Describing the Structural Phenotype of the Glaucomatous Optic Nerve Head Using Artificial Intelligence.
Panda Satish K, Cheong Haris, Tun Tin A, Devella Sripad K, Senthil Vijayalakshmi, Krishnadas Ramaswami, Buist Martin L, Perera Shamira, Cheng Ching-Yu, Aung Tin
AI Summary
AI deep learning accurately identified novel structural optic nerve head biomarkers from OCTs, revealing how ONH morphology changes in glaucoma and offering a robust diagnostic tool.
Abstract
Purpose
To develop a novel deep-learning approach that can describe the structural phenotype of the glaucomatous optic nerve head (ONH) and can be used as a robust glaucoma diagnosis tool.
Design
Retrospective, deep-learning approach diagnosis study.
Method
We trained a deep-learning network to segment 3 neural-tissue and 4 connective-tissue layers of the ONH. The segmented optical coherence tomography images were then processed by a customized autoencoder network with an additional parallel branch for binary classification. The encoder part of the autoencoder reduced the segmented optical coherence tomography images into a low-dimensional latent space (LS), whereas the decoder and the classification branches reconstructed the images and classified them as glaucoma or nonglaucoma, respectively. We performed principal component analysis on the latent parameters and identified the principal components (PCs). Subsequently, the magnitude of each PC was altered in steps and reported how it impacted the morphology of the ONH.
Results
The image reconstruction quality and diagnostic accuracy increased with the size of the LS. With 54 parameters in the LS, the diagnostic accuracy was 92.0 ± 2.3% with a sensitivity of 90.0 ± 2.4% (at 95% specificity), and the corresponding Dice coefficient for the reconstructed images was 0.86 ± 0.04. By changing the magnitudes of PC in steps, we were able to reveal how the morphology of the ONH changes as one transitions from a "nonglaucoma" to a "glaucoma" condition.
Conclusions
Our network was able to identify novel biomarkers of the ONH for glaucoma diagnosis. Specifically, the structural features identified by our algorithm were found to be related to clinical observations of glaucoma.
MeSH Terms
Shields Classification
Key Concepts5
With 54 parameters in the low-dimensional latent space (LS), the deep-learning network achieved a diagnostic accuracy of 92.0 ± 2.3% for glaucoma, with a sensitivity of 90.0 ± 2.4% (at 95% specificity), and a Dice coefficient of 0.86 ± 0.04 for reconstructed images.
By altering the magnitudes of principal components (PCs) within the deep-learning network, the morphology of the optic nerve head (ONH) was shown to change as one transitions from a 'nonglaucoma' to a 'glaucoma' condition.
The deep-learning network identified novel biomarkers of the optic nerve head (ONH) for glaucoma diagnosis, with the structural features identified by the algorithm found to be related to clinical observations of glaucoma.
A novel deep-learning approach was developed to describe the structural phenotype of the glaucomatous optic nerve head (ONH) and serve as a robust glaucoma diagnosis tool.
A deep-learning network was trained to segment 3 neural-tissue and 4 connective-tissue layers of the optic nerve head (ONH) from optical coherence tomography images.
Related Articles5
Age-related changes in optical coherence tomography glaucoma-related parameters: A systematic review.
Systematic ReviewArtificial Intelligence Deep Learning Models to Predict Spaceflight Associated Neuro-Ocular Syndrome.
Observational StudyAxial elongation in nonpathologic high myopia: Ocular structural changes and glaucoma diagnostic challenges.
ReviewLongitudinal Analysis of Retinal Ganglion Cell Damage at Individual Axon Bundle Level in Mice Using Visible-Light Optical Coherence Tomography Fibergraphy.
Basic ScienceGeometric Deep Learning to Identify the Critical 3D Structural Features of the Optic Nerve Head for Glaucoma Diagnosis.
Observational StudyIs this article assigned to the wrong chapter(s)? Let us know.