Development of AI-assisted tools for enhanced clinical lymphoma PET/CT imaging

There are over 225,000 new cancer cases in Canada every year. Positron emission tomography/computed tomography (PET/CT) is the primary imaging modality for a range of cancer types. Various studies have established that determining size/volume, shape, and texture features of tumors from PET/CT images can help identify patients at high-risk of cancer relapse, or for whom standard treatments might fail. Nevertheless, the process of image-reading in clinics remains largely qualitative, since manual tumor delineation by radiologists can significantly reduce patient throughput and increase scan wait times. We aim to develop artificial intelligence based tools to assist radiologists in the detection/delineation of tumors in PET/CT images. In collaboration with Microsoft, we will help deploy such tools in the cloud, making them available to practicing physicians and researchers at BC Cancer. The expected benefits of this project include faster diagnosis, improved treatment outcomes, and reduced cancer-related healthcare costs in Canada.

Faculty Supervisor:

Arman Rahmim

Student:

Partner:

Microsoft Canada Development Centre

Discipline:

Life Sciences

Sector:

Artificial Intelligence; Health and Related Sciences & Technology; Technology

University:

The University of British Columbia

Program: