{"id":"W2134916573","doi":"10.1109/42.887618","title":"Gradient and texture analysis for the classification of mammographic masses","year":2000,"lang":"en","type":"article","venue":"IEEE Transactions on Medical Imaging","topic":"AI in cancer detection","field":"Computer Science","cited_by":279,"is_retracted":false,"has_abstract":true,"ca_institutions":"Alberta Cancer Foundation; University of Calgary","funders":"","keywords":"Mahalanobis distance; Pixel; Artificial intelligence; Pattern recognition (psychology); Receiver operating characteristic; Texture (cosmology); Computer science; Contextual image classification; Database; Computer vision; Mathematics; Image (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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003300633,0.00008327237,0.0001198932,0.0002065731,0.0002102737,0.0000454797,0.0003040088,0.00004270211,0.0001080561],"category_scores_gemma":[0.000007944647,0.00006012299,0.0001287571,0.0009718856,0.0001647515,0.0001756732,0.000001044762,0.0001765586,0.000001814439],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002493786,"about_ca_system_score_gemma":0.00003324874,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005464925,"about_ca_topic_score_gemma":0.00007849546,"domain_scores_codex":[0.9990073,0.00004519121,0.0001965961,0.0002553758,0.0003559645,0.0001395428],"domain_scores_gemma":[0.9991637,0.0003378294,0.00005023499,0.0003210258,0.00004833897,0.00007882543],"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":[0.00001237218,0.00004712708,0.0002800419,0.0000120579,0.0001301352,7.153055e-7,0.000209326,0.002212367,0.0002452904,0.0002223643,0.00007234755,0.9965559],"study_design_scores_gemma":[0.0002799205,0.00003762457,0.008595789,0.00002415846,0.0002441475,0.0000144895,0.00008296714,0.9857851,0.001632729,0.0005363264,0.002669972,0.00009673773],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006969735,0.0002156161,0.9863822,0.005903526,0.0002333127,0.0001480565,0.00000465814,0.00006221955,0.00008071189],"genre_scores_gemma":[0.9959994,0.0003654467,0.003197796,0.0002745212,0.00002932012,0.00006771778,5.359273e-7,0.000005464917,0.00005982426],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9964591,"threshold_uncertainty_score":0.2451744,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01501128075316349,"score_gpt":0.2675426122484033,"score_spread":0.2525313314952398,"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."}}