{"id":"W3111816197","doi":"","title":"Fully automated segmentation algorithm for corneal nerves analysis from in-vivo UHR-OCT images","year":2019,"lang":"en","type":"article","venue":"Investigative Ophthalmology & Visual Science","topic":"Intraocular Surgery and Lenses","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Segmentation; Computer science; Ophthalmology; In vivo; Artificial intelligence; Computer vision; Medicine; Biology","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":[0.0008330749,0.0002240826,0.0005483497,0.0005588448,0.0001696186,0.00005152543,0.0002065854,0.000131688,0.0005730215],"category_scores_gemma":[0.0003963608,0.0001953023,0.0001575809,0.002091189,0.001664462,0.0004183371,0.00006726515,0.0001837373,0.0000598934],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001434242,"about_ca_system_score_gemma":0.000425517,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006159475,"about_ca_topic_score_gemma":0.000005348759,"domain_scores_codex":[0.9978055,0.0001583942,0.0003999257,0.000736038,0.0003897686,0.000510412],"domain_scores_gemma":[0.9985917,0.000449862,0.0002002055,0.000242794,0.0002950631,0.000220328],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0000651345,0.0001286633,0.2161214,0.00001382881,0.0001643821,0.0003165108,0.0005843593,0.00009472189,0.7816483,0.00002475597,0.00006627456,0.0007717278],"study_design_scores_gemma":[0.0006587862,0.0005954424,0.3757503,0.0000422282,0.0001862581,0.000104839,0.0004514742,0.04837553,0.5731597,0.000479015,0.00001047553,0.0001859484],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9979067,0.00006135937,0.000173879,0.0002340996,0.0003242232,0.00061997,0.00007726956,0.00009648767,0.0005060045],"genre_scores_gemma":[0.9781427,0.000002112775,0.02092555,0.0003280422,0.00006713604,0.00006406489,0.00009593822,0.00001346601,0.0003609264],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2084886,"threshold_uncertainty_score":0.7964197,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02726960634605733,"score_gpt":0.3469086801073936,"score_spread":0.3196390737613363,"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."}}