AI predicts cardiovascular risk during CT scans—no invasive tests or contrast required

Advanced artificial intelligence (AI) models can evaluate cardiovascular risk in routine chest CT scans without contrast, according to new research published in Nature Communications.[1] In fact, the authors noted, the AI approach may be more effective at identifying issues than relying on guidance from radiologists. Representative non-contrast CT slices for two patients (left), with super-imposed segmentations (right). One artificial intelligence (AI) model was used to segment a cardiac mask.

Representative non-contrast CT slices for two patients (left), with super-imposed segmentations (right). One artificial intelligence (AI) model was used to segment a cardiac mask (magenta line) and coronary artery calcium (red). A second AI model segmented left ventricular myocardium (purple), left atrial (green), left ventricle (light red), right ventricle (blue) and right atrial (yellow) volumes. Images/caption courtesy of Slomka et al. and Nature Communications.

Two advanced algorithms—one for CAC scores and another for segmenting cardiac chamber volumes—outperformed radiologists when assessing low-dose chest CT scans.