Structure boundary-preserving U-Net for prostate ultrasound image segmentation

• Published in: Frontiers in oncology Vol. 12; p. 900340
• Main Authors: Bi, Hui, Sun, Jiawei, Jiang, Yibo, Ni, Xinye, Shu, Huazhong
• Format: Journal Article
• Language: English
• Published: Frontiers Media 28.07.2022; Frontiers Media S.A
• Subjects: ASM-based key points selection; Bioengineering; deep learning; Life Sciences; Oncology; prostate ultrasound image segmentation; shape prior; U-Net architecture; deep learning; prostate ultrasound image segmentation; ASM-based key points selection; U-Net architecture; shape prior
• ISSN: 2234-943X; 2234-943X
• DOI: 10.3389/fonc.2022.900340

Prostate cancer diagnosis is performed under ultrasound-guided puncture for pathological cell extraction. However, determining accurate prostate location remains a challenge from two aspects: (1) prostate boundary in ultrasound images is always ambiguous; (2) the delineation of radiologists always occupies multiple pixels, leading to many disturbing points around the actual contour. We proposed a boundary structure-preserving U-Net (BSP U-Net) in this paper to achieve precise prostate contour. BSP U-Net incorporates prostate shape prior to traditional U-Net. The prior shape is built by the key point selection module, which is an active shape model-based method. Then, the module plugs into the traditional U-Net structure network to achieve prostate segmentation. The experiments were conducted on two datasets: PH2 + ISBI 2016 challenge and our private prostate ultrasound dataset. The results on PH2 + ISBI 2016 challenge achieved a Dice similarity coefficient (DSC) of 95.94% and a Jaccard coefficient (JC) of 88.58%. The results of prostate contour based on our method achieved a higher pixel accuracy of 97.05%, a mean intersection over union of 93.65%, a DSC of 92.54%, and a JC of 93.16%. The experimental results show that the proposed BSP U-Net has good performance on PH2 + ISBI 2016 challenge and prostate ultrasound image segmentation and outperforms other state-of-the-art methods.