{"id":"W2692662121","doi":"10.15353/vsnl.v1i1.48","title":"A Conditional Random Field Weakly Supervised Segmentation Approach for Segmenting keratocytes Cells in Corneal Optical Coherence Tomography Images","year":2015,"lang":"en","type":"article","venue":"Vision Letters","topic":"Corneal surgery and disorders","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Conditional random field; Segmentation; Optical coherence tomography; Artificial intelligence; Cornea; Pattern recognition (psychology); Computer science; Coherence (philosophical gambling strategy); Image segmentation; Computer vision; Mathematics; Ophthalmology; Medicine; Statistics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"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":[0.0007387418,0.0005684816,0.000805606,0.0009990118,0.0003520259,0.0005568725,0.001156372,0.0009887199,0.00109998],"category_scores_gemma":[0.001192161,0.0004254194,0.001054698,0.0006678772,0.0006255986,0.0008290156,0.0006063079,0.0007789811,0.000503493],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005538432,"about_ca_system_score_gemma":0.001406369,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007608281,"about_ca_topic_score_gemma":0.01115331,"domain_scores_codex":[0.9995554,0.0001008949,0.00002672611,0.0001464181,0.0001123606,0.00005819588],"domain_scores_gemma":[0.9994171,0.000184363,0.00008246302,0.0000973248,0.0001716513,0.00004710963],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005644456,0.000192793,0.002902798,0.000258524,0.0001272727,0.0002986176,0.0002785199,0.3659612,0.115467,0.008111504,0.007762734,0.4980746],"study_design_scores_gemma":[0.000008173519,0.00003394343,0.0004977669,0.000005402268,0.0000129689,0.00006429615,0.00001157184,0.9913952,0.005948268,0.001314013,0.0006974933,0.00001095652],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0243086,0.0001953266,0.9735066,0.0001357861,0.00002321512,0.00005472569,0.0001255384,0.001058798,0.0005914447],"genre_scores_gemma":[0.3749794,0.0003815956,0.6175128,0.0002951714,0.0001126161,0.0001783346,0.001432049,0.0003058673,0.004802294],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007608281,"threshold_uncertainty_score":0.01512802,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0215562377996501,"score_gpt":0.2753189951504887,"score_spread":0.2537627573508386,"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."}}