Structure Boundary-preserving U-Net for Prostate Ultrasound Image Segmentation

Overview

Journal Front Oncol

Specialty Oncology

Date 2022 Aug 15

PMID 35965563

Authors

Hui Bi

Jiawei Sun

Yibo Jiang

Xinye Ni

Huazhong Shu

Affiliations

Soon will be listed here.

Abstract

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: and our private prostate ultrasound dataset. The results on 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 and prostate ultrasound image segmentation and outperforms other state-of-the-art methods.

Citing Articles

PlaqueNet: deep learning enabled coronary artery plaque segmentation from coronary computed tomography angiography.

Wang L, Zhang X, Tian C, Chen S, Deng Y, Liao X Vis Comput Ind Biomed Art. 2024; 7(1):6.

PMID: 38514491 PMC: 11349722. DOI: 10.1186/s42492-024-00157-8.

References

Yan P, Xu S, Turkbey B, Kruecker J . Discrete deformable model guided by partial active shape model for TRUS image segmentation. IEEE Trans Biomed Eng. 2010; 57(5):1158-66. PMC: 8375567. DOI: 10.1109/TBME.2009.2037491. View

Gong L, Pathak S, Haynor D, Cho P, Kim Y . Parametric shape modeling using deformable superellipses for prostate segmentation. IEEE Trans Med Imaging. 2004; 23(3):340-9. DOI: 10.1109/TMI.2004.824237. View

Qin W, Wu J, Han F, Yuan Y, Zhao W, Ibragimov B . Superpixel-based and boundary-sensitive convolutional neural network for automated liver segmentation. Phys Med Biol. 2018; 63(9):095017. PMC: 5983385. DOI: 10.1088/1361-6560/aabd19. View

Murugesan B, Sarveswaran K, Shankaranarayana S, Ram K, Joseph J, Sivaprakasam M . Psi-Net: Shape and boundary aware joint multi-task deep network for medical image segmentation. Annu Int Conf IEEE Eng Med Biol Soc. 2020; 2019:7223-7226. DOI: 10.1109/EMBC.2019.8857339. View

Bi H, Jiang Y, Tang H, Yang G, Shu H, Dillenseger J . Fast and accurate segmentation method of active shape model with Rayleigh mixture model clustering for prostate ultrasound images. Comput Methods Programs Biomed. 2019; 184:105097. DOI: 10.1016/j.cmpb.2019.105097. View

Shelhamer E, Long J, Darrell T . Fully Convolutional Networks for Semantic Segmentation. IEEE Trans Pattern Anal Mach Intell. 2016; 39(4):640-651. DOI: 10.1109/TPAMI.2016.2572683. View

Mendonca T, Ferreira P, Marques J, Marcal A, Rozeira J . PH² - a dermoscopic image database for research and benchmarking. Annu Int Conf IEEE Eng Med Biol Soc. 2013; 2013:5437-40. DOI: 10.1109/EMBC.2013.6610779. View

Bi L, Kim J, Ahn E, Kumar A, Fulham M, Feng D . Dermoscopic Image Segmentation via Multistage Fully Convolutional Networks. IEEE Trans Biomed Eng. 2017; 64(9):2065-2074. DOI: 10.1109/TBME.2017.2712771. View

Mishra D, Chaudhury S, Sarkar M, Soin A . Ultrasound Image Segmentation: A Deeply Supervised Network With Attention to Boundaries. IEEE Trans Biomed Eng. 2018; 66(6):1637-1648. DOI: 10.1109/TBME.2018.2877577. View

10.

Aarnink R, Giesen R, Huynen A, de la Rosette J, Debruyne F, Wijkstra H . A practical clinical method for contour determination in ultrasonographic prostate images. Ultrasound Med Biol. 1994; 20(8):705-17. DOI: 10.1016/0301-5629(94)90028-0. View

11.

van Ginneken B, Frangi A, Staal J, Romeny B, Viergever M . Active shape model segmentation with optimal features. IEEE Trans Med Imaging. 2002; 21(8):924-33. DOI: 10.1109/TMI.2002.803121. View

12.

Badiei S, Salcudean S, Varah J, Morris W . Prostate segmentation in 2D ultrasound images using image warping and ellipse fitting. Med Image Comput Comput Assist Interv. 2007; 9(Pt 2):17-24. DOI: 10.1007/11866763_3. View

13.

Zhou Z, Siddiquee M, Tajbakhsh N, Liang J . UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentation. IEEE Trans Med Imaging. 2019; 39(6):1856-1867. PMC: 7357299. DOI: 10.1109/TMI.2019.2959609. View

14.

Richard W, Keen C . Automated texture-based segmentation of ultrasound images of the prostate. Comput Med Imaging Graph. 1996; 20(3):131-40. DOI: 10.1016/0895-6111(96)00048-1. View

15.

Shen D, Zhan Y, Davatzikos C . Segmentation of prostate boundaries from ultrasound images using statistical shape model. IEEE Trans Med Imaging. 2003; 22(4):539-51. DOI: 10.1109/TMI.2003.809057. View

16.

Hodge A, Fenster A, Downey D, Ladak H . Prostate boundary segmentation from ultrasound images using 2D active shape models: optimisation and extension to 3D. Comput Methods Programs Biomed. 2006; 84(2-3):99-113. DOI: 10.1016/j.cmpb.2006.07.001. View

17.

Noble J, Boukerroui D . Ultrasound image segmentation: a survey. IEEE Trans Med Imaging. 2006; 25(8):987-1010. DOI: 10.1109/tmi.2006.877092. View

18.

Ahn E, Bi L, Youn Hyun Jung , Kim J, Li C, Fulham M . Automated saliency-based lesion segmentation in dermoscopic images. Annu Int Conf IEEE Eng Med Biol Soc. 2016; 2015:3009-12. DOI: 10.1109/EMBC.2015.7319025. View