A New Semi-supervised Learning Benchmark for Classifying View and Diagnosing Aortic Stenosis from Echocardiograms

Zhe Huang, Gary Long, Benjamin Wessler, Michael C. Hughes
Proceedings of the 6th Machine Learning for Healthcare Conference, PMLR 149:614-647, 2021.

Abstract

Semi-supervised image classification has shown substantial progress in learning from limited labeled data, but recent advances remain largely untested for clinical applications. Motivated by the urgent need to improve timely diagnosis of life-threatening heart conditions, especially aortic stenosis, we develop a benchmark dataset to assess semi-supervised approaches to two tasks relevant to cardiac ultrasound (echocardiogram) interpretation: view classification and disease severity classification. We find that a state-of-the-art method called MixMatch achieves promising gains in heldout accuracy on both tasks, learning from a large volume of truly unlabeled images as well as a labeled set collected at great expense to achieve better performance than is possible with the labeled set alone. We further pursue patient-level diagnosis prediction, which requires aggregating across hundreds of images of diverse view types, most of which are irrelevant, to make a coherent prediction. The best patient-level performance is achieved by new methods that prioritize diagnosis predictions from images that are predicted to be clinically-relevant views and transfer knowledge from the view task to the diagnosis task. We hope our released dataset and evaluation framework inspire further improvements in multi-task semi-supervised learning for clinical applications.

Cite this Paper

BibTeX
@InProceedings{pmlr-v149-huang21a, title = {A New Semi-supervised Learning Benchmark for Classifying View and Diagnosing Aortic Stenosis from Echocardiograms}, author = {Huang, Zhe and Long, Gary and Wessler, Benjamin and Hughes, Michael C.}, booktitle = {Proceedings of the 6th Machine Learning for Healthcare Conference}, pages = {614--647}, year = {2021}, editor = {Jung, Ken and Yeung, Serena and Sendak, Mark and Sjoding, Michael and Ranganath, Rajesh}, volume = {149}, series = {Proceedings of Machine Learning Research}, month = {06--07 Aug}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v149/huang21a/huang21a.pdf}, url = {https://proceedings.mlr.press/v149/huang21a.html}, abstract = {Semi-supervised image classification has shown substantial progress in learning from limited labeled data, but recent advances remain largely untested for clinical applications. Motivated by the urgent need to improve timely diagnosis of life-threatening heart conditions, especially aortic stenosis, we develop a benchmark dataset to assess semi-supervised approaches to two tasks relevant to cardiac ultrasound (echocardiogram) interpretation: view classification and disease severity classification. We find that a state-of-the-art method called MixMatch achieves promising gains in heldout accuracy on both tasks, learning from a large volume of truly unlabeled images as well as a labeled set collected at great expense to achieve better performance than is possible with the labeled set alone. We further pursue patient-level diagnosis prediction, which requires aggregating across hundreds of images of diverse view types, most of which are irrelevant, to make a coherent prediction. The best patient-level performance is achieved by new methods that prioritize diagnosis predictions from images that are predicted to be clinically-relevant views and transfer knowledge from the view task to the diagnosis task. We hope our released dataset and evaluation framework inspire further improvements in multi-task semi-supervised learning for clinical applications.} }
Endnote
%0 Conference Paper %T A New Semi-supervised Learning Benchmark for Classifying View and Diagnosing Aortic Stenosis from Echocardiograms %A Zhe Huang %A Gary Long %A Benjamin Wessler %A Michael C. Hughes %B Proceedings of the 6th Machine Learning for Healthcare Conference %C Proceedings of Machine Learning Research %D 2021 %E Ken Jung %E Serena Yeung %E Mark Sendak %E Michael Sjoding %E Rajesh Ranganath %F pmlr-v149-huang21a %I PMLR %P 614--647 %U https://proceedings.mlr.press/v149/huang21a.html %V 149 %X Semi-supervised image classification has shown substantial progress in learning from limited labeled data, but recent advances remain largely untested for clinical applications. Motivated by the urgent need to improve timely diagnosis of life-threatening heart conditions, especially aortic stenosis, we develop a benchmark dataset to assess semi-supervised approaches to two tasks relevant to cardiac ultrasound (echocardiogram) interpretation: view classification and disease severity classification. We find that a state-of-the-art method called MixMatch achieves promising gains in heldout accuracy on both tasks, learning from a large volume of truly unlabeled images as well as a labeled set collected at great expense to achieve better performance than is possible with the labeled set alone. We further pursue patient-level diagnosis prediction, which requires aggregating across hundreds of images of diverse view types, most of which are irrelevant, to make a coherent prediction. The best patient-level performance is achieved by new methods that prioritize diagnosis predictions from images that are predicted to be clinically-relevant views and transfer knowledge from the view task to the diagnosis task. We hope our released dataset and evaluation framework inspire further improvements in multi-task semi-supervised learning for clinical applications.
APA
Huang, Z., Long, G., Wessler, B. & Hughes, M.C.. (2021). A New Semi-supervised Learning Benchmark for Classifying View and Diagnosing Aortic Stenosis from Echocardiograms. Proceedings of the 6th Machine Learning for Healthcare Conference, in Proceedings of Machine Learning Research 149:614-647 Available from https://proceedings.mlr.press/v149/huang21a.html.

Related Material