Quantification of Fundus Autofluorescence Features in a Molecularly Characterized Cohort of >3500 Patients with Inherited Retinal Disease from the United Kingdom.
Woof WA., de Guimarães TAC., Al-Khuzaei S., Daich Varela M., Sen S., Bagga P., Mendes B., Shah M., Burke P., Parry D., Lin S., Naik G., Ghoshal B., Liefers BJ., Fu DJ., Georgiou M., Nguyen Q., Sousa da Silva A., Liu Y., Fujinami-Yokokawa Y., Sumodhee D., Patel P., Furman J., Moghul I., Moosajee M., Sallum J., De Silva SR., Lorenz B., Holz FG., Fujinami K., Webster AR., Mahroo OA., Downes SM., Madhusudhan S., Balaskas K., Michaelides M., Pontikos N.
PURPOSE: To quantify relevant fundus autofluorescence (FAF) features cross-sectionally and longitudinally in a large cohort of patients with inherited retinal diseases (IRDs). DESIGN: Retrospective study of imaging data. PARTICIPANTS: Patients with a clinical and molecularly confirmed diagnosis of IRD who have undergone 55° FAF imaging at Moorfields Eye Hospital (MEH) and the Royal Liverpool Hospital between 2004 and 2019. METHODS: Five FAF features of interest were defined: vessels, optic disc, perimacular ring of increased signal (ring), relative hypo-autofluorescence (hypo-AF), and hyper-autofluorescence (hyper-AF). Features were manually annotated by 6 graders in a subset of patients based on a defined grading protocol to produce segmentation masks to train an artificial intelligence model, AIRDetect, which was then applied to the entire imaging data set. MAIN OUTCOME MEASURES: Quantitative FAF features, including area and vessel metrics, were analyzed cross-sectionally by gene and age, and longitudinally. AIRDetect feature segmentation and detection were validated with Dice score and precision/recall, respectively. RESULTS: A total of 45 749 FAF images from 3606 patients with IRD from MEH covering 170 genes were automatically segmented using AIRDetect. Model-grader Dice scores for the disc, hypo-AF, hyper-AF, ring, and vessels were, respectively, 0.86, 0.72, 0.69, 0.68, and 0.65. Across patients at presentation, the 5 genes with the largest hypo-AF areas were CHM, ABCC6, RDH12, ABCA4, and RPE65, with mean per-patient areas of 43.72, 29.57, 20.07, 19.65, and 16.92 mm2, respectively. The 5 genes with the largest hyper-AF areas were BEST1, CDH23, NR2E3, MYO7A, and RDH12, with mean areas of 0.50, 047, 0.44, 0.38, and 0.33 mm2, respectively. The 5 genes with the largest ring areas were NR2E3, CDH23, CRX, EYS, and PDE6B, with mean areas of 3.60, 2.90, 2.89, 2.56, and 2.20 mm2, respectively. Vessel density was found to be highest in EFEMP1, BEST1, TIMP3, RS1, and PRPH2 (11.0%, 10.4%, 10.1%, 10.1%, 9.2%) and was lower in retinitis pigmentosa (RP) and Leber congenital amaurosis genes. Longitudinal analysis of decreasing ring area in 4 RP genes (RPGR, USH2A, RHO, and EYS) found EYS to be the fastest progressor at -0.178 mm2/year. CONCLUSIONS: We have conducted the first large-scale cross-sectional and longitudinal quantitative analysis of FAF features across a diverse range of IRDs using a novel AI approach. FINANCIAL DISCLOSURES: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.