Deep Neural Network-Based Method for Detecting Obstructive Meibomian Gland Dysfunction With in Vivo Laser Confocal Microscopy

Abstract

Purpose: To evaluate the ability of deep learning (DL) models to detect obstructive meibomian gland dysfunction (MGD) using in vivo laser confocal microscopy images. Methods: For this study, we included 137 images from 137 individuals with obstructive MGD (mean age, 49.9 ± 17.7 years; 44 men and 93 women) and 84 images from 84 individuals with normal meibomian glands (mean age, 53.3 ± 19.6 years; 29 men and 55 women). We constructed and trained 9 different network structures and used single and ensemble DL models and calculated the area under the curve, sensitivity, and specificity to compare the diagnostic abilities of the DL. Results: For the single DL model (the highest model; DenseNet-201), the area under the curve, sensitivity, and specificity for diagnosing obstructive MGD were 0.966%, 94.2%, and 82.1%, respectively, and for the ensemble DL model (the highest ensemble model; VGG16, DenseNet-169, DenseNet-201, and InceptionV3), 0.981%, 92.1%, and 98.8%, respectively. Conclusions: Our network combining DL and in vivo laser confocal microscopy learned to differentiate between images of healthy meibomian glands and images of obstructive MGD with a high level of accuracy that may allow for automatic obstructive MGD diagnoses in patients in the future.

Prediction of age and brachial-ankle pulse-wave velocity using ultra-wide-field pseudo-color images by deep learning

“…Recently, artificial intelligence (AI) technology including deep learning (DL) has resulted in remarkable progress in medicine, and various applications for diagnostic imaging have been reported 15 . In the field of ophthalmology, many researchers, including the authors, have reported the performance of DL in image analysis using in vivo laser confocal microscopy, optical coherence tomography (OCT), OCT angiography, and ultra-wide-field fundus ophthalmoscopy 16 – 27 . Recently, Poplin et al reported that using machine-learning algorithms, cardiovascular risk factors including age can be predicted from retinal fundus photographs 28 .…”

A deep learning approach for successful big-bubble formation prediction in deep anterior lamellar keratoplasty

“…Automated image recognition using deep learning methods is becoming increasingly important in the decision making, planning, and execution of ophthalmic surgeries. While there are numerous studies on the retina, there are very few studies on the anterior eye segments, especially the cornea 17 , 18 . Nevertheless, it has been shown that artificial intelligence and image data obtained by OCT can be used to detect and classify certain corneal diseases, and even predict the probability of the need for future keratoplasty 19 .…”

A Deep Learning Approach for Successful Big-bubble Formation Prediction in Deep Anterior Lamellar Keratoplasty

“…Automated image recognition using deep learning methods is becoming increasingly important in the decision making, planning, and execution of ophthalmic surgeries. While there are numerous studies on the retina, there are very few studies on the anterior eye segments, especially the cornea [14,15].…”