Automatic Segmentation of Cortex and Nucleus in Anterior Segment OCT Images

被引：6

作者：

Yin, Pengshuai ^{[1
]}

Tan, Mingkui ^{[1
]}

Min, Huaqing ^{[1
]}

Xu, Yanwu ^{[2
,4
]}

Xu, Guanghui ^{[1
]}

Wu, Qingyao ^{[1
]}

Tong, Yunfei ^{[2
]}

Risa, Higashita ^{[3
]}

Liu, Jiang ^{[4
]}

机构：

[1] South China Univ Technol, Guangzhou, Guangdong, Peoples R China

[2] Guangzhou Shiyuan Elect Technol Co Ltd, Guangzhou, Guangdong, Peoples R China

[3] Tommy Corp, Nagoya, Aichi, Japan

[4] Chinese Acad Sci, Cixi Inst Biomed Engn, Cixi, Peoples R China

来源：

COMPUTATIONAL PATHOLOGY AND OPHTHALMIC MEDICAL IMAGE ANALYSIS | 2018年 / 11039卷

关键词：

SS-OCT; AS-OCT; Image segmentation; QUANTIFICATION;

D O I：

10.1007/978-3-030-00949-6_32

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

We propose a pipeline for automatically segmenting cortex and nucleus in a 360-degree anterior segment optical coherence tomography (AS-OCT) image. The proposed pipeline consists of a U-shaped network followed by a shape template. The U-shaped network predicts a mask for cortex and nucleus. However, the boundary between cortex and nucleus is weak, so that the boundary of the prediction is an irregular shape and does not satisfy the physiological structure of nucleus. To address this problem, in the second step, we design a shape template according to the physiological structure of nucleus to refine the boundary. Our method integrates both appearance and structure information. The accuracy is measured by the normalized mean squared error (NMSE) between ground truth line and predicted line. We achieve NMSE 7.09/7.94 for nucleus top/bottom boundary and 2.49/2.43 for cortex top/bottom boundary.

引用

页码：269 / 276

页数：8

共 9 条

[1] Joint Optic Disc and Cup Segmentation Based on Multi-Label Deep Network and Polar Transformation
Fu, Huazhu
Cheng, Jun
Xu, Yanwu
Wong, Damon Wing Kee
Liu, Jiang
Cao, Xiaochun
[J]. IEEE TRANSACTIONS ON MEDICAL IMAGING, 2018, 37 (07) : 1597 - 1605
[2] Segmentation and Quantification for Angle-Closure Glaucoma Assessment in Anterior Segment OCT
Fu, Huazhu
Xu, Yanwu
Lin, Stephen
Zhang, Xiaoqin
Wong, Damon Wing Kee
Liu, Jiang
Frangi, Alejandro F.
Baskaran, Mani
Aung, Tin
[J]. IEEE TRANSACTIONS ON MEDICAL IMAGING, 2017, 36 (09) : 1930 - 1938
[3] Fujimoto JG, 2016, INVEST OPHTH VIS SCI, V57
[4] Kaufman P.L., 2011, ADLERS PHYSL EYE
[5] New objective lens density quantification method using swept-source optical coherence tomography technology: Comparison with existing methods
Panthier, Christophe
Burgos, Justine
Rouger, Helene
Saad, Alain
Gatinel, Damien
[J]. JOURNAL OF CATARACT AND REFRACTIVE SURGERY, 2017, 43 (12) : 1575 - 1581
[6] U-Net: Convolutional Networks for Biomedical Image Segmentation
Ronneberger, Olaf
Fischer, Philipp
Brox, Thomas
[J]. MEDICAL IMAGE COMPUTING AND COMPUTER-ASSISTED INTERVENTION, PT III, 2015, 9351 : 234 - 241
[7] Fast Ray Features for Learning Irregular Shapes
Smith, Kevin
Carleton, Alan
Lepetit, Vincent
[J]. 2009 IEEE 12TH INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2009, : 397 - 404
[8] Quantitative assessment of lens opacities with anterior segment optical coherence tomography
Wong, A. L.
Leung, C. K-S
Weinreb, R. N.
Cheng, A. K. C.
Cheung, C. Y. L.
Lam, P. T-H
Pang, C. P.
Lam, D. S. C.
[J]. BRITISH JOURNAL OF OPHTHALMOLOGY, 2009, 93 (01) : 61 - 65
[9] Yanwu Xu, 2016, Medical Image Computing and Computer-Assisted Intervention - MICCAI 2016. 19th International Conference. Proceedings: LNCS 9902, P441, DOI 10.1007/978-3-319-46726-9_51

← 1 →