ABSTRACT

Pathology is the cornerstone of modern medicine and, in particular, cancer care. The pathologist’s diagnosis on glass slides is the basis for clinical and pharmaceutical research and, more importantly, for the decision on how to treat the patient. In recent years, thanks to advances in scanner technology and computer vision, computational pathology has emerged to facilitate computer-assisted diagnostics and to enable a digital workflow for pathologists. These diagnostic decision support tools can be developed to empower pathologists’ efficiency and accuracy to ultimately provide better patient care. Unfortunately, there are many challenges to overcome before these technologies are ready to be deployed in the clinic. In our work, we push the field closer to clinical application. We developed a new strategy for training predictive models that do not rely on annotation and can learn from very large datasets. Importantly, we defined clinical-grade for diagnostic tools in computational pathology and proposed a strategy to integrate a diagnostic decision support syste!m in the clinical work flow.

SPEAKER

Gabriele Campanella is a PhD student at Weill Cornell working at Memorial Sloan Kettering Cancer Center in the Fuchs lab. His research focuses on computational pathology and building decision support systems for clinical application.
Let me know if you have any questions.

Add event on Google Calendar