{"id":"W4391069929","doi":"10.1007/978-3-031-50075-6_33","title":"Exploring the Transferability of a Foundation Model for Fundus Images: Application to Hypertensive Retinopathy","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"DiagnoCure (Canada); École de Technologie Supérieure","funders":"","keywords":"Computer science; Initialization; Artificial intelligence; Deep learning; Transferability; Fundus (uterus); Machine learning; Transfer of learning; Fluid-attenuated inversion recovery; Contextual image classification; Classifier (UML); Pattern recognition (psychology); Image (mathematics); Magnetic resonance imaging; Ophthalmology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001275083,0.0004361217,0.0005640204,0.0006027897,0.0004086325,0.001313193,0.0008385046,0.001089621,0.003016584],"category_scores_gemma":[0.007620409,0.0003984143,0.000954754,0.0005487357,0.000792208,0.001869012,0.001296945,0.001315753,0.0002139765],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001080841,"about_ca_system_score_gemma":0.0008319463,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009166405,"about_ca_topic_score_gemma":0.004192693,"domain_scores_codex":[0.999768,0.00009108816,0.000009429117,0.00004462675,0.00005070796,0.00003629451],"domain_scores_gemma":[0.9961229,0.002990757,0.0002403899,0.0002718055,0.00024545,0.0001287575],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003811725,0.000193738,0.004036279,0.0001488949,0.00006282306,0.0004025262,0.0004086725,0.7368053,0.01241088,0.1534315,0.002090903,0.08962731],"study_design_scores_gemma":[0.000005843649,0.00002907488,0.0004022524,0.000005928738,0.000006099379,0.00003170667,0.00003056025,0.9752273,0.000460467,0.02358738,0.0002088219,0.000004525318],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2474803,0.0002370027,0.7460923,0.0005250538,0.00002537628,0.00004643707,0.0001824574,0.0003228591,0.005088273],"genre_scores_gemma":[0.9097935,0.0002931493,0.08600494,0.00005459975,0.00003143355,0.0000385147,0.0002558347,0.0001343156,0.003393731],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009166405,"threshold_uncertainty_score":0.01822615,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06709629298375425,"score_gpt":0.2957001497692471,"score_spread":0.2286038567854928,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}