Evaluation of Deep Neural Networks for Semantic Segmentation of Prostate in T2W MRI

Abstract

In this paper, we present an evaluation of four encoder–decoder CNNs in the segmentation of the prostate gland in T2W magnetic resonance imaging (MRI) image. The four selected CNNs are FCN, SegNet, U-Net, and DeepLabV3+, which was originally proposed for the segmentation of road scene, biomedical, and natural images. Segmentation of prostate in T2W MRI images is an important step in the automatic diagnosis of prostate cancer to enable better lesion detection and staging of prostate cancer. Therefore, many research efforts have been conducted to improve the segmentation of the prostate gland in MRI images. The main challenges of prostate gland segmentation are blurry prostate boundary and variability in prostate anatomical structure. In this work, we investigated the performance of encoder–decoder CNNs for segmentation of prostate gland in T2W MRI. Image pre-processing techniques including image resizing, center-cropping and intensity normalization are applied to address the issues of inter-patient and inter-scanner variability as well as the issue of dominating background pixels over prostate pixels. In addition, to enrich the network with more data, to increase data variation, and to improve its accuracy, patch extraction and data augmentation are applied prior to training the networks. Furthermore, class weight balancing is used to avoid having biased networks since the number of background pixels is much higher than the prostate pixels. The class imbalance problem is solved by utilizing weighted cross-entropy loss function during the training of the CNN model. The performance of the CNNs is evaluated in terms of the Dice similarity coefficient (DSC) and our experimental results show that patch-wise DeepLabV3+ gives the best performance with DSC equal to 92.8 % . This value is the highest DSC score compared to the FCN, SegNet, and U-Net that also competed the recently published state-of-the-art method of prostate segmentation.

Autosegmentation of Prostate Zones and Cancer Regions from Biparametric Magnetic Resonance Images by Using Deep-Learning-Based Neural Networks

“…They used a DenseNet-like U-Net for training and achieved a DSC of 89.5% ± 2% in the central gland region and 78.1% ± 2.5% in the PZ. Khan et al [16] used a model resembling the encoder-decoder architecture and only T2W images of two prostate MRI datasets for segmentation and training. They achieved a DSC of 90.8 ± 1.2% in the central gland region and 76.0 ± 3.9% in the PZ by using SegNet [16].…”

“…They allow for the automatic extraction of features and learning from large amounts of data for quantification. The DCNN architecture has been used for prostate segmentation or PCa detection [11,[14][15][16]. In most of these studies, conventional DCNNs were used for semantic image segmentation.…”

Evaluation of Multimodal Algorithms for the Segmentation of Multiparametric MRI Prostate Images

“…Khan et al [ 25 ] applied class-weighting approach to reduce class imbalance, thus yielding slightly higher DSC for classical UNet and SegNet, though they trained their networks with different number of subjects ( Table 5 ). Dense-2 UNet [ 26 ] produced similar performance as the cascaded 2D UNet [ 18 ].…”

“…Prostate cancer (PCa) is the most frequently diagnosed cancer with the second highest mortality in men worldwide in 2018 [ 1 ]. Commonly employed PCa screening methods such as the prostate-specific antigen test are subjective and inaccurate, leading to unnecessary invasive prostate biopsy or misdiagnosis of patients with aggressive PCa [ 2 , 25 ]. Multiparametric magnetic resonance imaging (mpMRI) is noninvasive and together with the Prostate Imaging-Reporting and Data System (PI-RADS) assessment guidelines (PI-RADS v2) allows for better diagnosis, localization, risk stratification, and staging of PCa [ 3 , 4 ].…”

Magnetic Resonance Imaging Based Radiomic Models of Prostate Cancer: A Narrative Review

“…Deep learning models (e.g., CNNs) form a specific approach that is directly applied on images to extract, select features, and predict the class (classification) or a value (regression) in an automated fashion. Examples in the PCa literature have observed that this deep learning approach detects malignant lesions [ 125 ], predicts the GS [ 126 ], and segments the ROI [ 127 , 128 ].…”