1. Cross-instrument optical coherence tomography-angiography (OCTA)-based prediction of age-related macular degeneration (AMD) disease activity using artificial intelligence
- Author
-
Heinke, Anna, Zhang, Haochen, Broniarek, Krzysztof, Michalska-Małecka, Katarzyna, Elsner, Wyatt, Galang, Carlo Miguel B, Deussen, Daniel N, Warter, Alexandra, Kalaw, Fritz, Nagel, Ines, Agnihotri, Akshay, Mehta, Nehal N, Klaas, Julian Elias, Schmelter, Valerie, Kozak, Igor, Baxter, Sally L, Bartsch, Dirk-Uwe, Cheng, Lingyun, An, Cheolhong, Nguyen, Truong, and Freeman, William R
- Subjects
Biomedical and Clinical Sciences ,Ophthalmology and Optometry ,Biomedical Imaging ,Macular Degeneration ,Neurodegenerative ,Eye Disease and Disorders of Vision ,Neurosciences ,Bioengineering ,Aging ,4.1 Discovery and preclinical testing of markers and technologies ,Eye ,Humans ,Tomography ,Optical Coherence ,Retrospective Studies ,Cross-Sectional Studies ,Artificial Intelligence ,Male ,Aged ,Female ,Neural Networks ,Computer ,Aged ,80 and over ,Middle Aged ,Age-related macular degeneration ,Artificial intelligence ,Cross-instrument training ,Deep neural networks ,Optical coherence tomography-angiography - Abstract
This study investigates the efficacy of predicting age-related macular degeneration (AMD) activity through deep neural networks (DNN) using a cross-instrument training dataset composed of Optical coherence tomography-angiography (OCTA) images from two different manufacturers. A retrospective cross-sectional study analyzed 2D vascular en-face OCTA images from Heidelberg Spectralis (1478 samples: 1102 training, 276 validation, 100 testing) and Optovue Solix (1003 samples: 754 training, 189 validation, 60 testing). OCTA scans were labeled based on clinical diagnoses and adjacent B-scan OCT fluid information, categorizing activity into normal, dry AMD, active wet AMD, and wet AMD in remission. Experiments explored cross-instrument disease classification using separate and combined datasets for training the DNN. Testing involved 100 Heidelberg and 60 Optovue samples. Training on Heidelberg data alone yielded 73% accuracy on Heidelberg images and 60% on Optovue images. Training on Optovue data alone resulted in 34% accuracy on Heidelberg and 85% on Optovue images. Combined training data from both instruments achieved 78% accuracy on Heidelberg and 76% on Optovue test sets. Results indicate that cross-instrument classifier training demonstrates high classification prediction accuracy, making cross-instrument training viable for future clinical applications. This implies that vascular morphology in OCTA can predict disease progression.
- Published
- 2024