Compass: Prostate Cancer Detection Needs Multi-View Context

2026-07-07

AI Summary

This work addresses the limitation of existing AI approaches that detect prostate cancer from single-frame micro-ultrasound images while neglecting the multi-view 3D contextual information routinely used in clinical practice. The study models micro-ultrasound examinations as 2D image sequences and introduces, for the first time, a probe rotation angle–conditioned Transformer architecture. By incorporating an angle-conditioned attention mechanism, the model fuses the entire examination video with biopsy-time frames to explicitly capture multi-view spatiotemporal context, thereby emulating expert interpretation workflows. Employing dual decoders at both frame and exam levels, the model is trained on multicenter micro-ultrasound video data and significantly outperforms current AI baselines and clinical expert assessments, demonstrating the critical role of multi-view contextual information in enhancing prostate cancer detection performance.

Abstract

Artificial intelligence (AI) analysis of micro-ultrasound ($μ$US) has shown promise for prostate cancer (PCa) detection. However, most existing AI methods focus on the analysis of single $μ$US images in isolation. By contrast, expert $μ$US readers typically assess a full recorded video study, which provides three-dimensional context, to improve PCa detection compared to single-frame analysis. Inspired by this clinical workflow, we propose Compass, a novel AI methodology which models a $μ$US study as a stream of 2D images. Compass jointly integrates rotational sweep videos of the prostate with $μ$US frames acquired at the moment of biopsy, and performs evidence aggregation across the study using a transformer conditioned on the probe's rotational angle. Finally, a decoder head predicts frame-level and study-level risk scores for the patient. The model is trained and evaluated using a multi-center clinical trial dataset of $μ$US studies, including continuous rotational scans of the prostate and videos captured during biopsy acquisition. We compare the proposed method to baseline AI methods from the literature and to risk scores provided by clinical experts. Our framework shows strong performance, highlighting the value of multi-view context for $μ$US PCa detection, and providing a potentially powerful tool to complement human expertise in $μ$US-based PCa diagnosis. Our code is available at: https://github.com/mharmanani/Compass.

Problem

• prostate cancer detection
• micro-ultrasound
• multi-view context
• AI analysis
• clinical workflow

Innovation

• multi-view context
• micro-ultrasound
• transformer-based aggregation
• prostate cancer detection
• rotational sweep video