{"doi":"10.1101/861757","title":"Self-supervised retinal thickness prediction enables deep learning from unlabeled data to boost classification of diabetic retinopathy","abstract":"Access to large, annotated samples represents a considerable challenge for training accurate deep-learning models in medical imaging. While current leading-edge transfer learning from pre-trained models can help with cases lacking data, it limits design choices, and generally results in the use of unnecessarily large models. We propose a novel, self-supervised training scheme for obtaining high-quality, pre-trained networks from unlabeled, cross-modal medical imaging data, which will allow for creating accurate and efficient models. We demonstrate this by accurately predicting optical coherence tomography (OCT)-based retinal thickness measurements from simple infrared (IR) fundus images. Subsequently, learned representations outperformed advanced classifiers on a separate diabetic retinopathy classification task in a scenario of scarce training data. Our cross-modal, three-staged scheme effectively replaced 26,343 diabetic retinopathy annotations with 1,009 semantic segmentations on OCT and reached the same classification accuracy using only 25% of fundus images, without any drawbacks, since OCT is not required for predictions. We expect this concept will also apply to other multimodal clinical data-imaging, health records, and genomics data, and be applicable to corresponding sample-starved learning problems.","journal":"bioRxiv (Cold Spring Harbor Laboratory)","year":2019,"id":3500,"datarank":0.16479184330021646,"base_score":1.0986122886681096,"endowment":1.0986122886681096,"self_citation_contribution":0.16479184330021646,"citation_network_contribution":0.0,"self_endowment_contribution":0.16479184330021646,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":2,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.0432,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2019-12-02","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":20758,"name":"Niklas D. Köhler","orcid":"0000-0003-2726-0518","position":1,"is_corresponding":false},{"id":21613,"name":"Thiago Gonçalves dos Santos Martins","orcid":"0000-0002-3878-8564","position":2,"is_corresponding":false},{"id":19638,"name":"Jakob Siedlecki","orcid":"0000-0002-0279-4823","position":3,"is_corresponding":false},{"id":19637,"name":"Tina Herold","orcid":"0000-0001-7422-1875","position":4,"is_corresponding":false},{"id":21614,"name":"Leonie Keidel","orcid":"0000-0003-4144-5754","position":5,"is_corresponding":false},{"id":4585,"name":"Ben Asani","orcid":"0000-0003-4809-2859","position":6,"is_corresponding":false},{"id":4591,"name":"Johannes B Schiefelbein","orcid":"0000-0001-5357-7469","position":7,"is_corresponding":false},{"id":4592,"name":"Siegfried G Priglinger","orcid":"0000-0002-5580-612X","position":8,"is_corresponding":false},{"id":19640,"name":"Karsten U. Kortuem","orcid":"0000-0001-9442-0708","position":9,"is_corresponding":false},{"id":42,"name":"Fabian Joachim Theis","orcid":"0000-0002-2419-1943","position":10,"is_corresponding":false},{"id":19635,"name":"Olle G. Holmberg","orcid":"0000-0001-5558-7628","position":0,"is_corresponding":true}],"reference_count":41,"raw_metadata":null,"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":[]}