shen, Yunhao Bai, Duowen Chen, Qingli Li, Yan Wang•Sun Apr 30 2023

It is revealed that the simple mechanism of copy-pasting bidirectionally between labeled and unlabeled data is good enough and the experiments show solid gains compared with other state-of-the-arts on various semi-supervised medical image segmentation datasets.

270 0

Paper Graph

A Generic Ensemble Based Deep Convolutional Neural Network for Semi-Supervised Medical Image Segmentation

Ruizhe Li, D. Auer, Christian Wagner, Xin Chen•Tue Mar 31 2020

This work proposes a generic semi-supervised learning framework for image segmentation based on a deep convolutional neural network (DCNN) and is able to significantly improve beyond fully supervised model learning by incorporating unlabeled data.

18 0

Paper Graph

Semi-supervised Medical Image Segmentation through Dual-task Consistency

Jieneng Chen, Guotai Wang, Shaoting Zhang, Xiangde Luo, Tao Song, Yinan Chen•Tue Sep 08 2020

This work proposes a novel dual-task-consistency semi-supervised framework that can largely improve the performance by incorporating the unlabeled data and outperforms the state-of-the-art semi- supervised learning methods.

704 0

Paper Graph

Adding a benchmark result helps the community track progress.