Cancer-Net PCa-Seg: Benchmarking Deep Learning Models for Prostate Cancer Segmentation Using Synthetic Correlated Diffusion Imaging

TL;DR

This study benchmarks deep learning models for prostate cancer gland segmentation using a novel MRI modality, synthetic correlated diffusion imaging, demonstrating promising results for improved diagnosis and clinical support.

Contribution

It introduces the use of synthetic correlated diffusion imaging for prostate segmentation and compares multiple deep learning models, highlighting their performance and efficiency.

Findings

SegResNet achieved the highest DSC of 76.68%.

Attention U-Net offered a good balance of accuracy and efficiency.

Deep learning models show potential in enhancing prostate cancer diagnosis.

Abstract

Prostate cancer (PCa) is the most prevalent cancer among men in the United States, accounting for nearly 300,000 cases, 29\% of all diagnoses and 35,000 total deaths in 2024. Traditional screening methods such as prostate-specific antigen (PSA) testing and magnetic resonance imaging (MRI) have been pivotal in diagnosis, but have faced limitations in specificity and generalizability. In this paper, we explore the potential of enhancing PCa gland segmentation using a novel MRI modality called synthetic correlated diffusion imaging (CDI$^s$). We employ several state-of-the-art deep learning models, including U-Net, SegResNet, Swin UNETR, Attention U-Net, and LightM-UNet, to segment prostate glands from a 200 CDI$^s$ patient cohort. We find that SegResNet achieved superior segmentation performance with a Dice-Sorensen coefficient (DSC) of $76.68 \pm 0.8$. Notably, the Attention U-Net, while slightly less accurate (DSC $74.82 \pm 2.0$), offered a favorable balance between accuracy and computational efficiency. Our findings demonstrate the potential of deep learning models in improving prostate gland segmentation using CDI$^s$ to enhance PCa management and clinical support.