Abstract
OBJECTIVES: To automatically segment prostate central gland (CG) and peripheral zone (PZ) on T2-weighted imaging using deep learning and assess the model's clinical utility by comparing it with a radiologist annotation and analyzing relevant influencing factors, especially the prostate zonal volume. METHODS: A 3D U-Net-based model was trained with 223 patients from one institution and tested using one internal testing group (n = 93) and two external testing datasets, including one public dataset (ETD(pub), n = 141) and one private dataset from two centers (ETD(pri), n = 59). The Dice similarity coefficients (DSCs), 95th Hausdorff distance (95HD), and average boundary distance (ABD) were calculated to evaluate the model's performance and further compared with a junior radiologist's performance in ETD(pub). To investigate factors influencing the model performance, patients' clinical characteristics, prostate morphology, and image parameters in ETD(pri) were collected and analyzed using beta regression. RESULTS: The DSCs in the internal testing group, ETD(pub), and ETD(pri) were 0.909, 0.889, and 0.869 for CG, and 0.844, 0.755, and 0.764 for PZ, respectively. The mean 95HD and ABD were less than 7.0 and 1.3 for both zones. The U-Net model outperformed the junior radiologist, having a higher DSC (0.769 vs. 0.706) and higher intraclass correlation coefficient for volume estimation in PZ (0.836 vs. 0.668). CG volume and Magnetic Resonance (MR) vendor were significant influencing factors for CG and PZ segmentation. CONCLUSIONS: The 3D U-Net model showed good performance for CG and PZ auto-segmentation in all the testing groups and outperformed the junior radiologist for PZ segmentation. The model performance was susceptible to prostate morphology and MR scanner parameters.