Assessing Cancer Presence in Prostate MRI Using Multi-Encoder Cross-Attention Networks

TL;DR

This paper introduces a deep learning method to detect prostate cancer in MRI scans, achieving strong performance on a large dataset.

Contribution

The paper introduces a novel multi-encoder cross-attention architecture for prostate cancer presence detection in MRI.

Findings

The proposed model achieved an AUC of 0.91 on test sets of 975 and 435 patients.

The method effectively fuses bi-parametric MRI modalities to enhance model robustness.

The study uses the largest PCa MR image dataset to date for training and evaluation.

Abstract

Prostate cancer (PCa) is currently the second most prevalent cancer among men. Accurate diagnosis of PCa can provide effective treatment for patients and reduce mortality. Previous works have merely focused on either lesion detection or lesion classification of PCa from magnetic resonance imaging (MRI). In this work we focus on a critical, yet underexplored task of the PCa clinical workflow: distinguishing cases with cancer presence (pathologically confirmed PCa patients) from conditions with no suspicious PCa findings (no cancer presence). To this end, we conduct large-scale experiments for this task for the first time by adopting and processing the multi-centric ProstateNET Imaging Archive which contains more than 6 million image representations of PCa from more than 11,000 PCa cases, representing the largest collection of PCa MR images. Bi-parametric MR (bpMRI) images of 4504 patients alongside their clinical variables are used for training, while the architectures are evaluated on two hold-out test sets of 975 retrospective and 435 prospective patients. Our proposed multi-encoder-cross-attention-fusion architecture achieved a promising area under the receiver operating characteristic curve (AUC) of 0.91. This demonstrates our method’s capability of fusing complex bi-parametric imaging modalities and enhancing model robustness, paving the way towards the clinical adoption of deep learning models for accurately determining the presence of PCa across patient populations.

Figures