{"id":"W1968855805","doi":"10.1117/12.2081637","title":"Bright-field cell image segmentation by principal component pursuit with an Ncut penalization","year":2015,"lang":"en","type":"article","venue":"Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"McGill University","keywords":"Segmentation; Artificial intelligence; Scale-space segmentation; Image segmentation; Background subtraction; Computer science; Computer vision; Segmentation-based object categorization; Pattern recognition (psychology); Pixel; Principal component analysis; Field (mathematics); Robust principal component analysis; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007605304,0.0007506934,0.0006881203,0.0007257292,0.0003357324,0.0007925939,0.0008097844,0.001098304,0.0006925522],"category_scores_gemma":[0.001349616,0.0004830173,0.0007567057,0.0007244684,0.000850569,0.0007712142,0.0008600291,0.001000739,0.0003712918],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009302921,"about_ca_system_score_gemma":0.001574451,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005478456,"about_ca_topic_score_gemma":0.004998809,"domain_scores_codex":[0.9995899,0.00009954438,0.00001748364,0.0000882224,0.0001666959,0.00003821128],"domain_scores_gemma":[0.9995738,0.0001786958,0.00007099829,0.00005053096,0.0001007695,0.000025199],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001854407,0.00009222445,0.0008082712,0.0001388645,0.00005550673,0.0001178233,0.0001268482,0.764505,0.06521888,0.0177896,0.002417323,0.1485442],"study_design_scores_gemma":[0.000002282381,0.000009439505,0.00007168159,0.00000166608,0.000001970622,0.00001048861,0.000002559082,0.9962812,0.002538537,0.0007582025,0.0003182385,0.000003633504],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008685561,0.00006845457,0.9904614,0.00009013729,0.00000821373,0.00001948151,0.00001967271,0.0002232609,0.0004238075],"genre_scores_gemma":[0.204829,0.0002999587,0.7912018,0.0001110131,0.00003020952,0.0001570296,0.0002520643,0.0001705401,0.00294839],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005478456,"threshold_uncertainty_score":0.01089311,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007633477196876765,"score_gpt":0.2378452883491246,"score_spread":0.2302118111522478,"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."}}