The following abstract is drawn from a recently published paper in Journal of Pathology Informatics | ScienceDirect.com by Elsevier. We invite you to read the full paper and join the conversation, become a member of the Pathology News community to share your thoughts, ask questions, and engage with others around this work.

Authors: Joona Pohjonen^a, Oussama Batouche^a,b, Janne Kantola^c,d,e, Antti Rannikko^e,f, Kevin Sandeman^g, Andrew Erickson^a,e, Esa Pitkänen^c,d,e, Tuomas Mirtti^e,h,i

Abstract

Foundation models are trained on massive amounts of data to capture complex patterns in images. Subsequently, a wide range of downstream tasks can be adopted with minimal computational resources. We have developed HistoEncoder, a foundation model for prostate cancer digital pathology by pre-training on 48 million prostate tissue tile images. HistoEncoder allows automated extraction of histological features highly predictive of Gleason patterns achieving comparable performance with substantially larger pan-cancer foundation models while being much more efficient. By fine-tuning the model with a small amount of data and computational resources, we describe two clinical use cases for HistoEncoder. First, HistoEncoder can be used to automatically annotate large-scale datasets with high accuracy. Second, we show that HistoEncoder-derived histology clusters contain prognostic information of a similar magnitude to Gleason grading in internal cross-validation. Lightweight foundation models such as HistoEncoder allow organizations to build effective clinical software tools without the need for extensive datasets and heavy computing.

Read the full article: HistoEncoder: A digital pathology foundation model for prostate cancer – ScienceDirect

^aResearch Program in Systemic Oncology (ONCOSYS), Faculty of Medicine, University of Helsinki, Helsinki, Finland

^bDoctoral Program in Computer Science, Faculty of Science, University of Helsinki, Helsinki, Finland

^cInstitute for Molecular Medicine Finland (FIMM), HiLIFE, University of Helsinki, Helsinki, Finland

^dResearch Program in Applied Tumour Genomics, Faculty of Medicine, University of Helsinki, Helsinki, Finland

^eiCAN Digital Precision Cancer Medicine Flagship, Helsinki, Finland

^fDepartment of Urology, Helsinki University Hospital, Helsinki, Finland

^gDepartment of Pathology, Division of Laboratory Medicine, Skåne University Hospital, Malmö, Sweden

^hDepartment of Pathology, Helsinki University Hospital, Helsinki, Finland

ⁱFinnish Cancer Institute, Helsinki, Finland