{"id":"W2908676718","doi":"10.3166/ts.35.121-136","title":"Automatic ranking of image thresholding techniques using consensus of ground truth","year":2018,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Thresholding; Ground truth; Ranking (information retrieval); Artificial intelligence; Image (mathematics); Pattern recognition (psychology); Computer science; Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008920998,0.0001448612,0.0002787144,0.0002233001,0.00007903603,0.00005486378,0.0005424602,0.00004988663,0.0003289882],"category_scores_gemma":[0.00007891175,0.0001342315,0.00006992109,0.0004151041,0.000411984,0.0003079668,0.0001516884,0.00008123842,0.000002375476],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005383022,"about_ca_system_score_gemma":0.000083987,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005345287,"about_ca_topic_score_gemma":0.00000121979,"domain_scores_codex":[0.9981832,0.0001108416,0.0006633258,0.0002582953,0.0005568771,0.0002274678],"domain_scores_gemma":[0.9987695,0.0001955537,0.0003902849,0.0003034996,0.0002743814,0.00006682026],"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":[0.00001105344,0.0001251327,0.0001364561,0.0001489883,0.00004031373,0.00001058617,0.001210557,0.00000170083,0.8947529,0.004782778,0.0003095592,0.09846994],"study_design_scores_gemma":[0.0003394197,0.0002599341,0.0003451314,0.0002509659,0.0000210541,0.00001579796,0.00007382537,0.07924103,0.916812,0.002497124,0.00001103723,0.0001326789],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2401079,0.00001870914,0.7587071,0.00004302886,0.00006735988,0.0002543749,0.000003100833,0.0002288167,0.0005696113],"genre_scores_gemma":[0.5586017,0.000001491386,0.4412632,0.00007576818,0.0000419817,0.000006258285,9.062426e-7,0.000006777188,0.000001957418],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.3184938,"threshold_uncertainty_score":0.5473802,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03314039487924562,"score_gpt":0.3086935162337058,"score_spread":0.2755531213544602,"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."}}