{"doi":"10.1101/2022.06.16.22276342","title":"Evaluation of OCT biomarker changes in treatment-naive neovascular AMD using a deep semantic segmentation algorithm","abstract":"<h4>Purpose</h4> To determine real life quantitative changes in OCT biomarkers in a large set of treatment naive patients undergoing anti-VEGF therapy. For this purpose, we devised a novel deep learning based semantic segmentation algorithm providing, to the best of our knowledge, the first benchmark results for automatic segmentation of 11 OCT features including biomarkers that are in line with the latest consensus nomenclature of the AAO for age-related macular degeneration (AMD). <h4>Design</h4> Retrospective study. <h4>Participants</h4> Segmentation algorithm training set of 458 volume scans as well as single scans from 363 treatment naive patients for the analysis. <h4>Methods</h4> Training of a Deep U-net based semantic segmentation ensemble algorithm leveraging multiple deep convolutional neural networks for state of the art semantic segmentation performance as well as analyzing OCT features prior to, after 3 and 12 months of anti-VEGF therapy. <h4>Main outcome measures</h4> F1 score for the segmentation efficiency and the quantified volumes of 11 OCT features. <h4>Results</h4> The segmentation algorithm achieved high F1 scores of almost 1.0 for neurosensory retina and subretinal fluid on a separate hold out test set with unseen patients. The algorithm performed worse for subretinal hyperreflective material and fibrovascular PED, on par with drusenoid PED and better in segmenting fibrosis. In the evaluation of treatment naive OCT scans, significant changes occurred for intraretinal fluid (mean: 0.03µm 3 to 0.01µm 3 , p<0.001), subretinal fluid (0.08µm 3 to 0.01µm 3 , p<0.001), subretinal hyperreflective material (0.02µm 3 to 0.01µm 3 , p<0.001), fibrovascular PED (0.12µm 3 to 0.09µm 3 , p=0.02) and central retinal thickness C0 (225.78µm 3 to 169.40µm 3 ).The amounts of intraretinal fluid, fibrovascular PED and ERM were predictive of poor outcome. <h4>Conclusions</h4> The segmentation algorithm allows efficient volumetric analysis of OCT scans. Anti-VEGF therapy provokes most potent changes in the first 3 months and afterwards only acts as a stabilizing agent. Furthermore, a gradual loss of RPE hints at a progressing decline of visual acuity even beyond month 12. Additional research is required to understand how these accurate OCT predictions can be leveraged for a personalized therapy regimen. <h4>Précis</h4> Novel high performance segmentation algorithm shows most volumetric changes under anti-VEGF therapy in oct biomarkers occur in the first 3 months. Afterwards the injections seem only to serve as a stabilizing agent.","journal":"medRxiv","year":2022,"id":1748,"datarank":0.2644929817955481,"base_score":1.6094379124341003,"endowment":1.6094379124341003,"self_citation_contribution":0.24141568686511508,"citation_network_contribution":0.02307729493043301,"self_endowment_contribution":0.24141568686511508,"citer_contribution":0.02307729493043301,"corpus_percentile":null,"corpus_rank":null,"citation_count":4,"citer_count":1,"citers_with_citation_signal":1,"citers_with_endowment":1,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.0517,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2022-06-17","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":19635,"name":"Olle G. Holmberg","orcid":"0000-0001-5558-7628","position":1,"is_corresponding":false},{"id":4591,"name":"Johannes B Schiefelbein","orcid":"0000-0001-5357-7469","position":2,"is_corresponding":false},{"id":19636,"name":"Michael Hafner","orcid":null,"position":3,"is_corresponding":false},{"id":19637,"name":"Tina Herold","orcid":"0000-0001-7422-1875","position":4,"is_corresponding":false},{"id":4584,"name":"Hannah Spitzer","orcid":"0000-0002-7858-0936","position":5,"is_corresponding":false},{"id":19638,"name":"Jakob Siedlecki","orcid":"0000-0002-0279-4823","position":6,"is_corresponding":false},{"id":19639,"name":"Christoph Kern","orcid":"0000-0002-9699-9255","position":7,"is_corresponding":false},{"id":19640,"name":"Karsten U. Kortuem","orcid":"0000-0001-9442-0708","position":8,"is_corresponding":false},{"id":4581,"name":"Amit Frishberg","orcid":"0000-0002-6912-9801","position":9,"is_corresponding":false},{"id":42,"name":"Fabian Joachim Theis","orcid":"0000-0002-2419-1943","position":10,"is_corresponding":false},{"id":4592,"name":"Siegfried G Priglinger","orcid":"0000-0002-5580-612X","position":11,"is_corresponding":false},{"id":19641,"name":"Michael Häfner","orcid":"0000-0002-2765-6689","position":12,"is_corresponding":false},{"id":4585,"name":"Ben Asani","orcid":"0000-0003-4809-2859","position":0,"is_corresponding":true}],"reference_count":54,"raw_metadata":{"citation_network_status":"fetched"},"created_at":"2026-03-01T18:20:47.508186Z","pmid":null,"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":[]}