Automated Coronary Calcium Scoring using U-Net Models through Semi-supervised Learning on Non-Gated CT Scans
This addresses a critical healthcare problem for patients at risk of undiagnosed heart attacks by enabling calcium scoring on widely available non-gated scans, representing a domain-specific incremental improvement.
The paper tackled automated coronary calcium scoring on non-gated CT scans, which are more common but harder to analyze than gated scans, by using a U-Net model with semi-supervised learning to improve performance from a mean absolute error of 674.19 to 62.38 and accuracy from 41% to 64%.
Every year, thousands of innocent people die due to heart attacks. Often undiagnosed heart attacks can hit people by surprise since many current medical plans don't cover the costs to require the searching of calcification on these scans. Only if someone is suspected to have a heart problem, a gated CT scan is taken, otherwise, there's no way for the patient to be aware of a possible heart attack/disease. While nongated CT scans are more periodically taken, it is harder to detect calcification and is usually taken for a purpose other than locating calcification in arteries. In fact, in real time coronary artery calcification scores are only calculated on gated CT scans, not nongated CT scans. After training a unet model on the Coronary Calcium and chest CT's gated scans, it received a DICE coefficient of 0.95 on its untouched test set. This model was used to predict on nongated CT scans, performing with a mean absolute error (MAE) of 674.19 and bucket classification accuracy of 41% (5 classes). Through the analysis of the images and the information stored in the images, mathematical equations were derived and used to automatically crop the images around the location of the heart. By performing semi-supervised learning the new cropped nongated scans were able to closely resemble gated CT scans, improving the performance by 91% in MAE (62.38) and 23% in accuracy.