The use of automated prognostic imaging biomarkers in clinical practice may enhance (re-) staging and response assessment, as it could inform more personalized treatment selection and patient monitoring, which in turn could lead to improved patient outcomes. The purpose of this project is to develop automated, deep learning-based imaging biomarkers that predict outcomes of breast cancer patients with solid tumors based on various modalities of medical imaging. By enabling an artificial neural network to “learn” what visual features in thousands of imaging studies are associated with respective patients’ actual future outcomes, the resulting deep learning algorithm will be able to predict survival for a new patient’s imaging study.
This record is a historical disbursement from Canada's open grants database — it documents a past payment, not an active program accepting applications.
View disbursement record →