{"id":"W2130880307","doi":"10.1109/42.974924","title":"Feature extraction and classification of dynamic contrast-enhanced T2*-weighted breast image data","year":2001,"lang":"en","type":"article","venue":"IEEE Transactions on Medical Imaging","topic":"MRI in cancer diagnosis","field":"Medicine","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Region of interest; Artificial intelligence; Computer science; Pixel; Pattern recognition (psychology); Breast imaging; Noise (video); Computer vision; Feature (linguistics); Feature extraction; Data set; Contrast (vision); Noise reduction; Mammography; Breast cancer; Image (mathematics); Medicine; Cancer","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":[],"consensus_categories":[],"category_scores_codex":[0.0003623235,0.0001952589,0.0003446297,0.0002141201,0.0001128153,0.00002624061,0.0002002424,0.0001520016,0.0007830733],"category_scores_gemma":[0.00004193131,0.0001790365,0.00006522947,0.0003700928,0.0003148446,0.0004264691,0.00000359462,0.0006836458,0.00002283159],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001336455,"about_ca_system_score_gemma":0.0001610813,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006390164,"about_ca_topic_score_gemma":0.00009262719,"domain_scores_codex":[0.9980929,0.00007219618,0.0003324019,0.0005245549,0.0007094933,0.0002684783],"domain_scores_gemma":[0.9984227,0.0002806267,0.000132575,0.0006817029,0.0001684901,0.0003139139],"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":[0.0004703362,0.0007000437,0.00064385,0.0001654359,0.0001261249,0.0000874457,0.0001258699,0.000004594264,0.2112841,0.000007994233,0.004453085,0.7819311],"study_design_scores_gemma":[0.01610235,0.0003928807,0.1285426,0.003991947,0.002159682,0.007563367,0.001758363,0.7330065,0.08990766,0.0001894636,0.01517401,0.001211101],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05543015,0.0003373252,0.8936097,0.04845213,0.0005902058,0.0004466498,0.0001548864,0.0001515479,0.0008274159],"genre_scores_gemma":[0.9918336,0.003613007,0.003514791,0.0005327818,0.000107374,0.00004315624,0.00008949698,0.00003628217,0.0002294984],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9364035,"threshold_uncertainty_score":0.8574103,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01961769740504659,"score_gpt":0.3323913412435437,"score_spread":0.3127736438384971,"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."}}