Artificial Intelligence for Prostate Cancer Diagnosis and Prognostication
Title: Artificial Intelligence for Prostate Cancer Diagnosis and Prognostication
SNIC Project: Berzelius-2022-110
Project Type: LiU Berzelius
Principal Investigator: Martin Eklund <martin.eklund@ki.se>
Affiliation: Karolinska Institutet
Duration: 2022-06-01 – 2022-12-01
Classification: 30203
Homepage: https://staff.ki.se/people/martin-eklund
Keywords:

Abstract

Digital pathology enables using AI for improved cancer diagnostics and ultimately better treatment decisions. We intend to develop a prognostic AI system for prostate cancer pathology by integrating: 1) Large-scale datasets of digitized prostate biopsies from a network of health care providers, 2) Cohorts with follow-up for clinical outcomes; and 3) Genomic profiling of the samples. This will allow extending prognostication beyond human capacity by directly predicting disease progress from images and by integrating molecular data with tissue morphology. Utilizing diverse international data will allow training robust models and evaluating them in view of real-world sources of variation. We will utilize the capacity of Berzelius AI/ML cluster by posing the project as an automated machine learning problem to design the system in a data-driven manner. This novel way of solving problems in computational pathology complements the major clinical significance of the project with the potential for technological advances.