Searcharxiv⌕ Search

arXiv subjects

Deepta Ghate

Publications and source records attributed to Deepta Ghate.

2 recordsLinked to original sources

Information about Optic Nerve Head Biomechanics is Already Coded in Your Clinical Charts and Can be Used to Predict Glaucoma Progression

Glaucoma patients routinely undergo optical coherence tomography (OCT) imaging and intraocular pressure (IOP) assessment as part of standard care. Because IOP typically differs across visits, it is possible to map visit-to-visit ONH strains by registering OCT volumes acquired under different IOPs. These strains reflect ONH elasticity and, over longer intervals, also capture growth and remodeling of the ONH. In this study, we evaluated whether such visit-to-visit ONH strain signatures could serve as predictors of glaucoma progression. We retrospectively analyzed 525 eyes from 430 glaucoma patients (238 fast and 287 slow progressors), defining fast progression by a visual field index slope of -1.5% per year or worse. 3D strain maps were derived from baseline and follow-up OCT scans using AI. Predictions using T=1 to T=4 follow-up visits were evaluated by five-fold cross-validation in a long-term cohort (T=1: 1.30 years; T=4: 5.26 years) and short-term testing (T=1: 0.46 years; T=4: 1.25 years). Overall, IOP differed between paired visits in 92% of cases. Long-term T=1 prediction achieved an area under the receiver operating characteristic curve (AUC) of 0.74 and accuracy of 0.72. A single short-term follow-up (T=1) yielded an AUC of 0.75 and accuracy of 0.71; four follow-ups yielded an AUC of 0.87 and accuracy of 0.82. SHapley Additive exPlanations (SHAP) identified neuroretinal rim compression and prelaminar elongation associated with fast progression, with substantial inter-eye variability. Overall, visit-to-visit ONH strains derived from routine OCT predicted glaucoma progression after a single follow-up visit at a mean interval of 0.46 years. These findings suggest that short-term OCT/IOP assessments could provide valuable insights into ONH biomechanics, identify eyes at risk of rapid progression, and reveal distinct strain signatures associated with disease progression.

eess.IV↗

The Emory Optic Nerve Head Atlas - Using 3D Anatomical Mapping to Study Optic Neuropathies with an Initial Focus on Glaucoma

Purpose: To develop the first 3D optic nerve head (ONH) atlas using AI-based registration and evaluate its use in: (1) atlas-adjusted retinal nerve fiber layer (RNFL) analysis for glaucoma diagnosis, and (2) strain-based assessment of glaucoma severity. Methods: Large-scale OCT datasets were registered using REFLECTIVITY-generated tissue segmentations. A healthy atlas (n=460) and glaucoma atlases for mild (n=852), moderate (n=640), and severe (n=546) disease were built using an AI-driven algorithm incorporating structural and biomechanical constraints. Atlas quality was evaluated using inter-layer contrast and agreement between warped scans and the template. Atlas-adjusted RNFL thickness was extracted by mapping fixed 1.5 mm BMO-based reference points from the atlas to each subject and compared with standard subject-specific RNFL measurements. Effective strain relative to each atlas was computed by morphing subjects to the atlas template. Strain and thickness features were used to classify glaucoma severity. Results: The healthy atlas captured normative ONH anatomy, while glaucoma atlases showed stage-dependent changes. Registration accuracy was high (NCC=0.86+-0.05; Dice=0.90+-0.02), with strong inter-layer contrast (0.40+-0.03). Atlas-adjusted RNFL thickness improved separation between healthy and mild glaucoma (Cohen's d=0.77 vs. 0.72). Classification using atlas-adjusted profiles outperformed native measurements (AUC=0.771 vs. 0.757). Mean effective strain differed significantly across severity groups (ANOVA p<0.05), and CNNs trained on strain maps achieved strong classification (AUC=0.79). Conclusion: The ONH atlas provides a population-derived structural reference enabling anatomically consistent thickness mapping and strain-based characterization. It enhances diagnostic discrimination, supports severity classification, and offers a framework to study glaucomatous biomechanics.

physics.med-ph↗