Deep Learning-Based Methods for Prostate Segmentation in Magnetic Resonance Imaging

Abstract

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.

Precise Identification of Prostate Cancer from DWI Using Transfer Learning

“…However, any segmentation approach can be integrated with the proposed system, as long as, it provides a continuous segmented object. For example, Comelli et al [ 46 ], presented a fast deep learning network, namely efficient neural network (ENet), for prostate segmentation from T2-weighted MRI. ENet is initially used for image segmentation tasks in self-driving cars where hardware availability is limited and the accuracy is critical for user safety.…”

“…ENet is initially used for image segmentation tasks in self-driving cars where hardware availability is limited and the accuracy is critical for user safety. In this study [ 46 ], ENet is trained using a dataset of 85 subjects and results in a dice similarity coefficient of .…”

A Multi-Scale and Multi-Level Fusion Approach for Deep Learning-Based Liver Lesion Diagnosis in Magnetic Resonance Images with Visual Explanation

“…Generally, for the case where the network contains large amount of parameters and have little training data, the transfer learning strategy can be used to support the training process. For the lightweight networks such as Enet [ 45 ], the network can be trained from the initial state, where the transfer learning is not adopted, like in the studies of Albert Comelli et al [ 46 ] and Renato Cuocolo et al [ 47 ]. In the experiments in our paper, we adopted the widely used large-scale networks and adopted the transfer learning strategy.…”

Radiomics and Prostate MRI: Current Role and Future Applications

“…In the biomedical imaging field, target delineation is routinely used as the first step in any automated disease diagnosis system to obtain quantitative parameters from biomedical images. Deep learning algorithms have been applied in automatic segmentation of the prostate gland [ 46 , 47 ] with potential benefit for patient management personalization. As a future perspective, the integration of a deep learning network in radiological PACS would lead to a rapid and precise procedure of segmentation of the prostate gland, thus reducing interuser variability.…”