{"id":"W2587010042","doi":"10.1038/srep42112","title":"Open-source algorithm for automatic choroid segmentation of OCT volume reconstructions","year":2017,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Retinal Diseases and Treatments","field":"Medicine","cited_by":69,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Hôpital Maisonneuve-Rosemont","funders":"Fonds de Recherche du Québec - Santé; Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research","keywords":"Volume (thermodynamics); Computer science; Segmentation; Choroid; Artificial intelligence; Computer vision; Algorithm; Biology; Retina; Physics; Neuroscience","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0004129555,0.00009107182,0.0002225204,0.00007738989,0.0006130641,0.0003067813,0.0001403267,0.00003287856,0.0002358591],"category_scores_gemma":[0.000179698,0.00007625913,0.0001311385,0.00007018497,0.000241531,0.0002779174,0.00008760869,0.00003075018,0.00001535635],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005064442,"about_ca_system_score_gemma":0.0001774383,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001066082,"about_ca_topic_score_gemma":0.000006202326,"domain_scores_codex":[0.998785,0.00001204618,0.0003863617,0.0004044232,0.0002557107,0.00015646],"domain_scores_gemma":[0.9980627,0.00001226461,0.0006050946,0.0009787572,0.0002098906,0.0001313287],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00002368396,0.0003740123,0.07785779,0.0001367178,0.0001528363,0.0001309652,0.0001193035,0.00000353322,0.00372385,0.00001725112,0.01578901,0.9016711],"study_design_scores_gemma":[0.006219725,0.001088694,0.8164144,0.001179146,0.001907976,0.003876884,0.0008991918,0.03639675,0.04937671,0.01328376,0.06868276,0.000674019],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9837238,0.0001388068,0.004894896,0.0003245779,0.004371068,0.002053154,0.00003910772,0.00005138211,0.004403264],"genre_scores_gemma":[0.8933011,0.000008367729,0.0590416,0.00002263153,0.00009220283,0.0001956249,0.0003136414,0.00002618084,0.0469986],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.900997,"threshold_uncertainty_score":0.4715255,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02672024559607693,"score_gpt":0.3348350797768869,"score_spread":0.30811483418081,"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."}}