{"doi":"10.1038/s41598-024-78327-0","title":"Cross-instrument optical coherence tomography-angiography (OCTA)-based prediction of age-related macular degeneration (AMD) disease activity using artificial intelligence","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.","journal":"Scientific Reports","year":2024,"id":439302,"datarank":0.3596842909197557,"base_score":2.3978952727983707,"endowment":2.3978952727983707,"self_citation_contribution":0.3596842909197557,"citation_network_contribution":0.0,"self_endowment_contribution":0.3596842909197557,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":10,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.7628,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2024-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":1249975,"name":"Haochen Zhang","orcid":"0009-0006-6950-5244","position":1,"is_corresponding":false},{"id":1249976,"name":"Krzysztof Broniarek","orcid":"0000-0002-7034-7240","position":2,"is_corresponding":false},{"id":1249977,"name":"Katarzyna Michalska‐Małecka","orcid":"0000-0002-0550-8386","position":3,"is_corresponding":false},{"id":1250616,"name":"Wyatt Elsner","orcid":null,"position":4,"is_corresponding":false},{"id":1054635,"name":"Carlo Miguel B. Galang","orcid":null,"position":5,"is_corresponding":false},{"id":1054634,"name":"Daniel N. Deussen","orcid":null,"position":6,"is_corresponding":false},{"id":949030,"name":"Alexandra Warter","orcid":"0000-0001-6569-8452","position":7,"is_corresponding":false},{"id":949031,"name":"Fritz Gerald P. Kalaw","orcid":"0000-0002-3940-2272","position":8,"is_corresponding":false},{"id":1235107,"name":"Ines D. Nagel","orcid":"0000-0002-4649-6764","position":9,"is_corresponding":false},{"id":1235106,"name":"Akshay Agnihotri","orcid":"0009-0001-4624-8250","position":10,"is_corresponding":false},{"id":233337,"name":"Nehal N. Mehta","orcid":"0000-0003-4939-5130","position":11,"is_corresponding":false},{"id":1249978,"name":"Julian Klaas","orcid":"0000-0003-3207-4517","position":12,"is_corresponding":false},{"id":1249979,"name":"Valerie Schmelter","orcid":"0000-0001-6205-7668","position":13,"is_corresponding":false},{"id":54598,"name":"Igor Kozak","orcid":"0000-0003-1813-0017","position":14,"is_corresponding":false},{"id":349921,"name":"Sally L. Baxter","orcid":"0000-0002-5271-7690","position":15,"is_corresponding":false},{"id":139505,"name":"Dirk-Uwe Bartsch","orcid":null,"position":16,"is_corresponding":false},{"id":949034,"name":"Lingyun Cheng","orcid":"0000-0002-8156-5550","position":17,"is_corresponding":false},{"id":374355,"name":"Cheolhong An","orcid":"0000-0003-2821-7386","position":18,"is_corresponding":false},{"id":384835,"name":"Truong Q. Nguyen","orcid":"0000-0002-5022-063X","position":19,"is_corresponding":false},{"id":1250617,"name":"W. R. Freeman","orcid":null,"position":20,"is_corresponding":false},{"id":949032,"name":"Anna Heinke","orcid":"0000-0002-7115-8767","position":0,"is_corresponding":true}],"reference_count":19,"raw_metadata":{"citation_network_status":"fetched"},"created_at":"2026-07-19T02:00:47.992543Z","pmid":"39511248","pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}