Phd Comprehensive Exam | Alison Cheeseman, Content-based Image Retrieval (CBIR) for Digital Histopathology

Friday, August 9, 2019 10:00 am - 10:00 am EDT (GMT -04:00)

MC 6460

 

Candidate

Alison Cheeseman | Applied Math, University of Waterloo

Title

Content-based Image Retrieval (CBIR) for Digital Histopathology

 Abstract

In recent years, histopathology images have been increasingly used as a diagnostic tool in the medical field. The process of accurately diagnosing a biopsy sample requires significant expertise in the field, and as such can be time-consuming and is prone to uncertainty and error. With the advent of digital pathology, using image recognition systems to highlight problem areas or locate similar images can aid pathologists in making quick and accurate diagnoses.

My research will focus on developing content-based image retrieval (CBIR) methods for digital histopathology, which means finding images which share the same visual characteristics as a given query image. CBIR is particularly effective for pathology images because it doesn’t necessarily rely on extensive amounts of annotated data. The identification and analysis of similar images can assist pathologists in quickly and accurately obtaining a diagnosis by providing a baseline for comparison. In particular, if the images in the database have been previously diagnosed, pathologists can refer to the diagnostic information of the retrieved images for more information.