Exploring Unlabeled Data in Multiple Aspects for Semi-Supervised MRI Segmentation-Reference-Cited by-同舟云学术

Exploring Unlabeled Data in Multiple Aspects for Semi-Supervised MRI Segmentation

Published:2024-01 Issue: Volume:4 Page:
ISSN:2765-8783
Container-title:Health Data Science
language:en
Short-container-title:Health Data Sci

Author:

He Qingyuan¹²^ORCID,Yan Kun³^ORCID,Luo Qipeng⁴,Yi Duan⁴,Wang Ping⁵⁶⁷,Han Hongbin¹²,Liu Defeng²⁸

Affiliation:

1. Radiology Department, Peking University Third Hospital, Beijing, China.

2. Peking University Third Hospital, Beijing Key Laboratory of Magnetic Resonance Imaging Devices and Technology, Beijing, China.

3. School of Computer Science, Peking University, Beijing, China.

4. Department of Pain Medicine, Peking University Third Hospital, Beijing, China.

5. School of Software and Microelectronics, Peking University, Beijing, China.

6. National Engineering Research Center for Software Engineering, Peking University, Beijing, China.

7. Key Laboratory of High Confidence Software Technologies (Peking University), Ministry of Education, Beijing, China.

8. Department of Obstetrics and Gynecology, Peking University Third Hospital, Beijing, China.

Abstract

Background: MRI segmentation offers crucial insights for automatic analysis. Although deep learning-based segmentation methods have attained cutting-edge performance, their efficacy heavily relies on vast sets of meticulously annotated data. Methods: In this study, we propose a novel semi-supervised MRI segmentation model that is able to explore unlabeled data in multiple aspects based on various semi-supervised learning technologies. Results: We compared the performance of our proposed method with other deep learning-based methods on 2 public datasets, and the results demonstrated that we have achieved Dice scores of 90.3% and 89.4% on the LA and ACDC datasets, respectively. Conclusions: We explored the synergy of various semi-supervised learning technologies for MRI segmentation, and our investigation will inspire research that focuses on designing MRI segmentation models.

Funder

Proof of Concept Program of Zhongguancun Science City and Peking University Third Hospital

China Postdoctoral Science Foundation

Clinical Medicine Plus X - Young Scholars Project, Peking University, the Fundamental Research Funds for the Central Universities

Beijing Natural Science Foundation

Publisher

American Association for the Advancement of Science (AAAS)

Link

https://spj.science.org/doi/pdf/10.34133/hds.0166

Reference51 articles.

1. Milletari F Navab N Ahmadi SA. V-net: Fully convolutional neural networks for volumetric medical image segmentation. In: 2016 Fourth International Conference on 3D Vision (3DV). Stanford (CA): IEEE; 2016. p. 565–571.

2. Isensee F Petersen J Klein A Zimmerer D Jaeger PF Kohl S Wasserthal J Koehler G Norajitra T Wirkert S et al. nnu-net: Self-adapting framework for u-net-based medical image segmentation. arXiv. 2018. https://doi.org/10.48550/arXiv.1809.10486.

3. AtrialJSQnet: A new framework for joint segmentation and quantification of left atrium and scars incorporating spatial and shape information;Li L;Med Image Anal,2022

4. Jamart K Xiong Z Talou GM Stiles MK Zhao J. Two-stage 2D CNN for automatic atrial segmentation from LGE-MRIs. In: Statistical Atlases and Computational Models of the Heart. Multi-Sequence CMR Segmentation CRT-EPiggy and LV Full Quantification Challenges: 10th International Workshop STACOM 2019 Held in Conjunction with MICCAI 2019 Shenzhen China October 13 2019 Revised Selected Papers 10. Shenzhen China: Springer; 2020. p. 81–89.

5. Wang J Lukasiewicz T. Rethinking bayesian deep learning methods for semi-supervised volumetric medical image segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. New Orleans (LA): IEEE; 2022. p. 182–190.