Evaluating semi-supervision methods for medical image segmentation: applications in cardiac magnetic resonance imaging

Sarah M. Hooper; Sen Wu; Rhodri H. Davies; Anish Bhuva; Erik B. Schelbert; James C. Moon; Peter Kellman; Hui Xue; Curtis Langlotz; Christopher Ré

doi:10.1117/1.JMI.10.2.024007

30 March 2023 Evaluating semi-supervision methods for medical image segmentation: applications in cardiac magnetic resonance imaging

Sarah M. Hooper, Sen Wu, Rhodri H. Davies, Anish Bhuva, Erik B. Schelbert, James C. Moon, Peter Kellman, Hui Xue, Curtis Langlotz, Christopher Ré

Author Affiliations +

Journal of Medical Imaging, Vol. 10, Issue 2, 024007 (March 2023). https://doi.org/10.1117/1.JMI.10.2.024007

Abstract

Purpose

Neural networks have potential to automate medical image segmentation but require expensive labeling efforts. While methods have been proposed to reduce the labeling burden, most have not been thoroughly evaluated on large, clinical datasets or clinical tasks. We propose a method to train segmentation networks with limited labeled data and focus on thorough network evaluation.

Approach

We propose a semi-supervised method that leverages data augmentation, consistency regularization, and pseudolabeling and train four cardiac magnetic resonance (MR) segmentation networks. We evaluate the models on multiinstitutional, multiscanner, multidisease cardiac MR datasets using five cardiac functional biomarkers, which are compared to an expert’s measurements using Lin’s concordance correlation coefficient (CCC), the within-subject coefficient of variation (CV), and the Dice coefficient.

Results

The semi-supervised networks achieve strong agreement using Lin’s CCC (>0.8), CV similar to an expert, and strong generalization performance. We compare the error modes of the semi-supervised networks against fully supervised networks. We evaluate semi-supervised model performance as a function of labeled training data and with different types of model supervision, showing that a model trained with 100 labeled image slices can achieve a Dice coefficient within 1.10% of a network trained with 16,000+ labeled image slices.

Conclusion

We evaluate semi-supervision for medical image segmentation using heterogeneous datasets and clinical metrics. As methods for training models with little labeled data become more common, knowledge about how they perform on clinical tasks, how they fail, and how they perform with different amounts of labeled data is useful to model developers and users.

Citation Download Citation

Sarah M. Hooper, Sen Wu, Rhodri H. Davies, Anish Bhuva, Erik B. Schelbert, James C. Moon, Peter Kellman, Hui Xue, Curtis Langlotz, and Christopher Ré "Evaluating semi-supervision methods for medical image segmentation: applications in cardiac magnetic resonance imaging," Journal of Medical Imaging 10(2), 024007 (30 March 2023). https://doi.org/10.1117/1.JMI.10.2.024007

Received: 2 August 2022; Accepted: 27 February 2023; Published: 30 March 2023

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

;

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE