{"id":"W2161791887","doi":"10.1109/tmi.2010.2076828","title":"Detection of Architectural Distortion in Prior Mammograms","year":2010,"lang":"en","type":"article","venue":"IEEE Transactions on Medical Imaging","topic":"AI in cancer detection","field":"Computer Science","cited_by":80,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"Health Research Board","keywords":"Artificial intelligence; Pattern recognition (psychology); Linear discriminant analysis; Receiver operating characteristic; Fractal dimension; Mathematics; Feature extraction; Entropy (arrow of time); False positive paradox; Computer science; Computer vision; Fractal; Statistics; Physics","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":[0.0003962411,0.0001182989,0.000139621,0.0003120964,0.00009798305,0.00003161288,0.0003813757,0.00008684266,0.00005039176],"category_scores_gemma":[0.00003410078,0.0001144718,0.00008559101,0.0005651513,0.0001461815,0.0003291981,0.000003333035,0.0008652707,0.00001186619],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009222453,"about_ca_system_score_gemma":0.00007577271,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002908015,"about_ca_topic_score_gemma":0.001333396,"domain_scores_codex":[0.9984936,0.00006345913,0.0003240567,0.0003171084,0.0005682557,0.0002335866],"domain_scores_gemma":[0.9992773,0.0001161569,0.00008107684,0.0003493281,0.00004405146,0.0001320871],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001603164,0.00007759752,0.0001091688,0.00001188058,0.000003966529,0.000007283774,0.0002145181,0.0003901772,0.04000333,0.00002215427,0.000001558101,0.9591423],"study_design_scores_gemma":[0.00124768,0.0001436756,0.008093824,0.0001286719,0.00001556715,0.0002957489,0.0000553906,0.4331084,0.5549779,0.001090521,0.00049999,0.0003426316],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2248511,0.00001107691,0.771951,0.0006714109,0.002207251,0.0001074184,7.797801e-7,0.0001271856,0.00007275791],"genre_scores_gemma":[0.9955639,0.000007433258,0.004179695,0.000113284,0.00006920299,0.00003714737,2.467547e-7,0.00001080986,0.00001823575],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9587997,"threshold_uncertainty_score":0.4668025,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006442996723981957,"score_gpt":0.249130156024909,"score_spread":0.2426871593009271,"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."}}