{"id":"W4200030210","doi":"10.1109/embc46164.2021.9629944","title":"XAI Feature Detector for Ultrasound Feature Matching","year":2021,"lang":"en","type":"article","venue":"2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Interpretability; Computer science; Artificial intelligence; Feature extraction; Robustness (evolution); Pattern recognition (psychology); Feature (linguistics); Matching (statistics); Artificial neural network; Computer vision; Field (mathematics); 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":[0.0006059117,0.0005548098,0.0006308676,0.001365402,0.000250027,0.0005957666,0.001022007,0.0009717845,0.003111631],"category_scores_gemma":[0.001518358,0.0003124353,0.0006184903,0.000935343,0.000345193,0.0009860054,0.0008602226,0.0009445935,0.001172625],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005276989,"about_ca_system_score_gemma":0.0005528195,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008213866,"about_ca_topic_score_gemma":0.001108089,"domain_scores_codex":[0.999563,0.00005500824,0.00002218206,0.00009850613,0.0002083421,0.00005294633],"domain_scores_gemma":[0.9996705,0.00008502591,0.00004578941,0.00005620234,0.0001214425,0.00002102713],"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":[0.0002658048,0.00008653136,0.002522165,0.0001474348,0.00008288501,0.0002299428,0.00005776745,0.02550801,0.1382496,0.01112343,0.007993899,0.8137325],"study_design_scores_gemma":[0.00002066731,0.0001231316,0.002900186,0.00001402593,0.00004514551,0.0006686384,0.00002207901,0.901947,0.08164053,0.004970223,0.007619465,0.00002902428],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009224994,0.00030561,0.9878861,0.0001753871,0.00005754576,0.00005770085,0.0001032221,0.001048005,0.00114139],"genre_scores_gemma":[0.272656,0.0005534659,0.7200987,0.0004497179,0.0001213401,0.0001902138,0.0006481468,0.0001884354,0.005094065],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003111631,"threshold_uncertainty_score":0.01040941,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02912065508957762,"score_gpt":0.3175837320850083,"score_spread":0.2884630769954307,"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."}}