StenUNet: Automatic Stenosis Detection from X-ray Coronary Angiography
This addresses the need for more reliable diagnosis of coronary artery disease, but it is incremental as it builds on existing datasets and methods.
The paper tackles the problem of automating stenosis detection from X-ray coronary angiography to improve reliability over manual methods, achieving an F1 score of 0.5348 and placing 3rd in the ARCADE challenge.
Coronary angiography continues to serve as the primary method for diagnosing coronary artery disease (CAD), which is the leading global cause of mortality. The severity of CAD is quantified by the location, degree of narrowing (stenosis), and number of arteries involved. In current practice, this quantification is performed manually using visual inspection and thus suffers from poor inter- and intra-rater reliability. The MICCAI grand challenge: Automatic Region-based Coronary Artery Disease diagnostics using the X-ray angiography imagEs (ARCADE) curated a dataset with stenosis annotations, with the goal of creating an automated stenosis detection algorithm. Using a combination of machine learning and other computer vision techniques, we propose the architecture and algorithm StenUNet to accurately detect stenosis from X-ray Coronary Angiography. Our submission to the ARCADE challenge placed 3rd among all teams. We achieved an F1 score of 0.5348 on the test set, 0.0005 lower than the 2nd place.