Disarranged Zone Learning (DZL): An unsupervised and dynamic automatic stenosis recognition methodology based on coronary angiography

TL;DR

This paper introduces Disarranged Zone Learning (DZL), an unsupervised method that automatically detects coronary artery stenosis from angiography videos by learning to recover disarranged frames, achieving high accuracy without labeled data.

Contribution

The study presents a novel self-supervised approach using sequence recovery as an indicator of stenosis, enabling unsupervised learning from large datasets without label engineering.

Findings

Average precision score of 0.93 and AUC of 0.8 for stenosis detection.

Segmented average precision of 0.98 and AUC of 0.87 for coronary occlusion.

DZL is easy to implement and generalizes well across data heterogeneity.

Abstract

We proposed a novel unsupervised methodology named Disarranged Zone Learning (DZL) to automatically recognize stenosis in coronary angiography. The methodology firstly disarranges the frames in a video, secondly it generates an effective zone and lastly trains an encoder-decoder GRU model to learn the capability to recover disarranged frames. The breakthrough of our study is to discover and validate the Sequence Intensity (Recover Difficulty) is a measure of Coronary Artery Stenosis Status. Hence, the prediction accuracy of DZL is used as an approximator of coronary stenosis indicator. DZL is an unsupervised methodology and no label engineering effort is needed, the sub GRU model in DZL works as a self-supervised approach. So DZL could theoretically utilize infinitely huge amounts of coronary angiographies to learn and improve performance without laborious data labeling. There is no data preprocessing precondition to run DZL as it dynamically utilizes the whole video, hence it is easy to be implemented and generalized to overcome the data heterogeneity of coronary angiography. The overall average precision score achieves 0.93, AUC achieves 0.8 for this pure methodology. The highest segmented average precision score is 0.98 and the highest segmented AUC is 0.87 for coronary occlusion indicator. Finally, we developed a software demo to implement DZL methodology.