End-to-end prostate cancer detection in bpMRI via 3D CNNs: Effects of attention mechanisms, clinical priori and decoupled false positive reduction

TLDR

The study develops a multi‑stage 3D CNN‑based CAD system to automatically localize clinically significant prostate cancer in bi‑parametric MRI, aiming to distinguish malignant lesions from indolent cancer and benign pathology and to validate its performance on an independent cohort. The CAD system employs deep attention mechanisms across multiple resolutions, a decoupled residual classifier for false‑positive reduction, and a probabilistic anatomical prior to encode spatial prevalence and zonal distinctions, trained on 1,950 bpMRI scans with radiology‑estimated annotations. On 486 institutional scans, the system achieved 83.69 % sensitivity at 0.50 FP/patient and 93.19 % at 1.46 FP/patient with an AUROC of 0.882, outperforming four state‑of‑the‑art baselines, and on 296 external scans it showed moderate agreement with expert radiologists (76.69 %; κ = 0.51) and pathologists (81.08 %; κ = 0.56), indicating strong generalization.

Abstract

We present a multi-stage 3D computer-aided detection and diagnosis (CAD) model2 for automated localization of clinically significant prostate cancer (csPCa) in bi-parametric MR imaging (bpMRI). Deep attention mechanisms drive its detection network, targeting salient structures and highly discriminative feature dimensions across multiple resolutions. Its goal is to accurately identify csPCa lesions from indolent cancer and the wide range of benign pathology that can afflict the prostate gland. Simultaneously, a decoupled residual classifier is used to achieve consistent false positive reduction, without sacrificing high sensitivity or computational efficiency. In order to guide model generalization with domain-specific clinical knowledge, a probabilistic anatomical prior is used to encode the spatial prevalence and zonal distinction of csPCa. Using a large dataset of 1950 prostate bpMRI paired with radiologically-estimated annotations, we hypothesize that such CNN-based models can be trained to detect biopsy-confirmed malignancies in an independent cohort. For 486 institutional testing scans, the 3D CAD system achieves 83.69±5.22% and 93.19±2.96% detection sensitivity at 0.50 and 1.46 false positive(s) per patient, respectively, with 0.882±0.030 AUROC in patient-based diagnosis -significantly outperforming four state-of-the-art baseline architectures (U-SEResNet, UNet++, nnU-Net, Attention U-Net) from recent literature. For 296 external biopsy-confirmed testing scans, the ensembled CAD system shares moderate agreement with a consensus of expert radiologists (76.69%; kappa = 0.51±0.04) and independent pathologists (81.08%; kappa = 0.56±0.06); demonstrating strong generalization to histologically-confirmed csPCa diagnosis.