Cancer-Net PCa-MultiSeg: Multimodal Enhancement of Prostate Cancer Lesion Segmentation Using Synthetic Correlated Diffusion Imaging

TL;DR

This study demonstrates that synthetic correlated diffusion imaging (CDI$^s$) significantly improves prostate cancer lesion segmentation accuracy across multiple deep learning models without additional scan time, enabling practical clinical deployment.

Contribution

We introduce CDI$^s$ as a novel enhancement to standard diffusion imaging, improving segmentation performance across six architectures without extra acquisition time.

Findings

CDI$^s$ improves or maintains segmentation in 94% of configurations.

Up to 72.5% relative improvement in some architectures.

No degradation observed with CDI$^s$ + DWI enhancement pathway.

Abstract

Current deep learning approaches for prostate cancer lesion segmentation achieve limited performance, with Dice scores of 0.32 or lower in large patient cohorts. To address this limitation, we investigate synthetic correlated diffusion imaging (CDI$^s$) as an enhancement to standard diffusion-based protocols. We conduct a comprehensive evaluation across six state-of-the-art segmentation architectures using 200 patients with co-registered CDI$^s$, diffusion-weighted imaging (DWI) and apparent diffusion coefficient (ADC) sequences. We demonstrate that CDI$^s$ integration reliably enhances or preserves segmentation performance in 94% of evaluated configurations, with individual architectures achieving up to 72.5% statistically significant relative improvement over baseline modalities. CDI$^s$ + DWI emerges as the safest enhancement pathway, achieving significant improvements in half of evaluated architectures with zero instances of degradation. Since CDI$^s$ derives from existing DWI acquisitions without requiring additional scan time or architectural modifications, it enables immediate deployment in clinical workflows. Our results establish validated integration pathways for CDI$^s$ as a practical drop-in enhancement for PCa lesion segmentation tasks across diverse deep learning architectures.