Automated segmentation of corneal nerves in confocal microscopy via contrastive learning based synthesis and quality enhancement

Lin，Li1,2; Cheng，Pujin1; Wang，Zhonghua1; Li，Meng3; Wang，Kai2; Tang，Xiaoying1

10.1109/ISBI48211.2021.9433955

2021-04-13

1945-7928

1945-8452

978-1-6654-2947-4

Proceedings - International Symposium on Biomedical Imaging

2021-April

1314-1318

13-16 April 2021

Nice, France

Precise quantification of the corneal nerve plexus morphology is of great importance in diagnosing peripheral diabetic neuropathy and assessing the progression of various eye-related systemic diseases, wherein segmentation of corneal nerves is an essential component. In this paper, we proposed and validated a novel pipeline for corneal nerve segmentation, comprising corneal confocal microscopy (CCM) image synthesis, image quality enhancement and nerve segmentation. Our goal was to address three major problems existing in most CCM datasets, namely inaccurate annotations, non-uniform illumination and contrast variations. In our synthesis and enhancement steps, we employed multilayer and patchwise contrastive learning based Generative Adversarial Network (GAN) frameworks, which took full advantage of multi-scale local features. Through both qualitative and quantitative experiments on two publicly available CCM datasets, our pipeline has achieved overwhelming enhancement performance compared to several state-of-the-art methods. Moreover, the segmentation results showed that models trained on our synthetic images performed much better than those trained on a real CCM dataset, which clearly identified the effectiveness of our synthesis method. Overall, our proposed pipeline can achieve satisfactory segmentation performance for poor-quality CCM images without using any manual labels and can effectively enhance those images.

Contrastive learning Corneal confocal microscopy. Corneal nerve segmentation Dataset synthesis Quality enhancement

第一 ; 通讯

英语

EI

20212310465472

Confocal microscopy ; Diagnosis ; Image segmentation ; Medical imaging ; Multilayers ; Pipelines ; Quality control

Medicine and Pharmacology:461.6 ; Pipe, Piping and Pipelines:619.1 ; Optical Devices and Systems:741.3 ; Imaging Techniques:746 ; Quality Assurance and Control:913.3

2-s2.0-85107191180

Scopus

1.Southern University of Science and Technology,Department of Electrical and Electronic Engineering,Shenzhen,China
2.Sun Yat-sen University,School of Electronics and Information Technology,Guangzhou,China
3.Sun Yat-sen University,State Key Laboratory of Ophthalmology,Zhongshan Ophthalmic Centre,Guangzhou,China

Lin，Li,Cheng，Pujin,Wang，Zhonghua,et al. Automated segmentation of corneal nerves in confocal microscopy via contrastive learning based synthesis and quality enhancement[C],2021:1314-1318.