Alison Cheeseman | Applied Math, University of Waterloo
Content-based Image Retrieval (CBIR) for Digital Histopathology
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.
In this seminar I will discuss current research in the field of image analysis for histopathology images, highlighting some specific challenges which are relevant to this field. I will also discuss some of my current work on a frequency-based image descriptor which captures the local frequency information of the image in a compact representation. I will present some preliminary results on the performance of this descriptor.