期刊
APPLIED SCIENCES-BASEL
卷 11, 期 2, 页码 -出版社
MDPI
DOI: 10.3390/app11020782
关键词
deep learning; segmentation; prostate; MRI; ENet; UNet; ERFNet; radiomics
类别
资金
- USA Army Research Office (ARO) [W911NF-18-1-0281]
- National Institute of Health (NIH) [R01-HL-143350]
This study demonstrates the use of high-speed deep learning networks for accurate prostate delineation, paving the way for novel imaging parameter analysis in prostatic oncologic diseases. ENet and UNet were found to be more accurate in prostate delineation compared to ERFNet, with ENet being faster.
Featured Application The study demonstrates that high-speed deep learning networks could perform accurate prostate delineation facilitating the adoption of novel imaging parameters, through radiomics analyses, for prostatic oncologic diseases. Magnetic Resonance Imaging-based prostate segmentation is an essential task for adaptive radiotherapy and for radiomics studies whose purpose is to identify associations between imaging features and patient outcomes. Because manual delineation is a time-consuming task, we present three deep-learning (DL) approaches, namely UNet, efficient neural network (ENet), and efficient residual factorized convNet (ERFNet), whose aim is to tackle the fully-automated, real-time, and 3D delineation process of the prostate gland on T2-weighted MRI. While UNet is used in many biomedical image delineation applications, ENet and ERFNet are mainly applied in self-driving cars to compensate for limited hardware availability while still achieving accurate segmentation. We apply these models to a limited set of 85 manual prostate segmentations using the k-fold validation strategy and the Tversky loss function and we compare their results. We find that ENet and UNet are more accurate than ERFNet, with ENet much faster than UNet. Specifically, ENet obtains a dice similarity coefficient of 90.89% and a segmentation time of about 6 s using central processing unit (CPU) hardware to simulate real clinical conditions where graphics processing unit (GPU) is not always available. In conclusion, ENet could be efficiently applied for prostate delineation even in small image training datasets with potential benefit for patient management personalization.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据