Artificial Intelligence to Detect Meibomian Gland Dysfunction From in-vivo Laser Confocal Microscopy

Ye-Ye Zhang; Hui Zhao; Jin-Yan Lin; Shi-Nan Wu; Xi-Wang Liu; Hong-Dan Zhang; Yi Shao; Wei-Feng Yang

doi:10.3389/fmed.2021.774344

Artificial Intelligence to Detect Meibomian Gland Dysfunction From in-vivo Laser Confocal Microscopy

Front Med (Lausanne). 2021 Nov 25:8:774344. doi: 10.3389/fmed.2021.774344. eCollection 2021.

Authors

Ye-Ye Zhang^{1

2}, Hui Zhao³, Jin-Yan Lin⁴, Shi-Nan Wu⁵, Xi-Wang Liu^{4

6}, Hong-Dan Zhang^{4

6}, Yi Shao⁵, Wei-Feng Yang^{2

4

6}

Affiliations

¹ Department of Electronic Engineering, School of Science, Hainan University, Haikou, China.
² Department of Electronic Engineering, College of Engineering, Shantou University, Shantou, China.
³ Department of Ophthalmology, Shanghai First People's Hospital, Shanghai Jiao Tong University, National Clinical Research Center for Eye Diseases, Shanghai, China.
⁴ Research Center for Advanced Optics and Photoelectronics, Department of Physics, College of Science, Shantou University, Shantou, China.
⁵ Jiangxi Centre of National Ophthalmology Clinical Research Center, Department of Ophthalmology, The First Affiliated Hospital of Nanchang University, Nanchang, China.
⁶ Department of Mathematics, College of Science, Shantou University, Shantou, China.

Abstract

Background: In recent years, deep learning has been widely used in a variety of ophthalmic diseases. As a common ophthalmic disease, meibomian gland dysfunction (MGD) has a unique phenotype in in-vivo laser confocal microscope imaging (VLCMI). The purpose of our study was to investigate a deep learning algorithm to differentiate and classify obstructive MGD (OMGD), atrophic MGD (AMGD) and normal groups. Methods: In this study, a multi-layer deep convolution neural network (CNN) was trained using VLCMI from OMGD, AMGD and healthy subjects as verified by medical experts. The automatic differential diagnosis of OMGD, AMGD and healthy people was tested by comparing its image-based identification of each group with the medical expert diagnosis. The CNN was trained and validated with 4,985 and 1,663 VLCMI images, respectively. By using established enhancement techniques, 1,663 untrained VLCMI images were tested. Results: In this study, we included 2,766 healthy control VLCMIs, 2,744 from OMGD and 2,801 from AMGD. Of the three models, differential diagnostic accuracy of the DenseNet169 CNN was highest at over 97%. The sensitivity and specificity of the DenseNet169 model for OMGD were 88.8 and 95.4%, respectively; and for AMGD 89.4 and 98.4%, respectively. Conclusion: This study described a deep learning algorithm to automatically check and classify VLCMI images of MGD. By optimizing the algorithm, the classifier model displayed excellent accuracy. With further development, this model may become an effective tool for the differential diagnosis of MGD.

Keywords: DenseNet CNN; convolution neural network; deep learning; in-vivo confocal microscopy; meibomian gland dysfunction.