{"id":"W2128089874","doi":"10.1109/tpami.2002.1114849","title":"Flux maximizing geometric flows","year":2002,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":381,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; IBM (Canada)","funders":"","keywords":"Image segmentation; Surface (topology); Artificial intelligence; Segmentation; Computer science; Computer vision; Image (mathematics); Set (abstract data type); Field (mathematics); Level set (data structures); Algorithm; Mathematics; Geometry","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000238295,0.0001870281,0.0002636802,0.001184695,0.0001784571,0.0001798895,0.0005123276,0.00005821939,0.001965019],"category_scores_gemma":[0.00001070763,0.0001645546,0.0002022097,0.002658902,0.00005070153,0.0003335929,0.00000698269,0.0002636751,0.0001584049],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003441811,"about_ca_system_score_gemma":0.000004764692,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003076131,"about_ca_topic_score_gemma":0.0001042139,"domain_scores_codex":[0.9984162,0.00008010031,0.0003806747,0.0004941318,0.0003906438,0.000238255],"domain_scores_gemma":[0.9990171,0.0001487192,0.00008713129,0.0005077167,0.00006066849,0.000178695],"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":[8.705039e-7,0.0001138881,0.00005771604,0.000007362557,0.0001542098,0.00001751933,0.0001618643,0.001367559,0.0003301863,0.00001011162,0.00005949083,0.9977192],"study_design_scores_gemma":[0.00007903705,0.0001102522,0.0001605555,0.00001522201,0.0002172352,0.00002620487,0.00002161122,0.6034791,0.39543,0.0001103343,0.00008559113,0.0002648119],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0004196829,0.0001698211,0.9983094,0.0003918599,0.0001353369,0.0001048747,0.00001007018,0.0002185459,0.0002404634],"genre_scores_gemma":[0.9651566,0.0006002423,0.0327182,0.0007773532,0.00001410376,0.00002602637,0.000002396356,0.000009025449,0.0006960155],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9974544,"threshold_uncertainty_score":0.9989473,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03171995903845451,"score_gpt":0.2775371475731147,"score_spread":0.2458171885346601,"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."}}