Towards Fully Automated Abdominal CT Image Interpretation

This talk will describe our approach to full automation of abdominal CT image interpretation. Topics will include fully automated detection and segmentation of the major abdominal organs and their lesions, the spine and spine lesions and lymphadenopathy. We show how fully automated quantitation of bone mineral density and visceral fat can be obtained from CT scans without additional radiation exposure. We also present work on using Internet-based crowdsourcing for improved decision making.