End-to-end Prostate Cancer Detection in bpMRI via 3D CNNs: Effect of Attention Mechanisms, Clinical Priori and Decoupled False Positive Reduction
Preprint
Abstract
We present a novel multi-stage 3D computer-aided detection and diagnosis (CAD) model for automated localization of clinically significant prostate cancer (csPCa) in bi-parametric MR imaging (bpMRI). Deep attention mechanisms drive its detection network, targeting multi-resolution, salient structures and highly discriminative feature dimensions, in order to accurately identify csPCa lesions from indolent cancer and the wide range of benign pathology that can afflict the prostate gland. In parallel, a decoupled residual classifier is used to achieve consistent false positive reduction, without sacrificing high sensitivity or computational efficiency. Furthermore, a probabilistic anatomical prior, which captures the spatial prevalence of csPCa as well as its zonal distinction, is computed and encoded into the CNN architecture to guide model generalization with domain-specific clinical knowledge. For 486 institutional testing scans, the 3D CAD system achieves $83.69\pm5.22\%$ and $93.19\pm2.96\%$ detection sensitivity at 0.50 and 1.46 false positive(s) per patient, respectively, along with $0.882$ 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 testing scans, the ensembled CAD system shares moderate agreement with a consensus of expert radiologists ($76.69\%$; $kappa=0.511$) and independent pathologists ($81.08\%$; $kappa=0.559$); demonstrating strong generalization to histologically-confirmed malignancies, despite using 1950 training-validation cases with radiologically-estimated annotations only.
Keywords
All Related Versions
This publication has 38 references indexed in Scilit:
- Deep Attentive Panoptic Model for Prostate Cancer Detection Using Biparametric MRI Scans2020
- Simulated clinical deployment of fully automatic deep learning for clinical prostate MRI assessmentEuropean Radiology, 2020
- Deep‐Learning‐Based Artificial Intelligence for PI‐RADS Classification to Assist Multiparametric Prostate MRI Interpretation: A Development StudyJournal of Magnetic Resonance Imaging, 2020
- Two-Stage Cascaded U-Net: 1st Place Solution to BraTS Challenge 2019 Segmentation Task2020
- NoduleNet: Decoupled False Positive Reduction for Pulmonary Nodule Detection and Segmentation2019
- Semi-automatic classification of prostate cancer on multi-parametric MR imaging using a multi-channel 3D convolutional neural networkEuropean Radiology, 2019
- Comparison of Multiparametric Magnetic Resonance Imaging and Targeted Biopsy With Systematic Biopsy Alone for the Diagnosis of Prostate CancerJAMA Network Open, 2019
- Intra‐ and interreader reproducibility of PI‐RADSv2: A multireader studyJournal of Magnetic Resonance Imaging, 2018
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Detection of prostate cancer with multiparametric MRI (mpMRI): effect of dedicated reader education on accuracy and confidence of index and anterior cancer diagnosisAbdominal Radiology, 2014