{"id":"W4406810748","doi":"10.1080/02713683.2025.2456783","title":"Integrating Retinal Segmentation Metrics with Machine Learning for Predictions from Mouse SD-OCT Scans","year":2025,"lang":"en","type":"article","venue":"Current Eye Research","topic":"Retinal Imaging and Analysis","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Columbia College","funders":"National Eye Institute; Research to Prevent Blindness","keywords":"Retinal; Segmentation; Artificial intelligence; Ophthalmology; Optical coherence tomography; Computer science; Machine learning; Medicine","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001027983,0.000124404,0.0002376597,0.0008199111,0.0004516457,0.0001092983,0.0001171941,0.00004102364,0.00005402786],"category_scores_gemma":[0.001505332,0.00009318964,0.0001020587,0.001710812,0.0001191125,0.00008389266,0.0000581092,0.0009247119,0.00001107723],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002285184,"about_ca_system_score_gemma":0.000220765,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004849939,"about_ca_topic_score_gemma":0.00004419034,"domain_scores_codex":[0.9982075,0.0002058009,0.0002524035,0.0003600747,0.0006283494,0.0003458467],"domain_scores_gemma":[0.998397,0.0005220253,0.00006049518,0.0002146646,0.0006832168,0.0001225878],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007781331,0.0005431408,0.7935423,0.0006344292,0.0004872308,0.00001044438,0.0008950414,0.0005543457,0.02219023,0.0003980305,0.005923359,0.1740433],"study_design_scores_gemma":[0.005423882,0.001543756,0.02425363,0.00325009,0.001156406,0.000006719637,0.007318506,0.8892097,0.02508027,0.0004057448,0.04193832,0.0004129056],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5695788,0.00513288,0.4168144,0.003765642,0.0002109014,0.00118033,0.0001088515,0.0002072253,0.003000957],"genre_scores_gemma":[0.9845198,0.0005557411,0.006527571,0.00002030114,0.0002223208,0.0001662557,0.0008406307,0.00002500378,0.00712237],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8886554,"threshold_uncertainty_score":0.4017465,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08464067170816143,"score_gpt":0.4566789162108286,"score_spread":0.3720382445026671,"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."}}