{"id":"W2716665989","doi":"10.1038/s41598-017-04075-z","title":"Breast Cancer Multi-classification from Histopathological Images with Structured Deep Learning Model","year":2017,"lang":"en","type":"article","venue":"Scientific Reports","topic":"AI in cancer detection","field":"Computer Science","cited_by":675,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Project of Shandong Province Higher Educational Science and Technology Program; Natural Science Foundation of Shandong Province; National Natural Science Foundation of China","keywords":"Breast cancer; Artificial intelligence; Fibroadenoma; Cancer; Deep learning; Invasive lobular carcinoma; Lobular carcinoma; Computer science; Contextual image classification; Binary classification; Medicine; Pattern recognition (psychology); Ductal carcinoma; Pathology; Invasive ductal carcinoma; Support vector machine; Internal medicine; 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":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0005714305,0.0001672478,0.0001715871,0.0000873338,0.001559794,0.001449203,0.0007639187,0.00008833518,0.00003347974],"category_scores_gemma":[0.00006590615,0.0001306214,0.00005327461,0.0001501872,0.0004345268,0.001126788,0.0002563082,0.0002425145,0.000008997393],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002246927,"about_ca_system_score_gemma":0.0001791583,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000299176,"about_ca_topic_score_gemma":0.0002876357,"domain_scores_codex":[0.9975458,0.00005117765,0.0002893928,0.001266021,0.0005579707,0.0002896525],"domain_scores_gemma":[0.9968474,0.00001416318,0.0007533547,0.00199231,0.0002790788,0.0001136995],"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":[0.00005790553,0.0001511376,0.1417675,0.00002555094,0.0000430041,0.0008836477,0.002455272,0.06853153,0.2770345,0.0003748789,0.002039126,0.506636],"study_design_scores_gemma":[0.0002038763,0.00001669428,0.2894265,0.00003065098,0.00001574491,0.0004197874,0.0000275706,0.6952634,0.008583203,0.005161303,0.0005772293,0.000273942],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2276134,0.0001086887,0.7660797,0.0005380784,0.004808828,0.0001963489,0.000005012662,0.0002659968,0.0003839641],"genre_scores_gemma":[0.9356833,0.000006063542,0.06260211,0.0000145631,0.00008256962,0.00004768931,0.000007475314,0.00001229593,0.001543974],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7080699,"threshold_uncertainty_score":0.9997401,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03145578864690726,"score_gpt":0.2777013429502791,"score_spread":0.2462455543033718,"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."}}