Biostatistics seminar
This talk will be led by Dr. Stacey Culp and is titled "Risk Stratification of Pancreatic Cysts: Integrating Imaging and Clinical Guidelines."
About
Stacey Culp is an associate professor in the Department of Biomedical Informatics at Ohio State.
The Biostatistics seminar series invites researchers from across the nation to discuss methodological research and its implications for a variety of health issues.
Abstract
Up to 13% of all cross-sectional abdominal imaging studies in asymptomatic subjects will identify a pancreatic cyst lesion (PCL), with higher rates for older patients. This creates the diagnostic challenge of differentiating benign cysts from those with malignant potential. Current approaches to risk stratification are limited and often lead to unnecessary surgery or failure to identify high-risk PCLs. This talk describes collaborative work using endoscopic ultrasound–guided confocal laser endomicroscopy (EUS-nCLE) to improve risk stratification of PCLs, with a focus on intraductal papillary mucinous neoplasms (IPMNs). Results for detecting high-grade dysplasia using EUS-nCLE alone and in combination with international clinical guidelines are presented for Ohio State experts and then among an international panel of endosonographers, motivating the development of machine learning approaches to analyze EUS-nCLE videos. Challenges with structure detection and patient-level classification are described, along with an initial attempt to integrate MRI data. Finally, the application of these approaches within the ERASE study is briefly discussed.
Contact
Andy Ni