# AI-based Clinical Assessment of Optic Nerve Head Robustness Superseding Biomechanical Testing

arXiv: https://arxiv.org/abs/2206.04689 · HTML: https://mlsanity.com/paper/2206.04689/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 65 references that are in the map.
- First posted on arXiv 9 Jun 2022.

## Builds on (most cited first, 6 of 6)

- [Dynamic Graph CNN for Learning on Point Clouds](https://mlsanity.com/paper/1801.07829/) (2018)
- [A feature agnostic approach for glaucoma detection in OCT volumes](https://mlsanity.com/paper/1807.04855/) (2018)
- [Describing the Structural Phenotype of the Glaucomatous Optic Nerve Head Using Artificial Intelligence](https://mlsanity.com/paper/2012.09755/) (2020)
- [Towards Label-Free 3D Segmentation of Optical Coherence Tomography Images of the Optic Nerve Head Using Deep Learning](https://mlsanity.com/paper/2002.09635/) (2020)
- [DRUNET: A Dilated-Residual U-Net Deep Learning Network to Digitally Stain Optic Nerve Head Tissues in Optical Coherence Tomography Images](https://mlsanity.com/paper/1803.00232/) (2018)
- [Geometric Deep Learning to Identify the Critical 3D Structural Features of the Optic Nerve Head for Glaucoma Diagnosis](https://mlsanity.com/paper/2204.06931/) (2022)

## Built on by (most cited first, 1 of 1)

- [On Inverse Problems, Parameter Estimation, and Domain Generalization](https://mlsanity.com/paper/2506.06024/) (2025)

## Abstract (arXiv)

Purpose: To use artificial intelligence (AI) to: (1) exploit biomechanical knowledge of the optic nerve head (ONH) from a relatively large population; (2) assess ONH robustness from a single optical coherence tomography (OCT) scan of the ONH; (3) identify what critical three-dimensional (3D) structural features make a given ONH robust. Design: Retrospective cross-sectional study. Methods: 316 subjects had their ONHs imaged with OCT before and after acute intraocular pressure (IOP) elevation through ophthalmo-dynamometry. IOP-induced lamina-cribrosa deformations were then mapped in 3D and used to classify ONHs. Those with LC deformations superior to 4% were considered fragile, while those with deformations inferior to 4% robust. Learning from these data, we compared three AI algorithms to predict ONH robustness strictly from a baseline (undeformed) OCT volume: (1) a random forest classifier; (2) an autoencoder; and (3) a dynamic graph CNN (DGCNN). The latter algorithm also allowed us to identify what critical 3D structural features make a given ONH robust. Results: All 3 methods were able to predict ONH robustness from 3D structural information alone and without the need to perform biomechanical testing. The DGCNN (area under the receiver operating curve [AUC]: 0.76 ± 0.08) outperformed the autoencoder (AUC: 0.70 ± 0.07) and the random forest classifier (AUC: 0.69 ± 0.05). Interestingly, to assess ONH robustness, the DGCNN mainly used information from the scleral canal and the LC insertion sites. Conclusions: We propose an AI-driven approach that can assess the robustness of a given ONH solely from a single OCT scan of the ONH, and without the need to perform biomechanical testing. Longitudinal studies should establish whether ONH robustness could help us identify fast visual field loss progressors.