{"id":"W4403947353","doi":"10.18280/mmep.111024","title":"A Retinal Fundus Image Segmentation Approach Based on the Segment Anything Model","year":2024,"lang":"en","type":"article","venue":"Mathematical Modelling and Engineering Problems","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Fundus (uterus); Segmentation; Artificial intelligence; Computer science; Retinal; Computer vision; Image segmentation; Image (mathematics); Ophthalmology; Optometry; Medicine","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038919,0.0005245776,0.000949649,0.0008145114,0.0005100758,0.001153904,0.0009923172,0.00138485,0.001354562],"category_scores_gemma":[0.0005758335,0.0004738004,0.001459985,0.0006229054,0.0005292433,0.0008781909,0.0008050462,0.0008989259,0.000580207],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008402266,"about_ca_system_score_gemma":0.0009195691,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005325723,"about_ca_topic_score_gemma":0.003743866,"domain_scores_codex":[0.9998118,0.0000341147,0.000009799495,0.00006637012,0.0000572649,0.00002072686],"domain_scores_gemma":[0.9998542,0.00004598997,0.0000229253,0.00002078017,0.00004019458,0.00001593646],"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":[0.000274027,0.0000936932,0.001698878,0.0002535008,0.000197504,0.0005016598,0.000344218,0.5881519,0.09813096,0.09902058,0.003341488,0.2079917],"study_design_scores_gemma":[0.000003922098,0.00003122117,0.0001937575,0.000007622243,0.00002387889,0.00008712844,0.00001031472,0.9892854,0.002721791,0.00622061,0.001402046,0.00001228143],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007035248,0.0002245171,0.9912685,0.0001566886,0.00002638711,0.00001937572,0.00003196884,0.0001764293,0.001060737],"genre_scores_gemma":[0.4229087,0.001266657,0.5632237,0.0002165688,0.0001547166,0.0001636042,0.0003708777,0.000355236,0.01133988],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005325723,"threshold_uncertainty_score":0.01058948,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03236514773684422,"score_gpt":0.2487979911600582,"score_spread":0.2164328434232139,"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."}}