Utilizing human intelligence in artificial intelligence for detecting glaucomatous fundus images using human-in-the-loop machine learning

Abstract

Purpose: For diagnosing glaucomatous damage, we have employed a novel convolutional neural network (CNN) from TrueColor confocal fundus images to conquer the black box dilemma in artificial intelligence (AI). This neural network with CNN architecture with human-in-the-loop (HITL) data annotation helps not only in diagnosing glaucoma but also in predicting and locating detailed signs in the glaucomatous fundus, such as splinter hemorrhages, glaucomatous optic atrophy, vertical glaucomatous cupping, peripapillary atrophy, and retinal nerve fiber layer (RNFL) defect. Methods: The training was done on a well-curated private dataset of 1,400 high-resolution confocal fundus images, out of which 1,120 images (80%) were used exclusively for training and 280 images (20%) were used exclusively for testing. A custom trained You Only Look Once version 5 (YOLOv5)-based object detection methodology was used to identify the underlying conditions precisely. Twenty-six predefined medical conditions were annotated by a team of humans (comprising two glaucoma specialists and two optometrists) by using the Microsoft Visual Object Tagging Tool (VoTT) tool. The 280 testing images were split into three groups (90,100, and 90 images) for three test runs done once every 15 days. Results: Test results showed consistent increments in the accuracy, from 94.44% to 98.89%, in predicting the glaucoma diagnosis along with the detailed signs of the glaucomatous fundus Conclusion: Utilizing human intelligence in AI for detecting glaucomatous fundus images by using HITL machine learning has never been reported in the literature before. This AI model not only has good sensitivity and specificity in accurate glaucoma predictions but is also an explainable AI, thus overcoming the black box dilemma.

Under lock and key: Incorporation of blockchain technology in the field of ophthalmic artificial intelligence for big data management - A perfect match?

“…Ophthalmic AI is a growing branch with active research. [ 5 6 ] It is highly reliant on the availability of large, high-quality datasets with rigorous model validations and multiple testing phases. [ 7 8 9 ] However, the management of diverse data from different countries and centres for training and testing of algorithms poses significant challenges, such as data security threats and patient confidentiality issues.…”

Artificial intelligence in ophthalmology - Machines think!

“…[ 8 ] This issue of the Indian Journal of Ophthalmology carries publications on AI-applications in glaucoma, ultrasonography, and the acceptability of AI-based retinal screening. [ 10 11 12 ]…”

Automatic Classification of Slit-Lamp Photographs by Imaging Illumination

“…13 AI models have been applied to glaucoma, cataracts, and other anterior segment diseases, with promising work demonstrating the potential utility of DL for diagnosing keratitis using ocular surface slit-lamp photographs (SLPs). [14][15][16][17] A key step to realizing the full potential of these algorithms is integrating their use into the clinical workflow. To do this, a technologic infrastructure needs to be built to preprocess imaging data that are expected to be of high volume.…”

“…13 AI models have been applied to glaucoma, cataracts, and other anterior segment diseases, with promising work demonstrating the potential utility of DL for diagnosing keratitis using ocular surface slit-lamp photographs (SLPs). 14–17…”