Compete to Win: Enhancing Pseudo Labels for Barely-Supervised Medical Image Segmentation (2023-04-15T00:00:00.000000Z)

TL;DR

This paper proposes a novel Compete-to-Win method (ComWin) to enhance the pseudo label quality, which can achieve the best performance on three public medical image datasets for cardiac structure segmentation, pancreas segmentation and colon tumor segmentation.

Abstract

This study investigates barely-supervised medical image segmentation where only few labeled data, i.e., single-digit cases are available. We observe the key limitation of the existing state-of-the-art semi-supervised solution cross pseudo supervision is the unsatisfactory precision of foreground classes, leading to a degenerated result under barely-supervised learning. In this paper, we propose a novel Compete-to-Win method (ComWin) to enhance the pseudo label quality. In contrast to directly using one model’s predictions as pseudo labels, our key idea is that high-quality pseudo labels should be generated by comparing multiple confidence maps produced by different networks to select the most confident one (a compete-to-win strategy). To further refine pseudo labels at near-boundary areas, an enhanced version of ComWin, namely, ComWin $^{+}$ , is proposed by integrating a boundary-aware enhancement module. Experiments show that our method can achieve the best performance on three public medical image datasets for cardiac structure segmentation, pancreas segmentation and colon tumor segmentation, respectively. The source code is now available at https://github.com/Huiimin5/comwin.

Authors

Kwang-Ting Cheng

2 papers

X. Li

4 papers

Yiqun Lin

2 papers

TL;DR

Abstract

Authors

References64 items

ShapePU: A New PU Learning Framework Regularized by Global Consistency for Scribble Supervised Cardiac Segmentation

FreeMatch: Self-adaptive Thresholding for Semi-supervised Learning

SSA-Net: Spatial self-attention network for COVID-19 pneumonia infection segmentation with semi-supervised few-shot learning

Translation Consistent Semi-Supervised Segmentation for 3D Medical Images

Barely-Supervised Learning: Semi-Supervised Learning with very few labeled images

Semi-Supervised Medical Image Segmentation via Cross Teaching between CNN and Transformer

Semi-supervised NPC segmentation with uncertainty and attention guided consistency

Embryo Grading With Unreliable Labels Due to Chromosome Abnormalities by Regularized PU Learning With Ranking

Semi-supervised Learning via Improved Teacher-Student Network for Robust 3D Reconstruction of Stereo Endoscopic Image

A Positive/Unlabeled Approach for the Segmentation of Medical Sequences using Point-Wise Supervision

Positive-unlabeled Learning for Cell Detection in Histopathology Images with Incomplete Annotations

ST++: Make Self-trainingWork Better for Semi-supervised Semantic Segmentation

Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision

Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation

Every Annotation Counts: Multi-label Deep Supervision for Medical Image Segmentation

Medical Image Segmentation With Limited Supervision: A Review of Deep Network Models

Efficient Semi-supervised Gross Target Volume of Nasopharyngeal Carcinoma Segmentation via Uncertainty Rectified Pyramid Consistency

PseudoSeg: Designing Pseudo Labels for Semantic Segmentation

DMNet: Difference Minimization Network for Semi-supervised Segmentation in Medical Images

Local and Global Structure-Aware Entropy Regularized Mean Teacher Model for 3D Left Atrium Segmentation

Semi-supervised Medical Image Segmentation through Dual-task Consistency

Shape-aware Semi-supervised 3D Semantic Segmentation for Medical Images

Deeply-Supervised Networks With Threshold Loss for Cancer Detection in Automated Breast Ultrasound

Curriculum Labeling: Revisiting Pseudo-Labeling for Semi-Supervised Learning

Uncertainty Guided Semi-supervised Segmentation of Retinal Layers in OCT Images

Embracing Imperfect Datasets: A Review of Deep Learning Solutions for Medical Image Segmentation

Interlaced Sparse Self-Attention for Semantic Segmentation

Uncertainty-aware Self-ensembling Model for Semi-supervised 3D Left Atrium Segmentation

Transformation-Consistent Self-Ensembling Model for Semisupervised Medical Image Segmentation

A large annotated medical image dataset for the development and evaluation of segmentation algorithms

Semi-supervised Skin Lesion Segmentation via Transformation Consistent Self-ensembling Model

Tri-net for Semi-Supervised Deep Learning

Deep Learning Techniques for Automatic MRI Cardiac Multi-Structures Segmentation and Diagnosis: Is the Problem Solved?

Semi-Supervised 3D Abdominal Multi-Organ Segmentation Via Deep Multi-Planar Co-Training

Deep Co-Training for Semi-Supervised Image Recognition

Non-local Neural Networks

Recurrent Saliency Transformation Network: Incorporating Multi-stage Visual Cues for Small Organ Segmentation

Semi-supervised Learning for Network-Based Cardiac MR Image Segmentation

Deep Adversarial Networks for Biomedical Image Segmentation Utilizing Unannotated Images

Attention is All you Need

Bayesian belief network for positive unlabeled learning with uncertainty

Deeply-supervised CNN for prostate segmentation

Positive-Unlabeled Learning with Non-Negative Risk Estimator

Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results

V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation

Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learning

Theoretical Comparisons of Positive-Unlabeled Learning against Positive-Negative Learning

DeepOrgan: Multi-level Deep Convolutional Networks for Automated Pancreas Segmentation

U-Net: Convolutional Networks for Biomedical Image Segmentation

An RKHS for multi-view learning and manifold co-regularization

Semi-supervised Learning by Entropy Minimization

Learning to Classify Texts Using Positive and Unlabeled Data

Partially Supervised Classification of Text Documents

PAC Generalization Bounds for Co-training

Bootstrapping

Unsupervised Word Sense Disambiguation Rivaling Supervised Methods

Class-Imbalanced Semi-Supervised Learning with Adaptive Thresholding

Swin Transformer: Hierarchical Vision Transformer using Shifted Windows

Dual Student: Breaking the Limits of the Teacher in Semi-supervised Learning

Segmentation

A Co-Regularization Approach to Semi-supervised Learning with Multiple Views

Unsupervised Models for Named Entity Classification

“Combining labeled and unlabeled data with co-training,”

Ieee Transactions on Pattern Analysis and Machine Intelligence Classification with Noisy Labels by Importance Reweighting

Field of Study

Journal Information

Name

Page

Volume

Venue Information

Name

Type

URL

Alternate Names