Umair Akhtar Hasan Khan, Carolin Stu ̈renberg, Oguzhan Gencoglu, Kevin Sandeman, Timo Heikkinen, Antti Rannikko, and Tuomas Mirtti

Top Data Science Ltd., Helsinki, Finland
University of Helsinki, Faculty of Medicine, Department of Pathology and Research

Program in Systemic Oncology, Helsinki, Finland
Department of Laboratory Medicine, Department of Pathology, Sk ̊ane University

Hospital, Malmo ̈, Sweden
4 Helsinki University Hospital, Department of Urology and Research Program in Systemic Oncology, Faculty of Medicine, University of Helsinki, Helsinki, Finland


Abstract

Deep neural networks have introduced significant advancements in the field of machine learning-based analysis of digital pathology images including prostate tissue images. With the help of transfer learning, classification and segmentation performance of neural network models have been further increased. However, due to the absence of large, extensively annotated, publicly available prostate histopathology datasets, several previous studies employ datasets from well-studied computer vision tasks such as ImageNet dataset. In this work, we propose a transfer learning scheme from breast histopathology images to improve prostate cancer detection performance. We validate our approach on annotated prostate whole slide images by using a publicly available breast histopathology dataset as pre-training. We show that the proposed crosscancer approach outperforms transfer learning from ImageNet dataset.

Our Publication