Inherent Consistent Learning for Accurate Semi-supervised Medical Image Segmentation (2023-03-24T00:00:00.000000Z)

TL;DR

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.

Abstract

Semi-supervised medical image segmentation has attracted much attention in recent years because of the high cost of medical image annotations. In this paper, we propose a novel Inherent Consistent Learning (ICL) method, aims to learn robust semantic category representations through the semantic consistency guidance of labeled and unlabeled data to help segmentation. In practice, we introduce two external modules, namely Supervised Semantic Proxy Adaptor (SSPA) and Unsupervised Semantic Consistent Learner (USCL) that is based on the attention mechanism to align the semantic category representations of labeled and unlabeled data, as well as update the global semantic representations over the entire training set. The proposed ICL is a plug-and-play scheme for various network architectures, and the two modules are not involved in the testing stage. Experimental results on three public benchmarks show that the proposed method can outperform the state-of-the-art, especially when the number of annotated data is extremely limited. Code is available at: https://github.com/zhuye98/ICL.git.

Authors

Jie Yang

4 papers

Ye Zhu

2 papers

Ruimao Zhang

5 papers

Inherent Consistent Learning for Accurate Semi-supervised Medical Image Segmentation

TL;DR

Abstract

Authors

References27 items

Learning with Limited Annotations: A Survey on Deep Semi-Supervised Learning for Medical Image Segmentation

AMOS: A Large-Scale Abdominal Multi-Organ Benchmark for Versatile Medical Image Segmentation

Semi-supervised medical image segmentation via uncertainty rectified pyramid consistency

Swin UNETR: Swin Transformers for Semantic Segmentation of Brain Tumors in MRI Images

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

The Bottleneck

R-Drop: Regularized Dropout for Neural Networks

Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision

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

Segmenter: Transformer for Semantic Segmentation

TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation

Self-paced and self-consistent co-training for semi-supervised image segmentation

PseudoSeg: Designing Pseudo Labels for Semantic Segmentation

Semi-Supervised Semantic Segmentation With Cross-Consistency Training

FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence

PyTorch: An Imperative Style, High-Performance Deep Learning Library

Deep Co-Training for Semi-Supervised Image Segmentation

ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation

Deep learning in medical imaging and radiation therapy.

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

DeepIGeoS: A Deep Interactive Geodesic Framework for Medical Image Segmentation

The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS)

U-Net: Convolutional Networks for Biomedical Image Segmentation

Learning with Pseudo-Ensembles

Segmenting transparent object in the wild with transformer

Visualizing Data using t-SNE

Field of Study

Venue Information

Name

Type

URL

Alternate Names