{"doi":"10.1016/j.xops.2024.100587","title":"Estimating Uncertainty of Geographic Atrophy Segmentations with Bayesian Deep Learning","abstract":"Purpose: To apply methods for quantifying uncertainty of deep learning segmentation of geographic atrophy (GA). Design: Retrospective analysis of OCT images and model comparison. Participants: One hundred twenty-six eyes from 87 participants with GA in the SWAGGER cohort of the Nonexudative Age-Related Macular Degeneration Imaged with Swept-Source OCT (SS-OCT) study. Methods: The manual segmentations of GA lesions were conducted on structural subretinal pigment epithelium en face images from the SS-OCT images. Models were developed for 2 approximate Bayesian deep learning techniques, Monte Carlo dropout and ensemble, to assess the uncertainty of GA semantic segmentation and compared to a traditional deep learning model. Main Outcome Measures: Model performance (Dice score) was compared. Uncertainty was calculated using the formula for Shannon Entropy. Results: < 0.001) than for the traditional model (0.82, 95% confidence interval 0.78-0.86). Conclusions: Quantifying the uncertainty in a prediction of GA may improve trustworthiness of the models and aid clinicians in decision-making. The Bayesian deep learning techniques generated pixel-wise estimates of model uncertainty for segmentation, while also improving model performance compared with traditionally trained deep learning models. Financial Disclosures: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.","journal":"Ophthalmology Science","year":2024,"id":468660,"datarank":0.0,"base_score":0.0,"endowment":0.0,"self_citation_contribution":0.0,"citation_network_contribution":0.0,"self_endowment_contribution":0.0,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":3,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.7132,"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":1018089,"name":"Anand E. Rajesh","orcid":"0000-0002-1120-2869","position":1,"is_corresponding":false},{"id":1218166,"name":"Nayoon Gim","orcid":"0000-0001-6169-7452","position":2,"is_corresponding":false},{"id":425622,"name":"Marian Blazes","orcid":"0000-0001-7401-5238","position":3,"is_corresponding":false},{"id":107569,"name":"Cecilia S. Lee","orcid":"0000-0003-1994-7213","position":4,"is_corresponding":false},{"id":1302157,"name":"Niranchana Macivannan","orcid":null,"position":5,"is_corresponding":false},{"id":638024,"name":"Gary Lee","orcid":"0000-0002-0036-511X","position":6,"is_corresponding":false},{"id":1135312,"name":"Warren Lewis","orcid":null,"position":7,"is_corresponding":false},{"id":1301717,"name":"Ali Salehi","orcid":"0009-0006-6792-295X","position":8,"is_corresponding":false},{"id":306437,"name":"Luís de Sisternes","orcid":null,"position":9,"is_corresponding":false},{"id":1227522,"name":"Gissel Herrera","orcid":"0009-0003-5105-0702","position":10,"is_corresponding":false},{"id":687992,"name":"Mengxi Shen","orcid":"0000-0002-1336-1695","position":11,"is_corresponding":false},{"id":304780,"name":"Giovanni Gregori","orcid":"0000-0003-0951-2216","position":12,"is_corresponding":false},{"id":304779,"name":"Philip J. Rosenfeld","orcid":"0000-0002-4068-6671","position":13,"is_corresponding":false},{"id":436742,"name":"Varsha Pramil","orcid":null,"position":14,"is_corresponding":false},{"id":326978,"name":"Nadia K. Waheed","orcid":"0000-0002-8229-7519","position":15,"is_corresponding":false},{"id":830908,"name":"Yue Wu","orcid":"0000-0002-2917-5862","position":16,"is_corresponding":false},{"id":1227524,"name":"Qinqin Zhang","orcid":"0000-0002-3925-3211","position":17,"is_corresponding":false},{"id":86323,"name":"Aaron Lee","orcid":"0000-0002-7452-1648","position":18,"is_corresponding":false},{"id":667210,"name":"Theodore Spaide","orcid":null,"position":0,"is_corresponding":true}],"reference_count":30,"raw_metadata":null,"created_at":"2026-07-19T02:05:23.500722Z","pmid":"39380882","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":[]}