RadHop-Net: A Lightweight Radiomics-to-Error Regression for False Positive Reduction In MRI Prostate Cancer Detection

TL;DR

RadHop-Net is a lightweight CNN designed to reduce false positives in MRI prostate cancer detection by predicting and correcting errors from initial radiomics-based candidate identification, improving detection precision.

Contribution

It introduces a novel radiomics-to-error regression framework with a new loss function, decoupling from traditional voxel-to-label methods for better FP reduction.

Findings

Increases average precision from 0.407 to 0.468

Maintains smaller model size than state-of-the-art

Effective FP reduction in prostate MRI detection

Abstract

Clinically significant prostate cancer (csPCa) is a leading cause of cancer death in men, yet it has a high survival rate if diagnosed early. Bi-parametric MRI (bpMRI) reading has become a prominent screening test for csPCa. However, this process has a high false positive (FP) rate, incurring higher diagnostic costs and patient discomfort. This paper introduces RadHop-Net, a novel and lightweight CNN for FP reduction. The pipeline consists of two stages: Stage 1 employs data driven radiomics to extract candidate ROIs. In contrast, Stage 2 expands the receptive field about each ROI using RadHop-Net to compensate for the predicted error from Stage 1. Moreover, a novel loss function for regression problems is introduced to balance the influence between FPs and true positives (TPs). RadHop-Net is trained in a radiomics-to-error manner, thus decoupling from the common voxel-to-label approach. The proposed Stage 2 improves the average precision (AP) in lesion detection from 0.407 to 0.468 in the publicly available pi-cai dataset, also maintaining a significantly smaller model size than the state-of-the-art.