DISEASE CLASSIFICATION OF MACULAR OPTICAL COHERENCE TOMOGRAPHY SCANS USING DEEP LEARNING SOFTWARE: Validation on Independent, Multicenter Data. Issue 8 (August 2020)

• Record Type: Journal Article
• Authors: Bhatia, Kanwal K.; Graham, Mark S.; Terry, Louise; Wood, Ashley; Tranos, Paris; Trikha, Sameer; Jaccard, Nicolas
• Is Part Of: Retina. Volume 40:Issue 8(2020)
• Publication Date: 2020-08
• Subjects: age-related macular degeneration -- artificial intelligence -- clinical decision support -- computer-aided diagnosis -- deep learning -- diabetic macular edema -- optical coherence tomography; Retina -- Diseases -- Periodicals; Retinal Diseases; Vitreous Body; 617.735
• DOI: 10.1097/IAE.0000000000002640
• Languages: English
• ISSNs: 0275-004X

Abstract

Abstract : Purpose: To evaluate Pegasus optical coherence tomography (OCT), a clinical decision support software for the identification of features of retinal disease from macula OCT scans, across heterogenous populations involving varying patient demographics, device manufacturers, acquisition sites, and operators. Methods: Five thousand five hundred and eighty-eight normal and anomalous macular OCT volumes (162, 721 B-scans), acquired at independent centers in five countries, were processed using the software. Results were evaluated against ground truth provided by the data set owners. Results: Pegasus-OCT performed with areas under the curve of the receiver operating characteristic of at least 98% for all data sets in the detection of general macular anomalies. For scans of sufficient quality, the areas under the curve of the receiver operating characteristic for general age-related macular degeneration and diabetic macular edema detection were found to be at least 99% and 98%, respectively. Conclusion: The ability of a clinical decision support system to cater for different populations is key to its adoption. Pegasus-OCT was shown to be able to detect age-related macular degeneration, diabetic macular edema, and general anomalies in OCT volumes acquired across multiple independent sites with high performance. Its use thus offers substantial promise, with the potential to alleviate the burden of growing demand in eye care services caused by retinal disease. Abstract : Supplemental Digital Content is Available in the Text.Validation of Pegasus optical coherence tomography, an artificial intelligence–based software for the automated detection of macula disease from optical coherence tomography scans, is conducted on independent, multicenter data. Five thousand five hundred and eighty-eight volumes spanning multiple populations, device manufacturers, and acquisition sites were assessed. Pegasus optical coherence tomography achieves areas under the curve of the receiver operating characteristic of >98% on age-related macular degeneration, diabetic macular edema, and general anomaly detection.