Automatic corneal nerve fiber segmentation and geometric biomarker quantification
- PDF / 2,723,963 Bytes
- 16 Pages / 439.37 x 666.142 pts Page_size
- 51 Downloads / 168 Views
Automatic corneal nerve fiber segmentation and geometric biomarker quantification Dan Zhang1, Fan Huang2 , Maziyar Khansari3 , Tos T. J. M. Berendschot4 , Xiayu Xu5 , Behdad Dashtbozorg6 , Yue Sun7 , Jiong Zhang3 , Tao Tan1,a 1 Department of Mathematics and Computer Science, Eindhoven University of Technology, Eindhoven,
The Netherlands
2 Department of Biomedical Engineering, Eindhoven University of Technology, Eindhoven,
The Netherlands
3 Laboratory of Neuro Imaging (LONI), USC Stevens Neuroimaging and Informatics Institute, Keck School
of Medicine of University of Southern California, Los Angeles, USA
4 University Eye Clinic Maastricht, Maastricht, The Netherlands 5 Key Laboratory of Biomedical Information Engineering of Ministry of Education, School of Life Science
and Technology, Xi’an Jiaotong University, Xi’an, China
6 Department of Surgery, Netherlands Cancer Institute, Amsterdam, The Netherlands 7 Department of Electrical Engineering, Eindhoven University of Technology, Eindhoven, The Netherlands
Received: 11 June 2019 / Accepted: 2 December 2019 © The Author(s) 2020
Abstract Geometric and topological features of corneal nerve fibers in confocal microscopy images are important indicators for the diagnosis of common diseases such as diabetic neuropathy. Quantitative analysis of these important biomarkers requires an accurate segmentation of the nerve fiber network. Currently, most of the analysis are performed based on manual annotations of the nerve fiber segments, while a fully automatic corneal nerve fiber extraction and analysis framework is still needed. In this paper, we establish a fully convolutional network method to precisely enhance and segment corneal nerve fibers in microscopy images. Based on the segmentation results, automatic tortuosity measurement and branching detection modules are established to extract valuable geometric and topological biomarkers. The proposed segmentation method is validated on a dataset with 142 images. The experimental results show that our deep learning-based framework outperforms state-of-the-art segmentation approaches. The biomarker extraction methods are validated on two different datasets, demonstrating high effectiveness and reliability of the proposed methods.
1 Introduction Corneal confocal microscopy (CCM) is an efficient and non-invasive imaging technique that is used to examine the human corneal nerve fiber morphology in a variety of diseases [1–
Dan Zhang and Fan Huang contributed equally. This work was supported in part by National Natural Science Foundation of China (No. 81801776), Natural Science Research Foundation of Jiangsu Province (No. BK20170256) and Shanghai Key Lab of Digital Media Processing and Transmission (STCSM 18DZ2270700). a e-mail: [email protected] (corresponding author)
0123456789().: V,-vol
123
266
Page 2 of 16
Eur. Phys. J. Plus
(2020) 135:266
3]. There exist strong connections between disease progression and geometric/topological changes of nerve fibers. Previous findings show that tortuosity, branching points and d
Data Loading...
