Artificial intelligence for streamlining prostate cancer diagnostics
The objective of Peter's thesis is to develop and improve technologies for prostate cancer diagnostics and to acquire knowledge related to these technologies that directly translate to clinical utility.
With around 1.2 million cases per year, prostate cancer is the second most common cancer among men world-wide. It is usually a slow growing disease that affects older men. It is also a cancer that is heterogenous,often multifocal,and rarely shows symptoms as long as it is localized. All these things make the disease difﬁcult to detect, diagnose and study.
Due to the common use of the imprecise PSA screening test and the complexity and subjective nature of the diagnosis of prostate cancer, this disease is known for both high overtreatment and undertreatment leading to unnecessary anxiety, unpleasant and risky operational procedures, and, in the worst case, death.
By making use of modern computation, high quality data and advanced prediction models, this thesis aims to improve the screening of patients, develop efﬁcient diagnostic algorithms and improve prognostication.
In conclusion, the technologies developed in this thesis shows promise in streamlining the clinical workload around prostate cancer detection and diagnostics.
On May 15, Peter will defend hist hesis “Artificial intelligence for streamlining prostate cancer diagnostics". Peter's opponent is Associate Professor Darren Treanor from Leeds Institute of Molecular Medicine at Leeds University. His supervisors are Martin Eklund, Tobias Nordström, Mattias Rantalainen and Mark Clements
Location: Lecture hall Atrium, Nobels väg 12B, Karolinska Institutet, Solna
Join by Zoom: https://ki-se.zoom.us/j/67782008650
Read the thesis in KI's open archive.