Using Artificial Intelligence to Detect Liver Cancer
Liver cancer is an important cause of mortality worldwide. Current screening guidelines recommend liver ultrasound in those at risk so to visually identify a mass. This approach has poor sensitivity (<50%) and is subjected to operator expertise. MSI PIs Jose Debes (associate professor, Medicine) and Ju Sun (assistant professor, Computer Science and Engineering) propose a novel approach of analyzing sound waves of Doppler ultrasound from easy-to-find liver vessels via artificial intelligence (AI) to detect the presence of liver cancer. Their approach of analyzing sound waves via AI to detect cancer is a first of a kind and has the potential to change our approach to cancer detection.
This project recently received a UMII Seed Grant. UMII Seed Grant funds are intended to promote, catalyze, accelerate and advance UMN-based informatics research in areas related to the MnDRIVE initiative, so that UMN faculty and staff are well prepared to compete for longer-term external funding opportunities. This Seed Grant falls under the Cancer Clinical Trials research areas of the MnDRIVE initiative.
Professor Sun uses MSI for projects involving machine/deep learning, computer vision, numerical optimization, and medical imaging. Professor Debes is using MSI resources for genetics investigations of the hepatitis C virus as it relates to liver cancer.