Shape-Aware Adversarial Learning for Scribble-Supervised Medical Image Segmentation with a MaskMix Siamese Network: A Case Study of Cardiac MRI Segmentation

The transition in medical image segmentation from fine-grained to coarse-grained annotation methods, notably scribble annotation, offers a practical and efficient preparation for deep learning applications. However, these methods often compromise segmentation precision and result in irregular contou...

Full description

Saved in:
Bibliographic Details
Main Authors: Chen Li, Zhong Zheng, Di Wu
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Bioengineering
Subjects:
Online Access:https://www.mdpi.com/2306-5354/11/11/1146
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850267234953330688
author Chen Li
Zhong Zheng
Di Wu
author_facet Chen Li
Zhong Zheng
Di Wu
author_sort Chen Li
collection DOAJ
description The transition in medical image segmentation from fine-grained to coarse-grained annotation methods, notably scribble annotation, offers a practical and efficient preparation for deep learning applications. However, these methods often compromise segmentation precision and result in irregular contours. This study targets the enhancement of scribble-supervised segmentation to match the accuracy of fine-grained annotation. Capitalizing on the consistency of target shapes across unpaired datasets, this study introduces a shape-aware scribble-supervised learning framework (MaskMixAdv) addressing two critical tasks: (1) Pseudo label generation, where a mixup-based masking strategy enables image-level and feature-level data augmentation to enrich coarse-grained scribbles annotations. A dual-branch siamese network is proposed to generate fine-grained pseudo labels. (2) Pseudo label optimization, where a CNN-based discriminator is proposed to refine pseudo label contours by distinguishing them from external unpaired masks during model fine-tuning. MaskMixAdv works under constrained annotation conditions as a label-efficient learning approach for medical image segmentation. A case study on public cardiac MRI datasets demonstrated that the proposed MaskMixAdv outperformed the state-of-the-art methods and narrowed the performance gap between scribble-supervised and mask-supervised segmentation. This innovation cuts annotation time by at least 95%, with only a minor impact on Dice performance, specifically a 2.6% reduction. The experimental outcomes indicate that employing efficient and cost-effective scribble annotation can achieve high segmentation accuracy, significantly reducing the typical requirement for fine-grained annotations.
format Article
id doaj-art-51ee4e97f89d4b919caedc41519eb342
institution OA Journals
issn 2306-5354
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Bioengineering
spelling doaj-art-51ee4e97f89d4b919caedc41519eb3422025-08-20T01:53:52ZengMDPI AGBioengineering2306-53542024-11-011111114610.3390/bioengineering11111146Shape-Aware Adversarial Learning for Scribble-Supervised Medical Image Segmentation with a MaskMix Siamese Network: A Case Study of Cardiac MRI SegmentationChen Li0Zhong Zheng1Di Wu2College of Computer Science and Technology, National University of Defense Technology, Changsha 410073, ChinaCollege of Computer Science and Technology, National University of Defense Technology, Changsha 410073, ChinaCollege of Computer Science and Technology, National University of Defense Technology, Changsha 410073, ChinaThe transition in medical image segmentation from fine-grained to coarse-grained annotation methods, notably scribble annotation, offers a practical and efficient preparation for deep learning applications. However, these methods often compromise segmentation precision and result in irregular contours. This study targets the enhancement of scribble-supervised segmentation to match the accuracy of fine-grained annotation. Capitalizing on the consistency of target shapes across unpaired datasets, this study introduces a shape-aware scribble-supervised learning framework (MaskMixAdv) addressing two critical tasks: (1) Pseudo label generation, where a mixup-based masking strategy enables image-level and feature-level data augmentation to enrich coarse-grained scribbles annotations. A dual-branch siamese network is proposed to generate fine-grained pseudo labels. (2) Pseudo label optimization, where a CNN-based discriminator is proposed to refine pseudo label contours by distinguishing them from external unpaired masks during model fine-tuning. MaskMixAdv works under constrained annotation conditions as a label-efficient learning approach for medical image segmentation. A case study on public cardiac MRI datasets demonstrated that the proposed MaskMixAdv outperformed the state-of-the-art methods and narrowed the performance gap between scribble-supervised and mask-supervised segmentation. This innovation cuts annotation time by at least 95%, with only a minor impact on Dice performance, specifically a 2.6% reduction. The experimental outcomes indicate that employing efficient and cost-effective scribble annotation can achieve high segmentation accuracy, significantly reducing the typical requirement for fine-grained annotations.https://www.mdpi.com/2306-5354/11/11/1146medical image segmentationshape-aware adversarial learningscribble annotationsiamese networkcardiac MRI
spellingShingle Chen Li
Zhong Zheng
Di Wu
Shape-Aware Adversarial Learning for Scribble-Supervised Medical Image Segmentation with a MaskMix Siamese Network: A Case Study of Cardiac MRI Segmentation
Bioengineering
medical image segmentation
shape-aware adversarial learning
scribble annotation
siamese network
cardiac MRI
title Shape-Aware Adversarial Learning for Scribble-Supervised Medical Image Segmentation with a MaskMix Siamese Network: A Case Study of Cardiac MRI Segmentation
title_full Shape-Aware Adversarial Learning for Scribble-Supervised Medical Image Segmentation with a MaskMix Siamese Network: A Case Study of Cardiac MRI Segmentation
title_fullStr Shape-Aware Adversarial Learning for Scribble-Supervised Medical Image Segmentation with a MaskMix Siamese Network: A Case Study of Cardiac MRI Segmentation
title_full_unstemmed Shape-Aware Adversarial Learning for Scribble-Supervised Medical Image Segmentation with a MaskMix Siamese Network: A Case Study of Cardiac MRI Segmentation
title_short Shape-Aware Adversarial Learning for Scribble-Supervised Medical Image Segmentation with a MaskMix Siamese Network: A Case Study of Cardiac MRI Segmentation
title_sort shape aware adversarial learning for scribble supervised medical image segmentation with a maskmix siamese network a case study of cardiac mri segmentation
topic medical image segmentation
shape-aware adversarial learning
scribble annotation
siamese network
cardiac MRI
url https://www.mdpi.com/2306-5354/11/11/1146
work_keys_str_mv AT chenli shapeawareadversariallearningforscribblesupervisedmedicalimagesegmentationwithamaskmixsiamesenetworkacasestudyofcardiacmrisegmentation
AT zhongzheng shapeawareadversariallearningforscribblesupervisedmedicalimagesegmentationwithamaskmixsiamesenetworkacasestudyofcardiacmrisegmentation
AT diwu shapeawareadversariallearningforscribblesupervisedmedicalimagesegmentationwithamaskmixsiamesenetworkacasestudyofcardiacmrisegmentation