{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004024099,0.0001474782,0.0002627298,0.0001783948,0.00006165501,0.00005013023,0.00006073848,0.0000707401,0.00007018181],"category_scores_gemma":[0.0001198534,0.0001324819,0.0001341668,0.0002414974,0.00006816961,0.0001729139,0.0000241641,0.0001374804,0.000008246033],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003722894,"about_ca_system_score_gemma":0.00005330917,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003241005,"about_ca_topic_score_gemma":0.000002344685,"domain_scores_codex":[0.9987801,0.00005854891,0.0003088824,0.0003019208,0.0002874841,0.0002630695],"domain_scores_gemma":[0.9991571,0.0004332599,0.00005986524,0.0001233113,0.00007189851,0.0001545542],"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":[0.006643028,0.0008842645,0.07800315,0.0002824881,0.00009078302,0.00006688662,0.0007683077,0.00143618,0.8050311,0.00008865108,0.09335878,0.01334637],"study_design_scores_gemma":[0.08630877,0.003189513,0.06288474,0.0006372515,0.0004104634,0.000110763,0.006202068,0.0749068,0.7602197,0.0006825706,0.002687631,0.001759773],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9167888,0.00008868258,0.07823207,0.002914416,0.000153647,0.001076118,0.00002594287,0.00005531191,0.0006649834],"genre_scores_gemma":[0.9788153,0.000005033839,0.0154011,0.005133366,0.00008618145,0.0001691353,0.0003404607,0.00001447725,0.00003498441],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09067116,"threshold_uncertainty_score":0.5402455,"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."}}