Computer Aided Detection for CT Colonography

Clinical Center

Investigators

Linked publications, trials & patents

Abstract

We are improving CT colonography (virtual colonoscopy) by developing computer-assisted diagnosis methods. These methods attempt to identify and characterize colonic polyps automatically, thereby increasing physician accuracy and efficiency and helping patients by finding their polyps. We are developing methods to detect extracolonic findings on CT colonography using fully-automated software. Examples include automated body composition analysis and bone mineral densitometry. We have improved the accuracy of such methods compared to earlier versions. In FY 2023, we made advances in several areas. In patients undergoing colorectal cancer (CRC) screening, we were able to (1) use AI-based profiling of body composition metrics from routine abdominal CT scans to identify myosteatosis as a key predictor of mortality risk in asymptomatic adults, (2) automatically assess kidney stone burdens over longitudinal CT scans and (3) show that sex-specific thresholds for automated CT-based body compositions measures for muscle abdominal fat, and aortic calcium can be used to predict the risk of death and adverse cardiovascular events.