The Reproducibility of Deep Learning-Based Segmentation of the Prostate Gland and Zones on T2-Weighted MR Images

Abstract

Volume of interest segmentation is an essential step in computer-aided detection and diagnosis (CAD) systems. Deep learning (DL)-based methods provide good performance for prostate segmentation, but little is known about the reproducibility of these methods. In this work, an in-house collected dataset from 244 patients was used to investigate the intra-patient reproducibility of 14 shape features for DL-based segmentation methods of the whole prostate gland (WP), peripheral zone (PZ), and the remaining prostate zones (non-PZ) on T2-weighted (T2W) magnetic resonance (MR) images compared to manual segmentations. The DL-based segmentation was performed using three different convolutional neural networks (CNNs): V-Net, nnU-Net-2D, and nnU-Net-3D. The two-way random, single score intra-class correlation coefficient (ICC) was used to measure the inter-scan reproducibility of each feature for each CNN and the manual segmentation. We found that the reproducibility of the investigated methods is comparable to manual for all CNNs (14/14 features), except for V-Net in PZ (7/14 features). The ICC score for segmentation volume was found to be 0.888, 0.607, 0.819, and 0.903 in PZ; 0.988, 0.967, 0.986, and 0.983 in non-PZ; 0.982, 0.975, 0.973, and 0.984 in WP for manual, V-Net, nnU-Net-2D, and nnU-Net-3D, respectively. The results of this work show the feasibility of embedding DL-based segmentation in CAD systems, based on multiple T2W MR scans of the prostate, which is an important step towards the clinical implementation.