{"id":"W2145649715","doi":"10.1109/iembs.2008.4650554","title":"Measuring and evaluating ground truth for boundary detection in medical images","year":2008,"lang":"en","type":"article","venue":"","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta; Natural Sciences and Engineering Research Council of Canada","funders":"","keywords":"Ground truth; Boundary (topology); Computer science; Artificial intelligence; Process (computing); Computer vision; Interface (matter); Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017109,0.001631321,0.001634904,0.008673936,0.00112301,0.004109172,0.002741643,0.004226055,0.001937167],"category_scores_gemma":[0.08475627,0.0009694152,0.0009149392,0.00192649,0.002151094,0.003648462,0.002152793,0.001053705,0.001278432],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001180128,"about_ca_system_score_gemma":0.001302398,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001685973,"about_ca_topic_score_gemma":0.001927513,"domain_scores_codex":[0.9792068,0.007367069,0.001627584,0.003252961,0.00773344,0.0008121521],"domain_scores_gemma":[0.9368362,0.03703441,0.006036037,0.007991357,0.01117545,0.000926577],"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":[0.001745134,0.0004077436,0.02923545,0.002092892,0.0005687301,0.0006836025,0.002146562,0.06261966,0.1649526,0.0106247,0.00415546,0.7207675],"study_design_scores_gemma":[0.0002374095,0.002131276,0.03754725,0.0009975267,0.0005053894,0.004429004,0.001771929,0.5201417,0.3934315,0.02039193,0.0181183,0.0002968029],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09691653,0.00239711,0.8941954,0.0001680224,0.00009284425,0.0002255744,0.0002935674,0.004298866,0.001412015],"genre_scores_gemma":[0.4074737,0.0007588439,0.5886784,0.0001204399,0.00006527227,0.0001867805,0.001526424,0.000654432,0.0005357348],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.017109,"threshold_uncertainty_score":0.09048218,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08407120490181105,"score_gpt":0.3466606757328352,"score_spread":0.2625894708310241,"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."}}