Quantitative Assessment of Fundus Tessellated Density in Highly Myopic Glaucoma Using Deep Learning.

Purpose: To characterize the fundus tessellated density (FTD) in highly myopic glaucoma (HMG) and high myopia (HM) for discovering early signs and diagnostic markers.

Methods: This retrospective cross-sectional study included hospital in-patients with HM (133 eyes) and HMG (73 eyes) with an axial length ≥26 mm at Zhongshan Ophthalmic Center. Using deep learning, FTD was quantified as the average exposed choroid area per unit area on fundus photographs in the global, macular, and disc regions. FTD-associated factors were assessed using partial correlation. Diagnostic efficacy was analyzed using the area under the curve (AUC).

Results: HMG patients had lower global (0.20 ± 0.12 versus 0.36 ± 0.09) and macular FTD (0.25 ± 0.14 vs. 0.40 ± 0.09) but larger disc FTD (0.24 ± 0.11 vs. 0.19 ± 0.07) than HM patients in the tessellated fundus (all P < 0.001). In the macular region, nasal FTD was lowest in the HM (0.26 ± 0.13) but highest in the HMG (0.32 ± 0.13) compared with the superior, inferior, and temporal subregions (all P < 0.05). A fundus with a macular region nasal/temporal (NT) FTD ratio > 0.96 (AUC = 0.909) was 15.7 times more indicative of HMG than HM. A higher macular region NT ratio with a lower horizontal parapapillary atrophy/disc ratio indicated a higher possibility of HMG than HM (AUC = 0.932).

Conclusions: FTD differs in degree and distribution between HMG and HM. A higher macular NT alone or with a lower horizontal parapapillary atrophy/disc ratio may help differentiate HMG.

Translational Relevance: Deep learning-based FTD measurement could potentially assist glaucoma diagnosis in HM.