Development and clinical utility analysis of a prostate zonal segmentation model on T2-weighted imaging: a multicenter study.

Lili XuGumuyang ZhangDaming ZhangJiahui ZhangXiaoxiao ZhangXin BaiLi ChenQianyu PengRu JinLi MaoXiuli LiZhengyu JinHao Sun

Published in: Insights into imaging (2023)

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.

Keyphrases

prostate cancer
deep learning
convolutional neural network
magnetic resonance
computed tomography
machine learning
mass spectrometry