UMamba-ProSSL: Self-Supervised Large-Scale Pretraining with Multi-Task UMamba Advances Prostate Cancer Detection in Biparametric MRI

Syed Farhan Abbas, Michael S. Larsen, Arild Strømsvåg, Tone F. Bathen, Frank Lindseth, Gabriel Kiss, Mattijs Elschot

Keywords: Self-Supervised Learning, Prostate Cancer, UMamba, Masked Autoencoders, Magnetic Resonance Imaging

TL;DR: Self-supervised learning advances prostate cancer detection.

Abstract:

Accurate prostate cancer (PCa) diagnosis is crucial, as it remains one of the leading cause of mortality among men. Although prostate magnetic resonance imaging (MRI) has improved the diagnostic workflow, radiologists still face challenges due to inter-observer
variability and limited specificity, leading to both over- and under-diagnosis. Deep learning methods have the potential to support radiologists, but their performance typically depends on large, high-quality labeled datasets that are often scarce and expensive to
curate. In contrast, large volumes of unlabeled prostate MRI scans are routinely generated in clinical practice, making self-supervised learning (SSL) a compelling approach to exploit this abundant, untapped resource. However, SSL performance depends strongly
on backbone architectures and effective pretext tasks. Moreover, the lack of large-scale standardized benchmarking further limits progress. In this study, we employ a state-ofthe-art UMamba for prostate cancer detection and investigate several SSL strategies using
a large in-house unlabeled prostate MRI dataset (N=2,431). Among the different pretraining methods, UMamba pretrained with masked autoencoders (MAE) achieved the best downstream performance, with an aggregated mean score of 0.780 (AUROC: 0.905, AP: 0.655) on the large-scale PI-CAI hidden testing set (N=1,000). This performance ranked first on the PI-CAI benchmark leaderboard at the time of evaluation, highlighting the strong potential of SSL, particularly MAE combined with UMamba for improving PCa detection accuracy and potentially reducing unnecessary biopsies. The code is available at https://github.com/farhancv09/UMamba-ProSSL.

Primary Subject Area: Segmentation

Secondary Subject Area: Unsupervised Learning and Representation Learning

Registration Requirement: Yes

Reproducibility: https://github.com/farhancv09/UMamba-ProSSL

Visa & Travel: Yes

Read CFP & Author Instructions: Yes

Originality Policy: Yes

Single-blind & Not Under Review Elsewhere: Yes

LLM Policy: Yes

Submission Number: 35