基于3D U-Net 实现人体耳软骨MRI图像的解剖结构分割

doi:10.3969/j.issn.0258-8021.2021.05.03

Abstract
Figure/Table
References
Related Citation (4)

Download: PDF (2477 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract The method of costal cartilage carving is currently the clinical standard treatment of microtia, and auricular cartilage tissue engineering and 3D bioprinting are promising approaches. However, there has been a lack of automatic auricular cartilage segmentation based on medical images that is the crucial and fundamental issue of the treatments. In this study, an improved network based on 3D U-Net was proposed to automatically segment the anatomical structures of human auricular cartilage on MRI images. The proposed network combined the residual structure and multi-scale fusion design to reduce the number of network parameters and achieved an accurate segmentation of 12 auricular cartilage anatomical structures. Firstly, the Ultra-short Echo Time (UTE) sequence was applied to collect MRI images of the unilateral external auricular of 40 volunteers; secondly, manual segmentation of both auricular cartilage and multiple anatomical structures were performed on the preprocessed images of each volunteer; next, the images were divided into the training dataset of 32 images, the validation dataset of 4 images, and the testing dataset of 4 images to train the improved 3D U-Net model; finally, the 3D fully connected conditional random field was used to post-process the output of the proposed network. Ten-fold cross-validation was performed on the model, and the averaged Dice similarity coefficient (DSC) and 95% Hausdorff distance (HD95) of the automatic segmentation results of the 12 structures were 0.818 and 1.917, respectively. Compared with the basic 3D U-Net model, DSC was increased by 6.0% and HD95 was decreased by 3.186. Especially, the DSC of the key structure, helix and the antihelix, were 0.907 and 0.901, respectively. The experimental results showed that the segmentation results of the proposed method were very close to the manual annotations by experts. In clinical applications, based on the UTE image of the unilateral or parental auricle, the proposed method can quickly and automatically generate a 3D personalized craving template for the scaffold reconstruction with autologous costochondral cartilage and provide high-quality printable model for tissue engineering or 3D bioprinting technology to construct the composite scaffold with detailed auricular cartilage shape.

Key words： auricular cartilage ultra-short echo time 3D U-Net automatic segmentation

Received: 08 April 2021

PACS:

R318

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Sun Ruofan
	Zhang Weiwei

Cite this article:

Sun Ruofan,Zhang Weiwei. Anatomical Structure Segmentation of Human Auricular Cartilage MRI Images Based on 3D U-Net[J]. Chinese Journal of Biomedical Engineering, 2021, 40(5): 531-539.

URL:

http://cjbme.csbme.org/EN/10.3969/j.issn.0258-8021.2021.05.03 OR http://cjbme.csbme.org/EN/Y2021/V40/I5/531

[1] 陈佳鹏,张蕾,陈功,等. 中国1993-1998 年出生缺陷监测能力分析[J]. 中华流行病学杂志, 2006, 27(5):392-395.
[2] Li Chuan, Jiang Haiyue, Huang Chenyu, et al. A new strategy for total auricular reconstruction using prelamination of an extended retroauricular flap with tissue expansion.[J]. Journal of Plastic, Reconstructive & Aesthetic Surgery: JPRAS, 2016, 69(6):819-826.
[3] Baluch N, Nagata S, Park C,et al.Auricular reconstruction for microtia:a review of available methods[J].Plast Surg,2014,22(1):39-43.
[4] 许枫, 许志成, 张如鸿,等. 应用自体肋软骨构建外耳轮的美学研究[J]. 中华整形外科杂志, 2018, 34(3):172-177.
[5] Mussi E, Furferi R, Volpe Y, et al. Ear Reconstruction Simulation: From Handcrafting to 3D Printing [J]. Bioengineering, 2019, 6(1):14-33.
[6] Liu Yu. In vitro engineering of human ear-shaped cartilage assisted with CAD/CAM technology [J]. Biomaterials, 2010, 31(8): 2176-2183.
[7] Huang Ying, Zhang Xiaofei, Gao Guifang, et al. 3D bioprinting and the current applications in tissue engineering [J]. Biotechnology Journal, 2017, 12(8):1600734.
[8] Kang HW, Lee SJ, Ko IK, et al. A 3D bioprinting system to produce human-scale tissue constructs with structural integrity [J]. Nature Biotechnology, 2016, 34(3):312-319.
[9] Zhou Jiayu, Pan Bo, Yang Qinghua, et al. Three-dimensional autologous cartilage framework fabrication assisted by new additive manufactured ear-shaped templates for microtia reconstruction [J]. J Plast Reconstr Aesthet Surg, 2016, 69(10): 1436-1444.
[10] Nimeskern L, Feldmann EM, Kuo W, et al. Magnetic resonance imaging of the ear for patient-specific reconstructive surgery[J]. PLoS ONE, 2014, 9(8): e104975.
[11] 万丽娣, 邵泓达, 汤光宇. MRI超短回波时间序列评价关节软骨的研究进展[J]. 国际医学放射学杂志, 2017, 40(4):424-427.
[12] Eric Y. UTE imaging in the musculoskeletal system[J]. Journal of Magnetic Resonance Imaging, 2015, 41(4):870-883.
[13] Bly RA, Bhrany AD, Murakami CS, et al. Microtia Reconstruction [J]. Facial Plast Surg Clin North Am, 2016, 24(4): 577-591.
[14] Hong SG. From classical to deep learning: review on cartilage and bone segmentation techniques in knee osteoarthritis research [J]. Artificial Intelligence Review, 2020, 2020:1-50.
[15] Vilimek D, J Kubicek, Penhaker M, et al. Current automatic methods for knee cartilage segmentation: A review [C]// 2019 8th European Workshop on Visual Information Processing (EUVIP). New York: IEEE, 2019: 117-122.
[16] Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 39(4):640-651.
[17] Ronneberger O, Fischer P, Brox T. U-Net: Convolutional networks for biomedical image segmentation [C]// International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham: Springer International Publishing, 2015: 234-241.
[18] Iek Z, Abdulkadir A, Lienkamp SS, et al. 3D U-Net: Learning dense volumetric segmentation from sparse annotation [C]// International Conference on Medical Image Computing and Computer-Assisted Intervention. Cham: Springer International Publishing, 2016: 424-432.
[19] Milletari F, Navab N, Ahmadi SA. V-Net: Fully Convolutional neural networks for volumetric medical image segmentation [C]//2016 Fourth International Conference on 3D Vision (3DV). New York: IEEE, 2016: 565-571.
[20] Liu Xiangbin, Song Liping, Liu Shuai, et al. A Review of deep-learning-based medical image segmentation methods [J]. Sustainability, 2021, 13:1-29.
[21] Rezaei M, Yang Haojin, Meinel C. Deep learning for medical image analysis [J]. Annual Review of Biomedical Engineering, 2017, 19:221-248.
[22] 刘晓芳, 赵成. 基于多模态MRI图像的耳软骨模型构建[J]. 中国生物医学工程学报, 2019, 38(6):711-718.
[23] He Kaiming, Zhang Xiangyu, Ren Shaoqing, et al. Deep residual learning for image recognition [C]// IEEE Conference on Computer Vision and Pattern Recognition (CVPR). New York: IEEE, 2016: 770-778.
[24] Konstantinos K. Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation [J]. Medical Image Analysis, 2017, 36: 61-78.
[25] 李雪,张唯唯. MRI超短回波时间成像序列结合T2*映射技术用于在体耳软骨无创检测[J]. 中国生物医学工程学报, 2020, 39(3): 271-279.
[26] Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need [J]. Advances in Neural Information Processing Systems, 2017, 5998-6008.