arXiv subjects

Charis Y. N. Chiang

Publications and source records attributed to Charis Y. N. Chiang.

3 recordsLinked to original sources

arXiv2026

Interpretable AI plus Handheld, Portable Retinal Photographs: A Low-Cost Glaucoma Screening Solution for West Africa

Purpose: To develop and evaluate an interpretable artificial intelligence (AI) framework for glaucoma screening from low-cost portable, handheld retinal fundus photographs in a West African population and to compare its performance with clinical tabletop fundus imaging. Methods: We used data from a community-based study of 681 participants (1,362 eyes) in Nigeria, comprising 414 glaucoma, 478 glaucoma suspect, and 470 non-glaucoma eyes. Fundus photographs were acquired using the low-cost handheld, portable Volk Viva retinal camera and the Canon CR-2-AF tabletop camera. We fine-tuned component models separately to each device to perform vessel segmentation, cup and disc boundary segmentation, and feature extraction to detect optic nerve head features. A final classification model combined these components to classify scans as glaucoma, glaucoma suspect or non-glaucoma. Feature-weight analysis and Gradient-weighted Class Activation Mapping were used for interpretation. Results: The models performed well on both Volk Viva and Canon CR-2-AF images: Vessel segmentation: 0.98 Dice Coefficient (DC) (Volk) and 0.94 DC (Canon); Cup and disc segmentation: 0.95 DC (Volk) and 0.96 DC (Canon); Optic nerve head feature detection: area under the receiver operating characteristic curve (AUCs) of 0.83$\pm$0.03 (Volk) and 0.87$\pm$0.04 (Canon); Classification model: AUCs of 0.85$\pm$0.01 (Volk) and 0.93$\pm$0.01 (Canon). Reports for each image, present model decision confidence scores and decision-rationale visualizations to support clinical interpretation. Conclusions: Volk Viva results were reasonably comparable to Canon CR-2-AF in the component models and not far behind in classification. This shows that interpretable AI combined with low-cost, portable imaging may enhance community-level glaucoma screening, especially in settings with limited specialist access and resources.

cs.CV↗

arXiv2025

Impact of Optic Nerve Tortuosity, Globe Proptosis, and Size on Retinal Ganglion Cell Thickness Across General, Glaucoma, and Myopic Populations: Insights from the UK Biobank

Purpose: To investigate the impact of optic nerve tortuosity (ONT), and the interaction of globe proptosis and globe size on retinal ganglion cell (RGC) thickness, using Retinal Nerve Fiber Layer (RNFL) thickness, across general, glaucoma, and myopic populations. Methods: We analyzed 17,940 eyes from the UKBiobank cohort (ID 76442), including 72 glaucoma and 2475 myopic eyes. AI models segmented structures from 3D optical coherence tomography (OCT) scans and magnetic resonance images (MRI). RNFL thickness was derived from OCT scans and corrected for ocular magnification, was derived from OCT. From MRIs, we extracted: ONT, globe proptosis, axial length, and a novel interzygomatic line-to-posterior pole (ILPP) distance, a composite marker of globe proptosis and size. GEE models assessed associations between orbital and retinal features across all populations. Results: Segmentation models achieved Dice coefficients over 0.94 for both MRI and OCT. RNFL thickness was positively correlated with both ONT and ILPP distance (r = 0.065, p < 0.001, and r = 0.206, p < 0.001 respectively). The same was true for glaucoma (r = 0.040, p = 0.74, and r = 0.224, p = 0.059), and for myopia (r = 0.069, p < 0.001, and r = 0.100, p < 0.0001). GEE models revealed straighter optic nerves and shorter ILPP distance as predictive of thinner RNFL in all populations. Conclusions: This study emphasizes the impact of ONT, globe size, and proptosis on retinal health, suggesting RNFL thinning may arise from biomechanical stress due to straighter optic nerves or reduced ILPP distance, particularly in glaucoma or myopia. The novel ILPP metric, integrating globe size and position, shows potential as a biomarker for axonal health. These findings highlight the role of orbit structures in RGC axonal health and warrant further exploration of the biomechanical relationship between the orbit and optic nerve.

physics.med-ph↗

arXiv2022

Are Macula or Optic Nerve Head Structures better at Diagnosing Glaucoma? An Answer using AI and Wide-Field Optical Coherence Tomography

Purpose: (1) To develop a deep learning algorithm to automatically segment structures of the optic nerve head (ONH) and macula in 3D wide-field optical coherence tomography (OCT) scans; (2) To assess whether 3D macula or ONH structures (or the combination of both) provide the best diagnostic power for glaucoma. Methods: A cross-sectional comparative study was performed which included wide-field swept-source OCT scans from 319 glaucoma subjects and 298 non-glaucoma subjects. All scans were compensated to improve deep-tissue visibility. We developed a deep learning algorithm to automatically label all major ONH tissue structures by using 270 manually annotated B-scans for training. The performance of our algorithm was assessed using the Dice coefficient (DC). A glaucoma classification algorithm (3D CNN) was then designed using a combination of 500 OCT volumes and their corresponding automatically segmented masks. This algorithm was trained and tested on 3 datasets: OCT scans cropped to contain the macular tissues only, those to contain the ONH tissues only, and the full wide-field OCT scans. The classification performance for each dataset was reported using the AUC. Results: Our segmentation algorithm was able to segment ONH and macular tissues with a DC of 0.94 $\pm$ 0.003. The classification algorithm was best able to diagnose glaucoma using wide-field 3D-OCT volumes with an AUC of 0.99 $\pm$ 0.01, followed by ONH volumes with an AUC of 0.93 $\pm$ 0.06, and finally macular volumes with an AUC of 0.91 $\pm$ 0.11. Conclusions: this study showed that using wide-field OCT as compared to the typical OCT images containing just the ONH or macular may allow for a significantly improved glaucoma diagnosis. This may encourage the mainstream adoption of 3D wide-field OCT scans. For clinical AI studies that use traditional machines, we would recommend the use of ONH scans as opposed to macula scans.

eess.IV↗