Automatic prostate and peri-prostatic fat segmentation based on pyramid mechanism fusion network for T2-weighted MRI. (August 2022)

• Record Type: Journal Article
• Authors: Li, Yuchun; Wu, Yuanyuan; Huang, Mengxing; Zhang, Yu; Bai, Zhiming
• Is Part Of: Computer methods and programs in biomedicine. Volume 223(2022)
• Publication Date: 2022-08
• Subjects: Prostate segmentation -- Peri-prostatic fat -- Pyramid mechanism -- Dilated convolution -- T2-weighted imaging; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2022.106918
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: Automatic and accurate segmentation of prostate and peri-prostatic fat in male pelvic MRI images is essential for the diagnosis, prediction, treatment and prognosis of prostate diseases (automatic peri-prostatic fat segmentation is proposed for the first time). A convolutional neural network model based on pyramid mechanism fusion is proposed to segment prostate and peri-prostatic fat on T2 weighted. Pyramid mechanism module (PMM) is proposed and embedded in the basic network before each down sampling to avoid information loss during down sampling and up sampling. Pyramid fusion module (PFM) is applied in the transition section from feature encoder to feature decoder to integrate information of different scales and extract context features accurately. We evaluated the algorithm on T2 weighted images of prostate obtained from local hospitals, and verified the novelty and effectiveness of the proposed method. Abstract: Background and Objective: Automatic and accurate segmentation of prostate and peri-prostatic fat in male pelvic MRI images is a critical step in the diagnosis and prognosis of prostate cancer. The boundary of prostate tissue is not clear, which makes the task of automatic segmentation very challenging. The main issues, especially for the peri-prostatic fat, which is being offered for the first time, are hazy boundaries and a large form variation. Methods: We propose a pyramid mechanism fusion network (PMF-Net) to learn global features and more comprehensive context information. In the proposed PMF-Net, we devised two pyramid techniques in particular. A pyramid mechanism module made of dilated convolutions of varying rates is inserted before each down sample of the fundamental network architecture encoder. The module is intended to address the issue of information loss during the feature coding process, particularly in the case of segmentation object boundary information. In the transition stage from encoder to decoder, pyramid fusion module is designed to extract global features. The features of the decoder not only integrate the features of the previous stage after up sampling and the output features of pyramid mechanism, but also include the features of skipping connection transmission under the same scale of the encoder. Results: The segmentation results of prostate and peri-prostatic fat on numerous diverse male pelvic MRI datasets show that our proposed PMF-Net has higher performance than existing methods. The average surface distance (ASD) and Dice similarity coefficient (DSC) of prostate segmentation results reached 10.06 and 90.21%, respectively. The ASD and DSC of the peri-prostatic fat segmentation results reached 50.96 and 82.41%. Conclusions: The results of our segmentation are substantially connected and consistent with those of expert manual segmentation. Furthermore, peri-prostatic fat segmentation is a new issue, and good automatic segmentation has substantial therapeutic implications.