Hierarchical Consistency Regularized Mean Teacher for Semi-supervised 3D Left Atrium Segmentation

05/21/2021
by   Shumeng Li, et al.
0

Deep learning has achieved promising segmentation performance on 3D left atrium MR images. However, annotations for segmentation tasks are expensive, costly and difficult to obtain. In this paper, we introduce a novel hierarchical consistency regularized mean teacher framework for 3D left atrium segmentation. In each iteration, the student model is optimized by multi-scale deep supervision and hierarchical consistency regularization, concurrently. Extensive experiments have shown that our method achieves competitive performance as compared with full annotation, outperforming other stateof-the-art semi-supervised segmentation methods.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 3

07/16/2019

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

Training deep convolutional neural networks usually requires a large amo...
07/12/2018

Deep semi-supervised segmentation with weight-averaged consistency targets

Recently proposed techniques for semi-supervised learning such as Tempor...
10/22/2021

Semi-Supervised Semantic Segmentation of Vessel Images using Leaking Perturbations

Semantic segmentation based on deep learning methods can attain appealin...
03/04/2019

Semi-Supervised Brain Lesion Segmentation with an Adapted Mean Teacher Model

Automated brain lesion segmentation provides valuable information for th...
09/17/2021

Adaptive Hierarchical Dual Consistency for Semi-Supervised Left Atrium Segmentation on Cross-Domain Data

Semi-supervised learning provides great significance in left atrium (LA)...
03/24/2021

Hetero-Modal Learning and Expansive Consistency Constraints for Semi-Supervised Detection from Multi-Sequence Data

Lesion detection serves a critical role in early diagnosis and has been ...
11/25/2021

Perturbed and Strict Mean Teachers for Semi-supervised Semantic Segmentation

Consistency learning using input image, feature, or network perturbation...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.