{"id":"W4385059574","doi":"10.2196/45547","title":"Data-Efficient Computational Pathology Platform for Faster and Cheaper Breast Cancer Subtype Identifications: Development of a Deep Learning Model","year":2023,"lang":"en","type":"article","venue":"JMIR Cancer","topic":"AI in cancer detection","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Medical Research Council; Medical Research Council; Korea Health Industry Development Institute; National Research Foundation Singapore; National Research Foundation","keywords":"Breast cancer; Computer science; Deep learning; Artificial intelligence; Pathology; Medicine; Computational biology; Cancer; Internal medicine; Biology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007626914,0.0006747529,0.0005114185,0.000751408,0.0002578916,0.0005962921,0.001218724,0.0006368218,0.001680997],"category_scores_gemma":[0.001896142,0.0003675726,0.0007815054,0.0005492708,0.0002523082,0.0009084109,0.00109444,0.0008991769,0.0006322625],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006721751,"about_ca_system_score_gemma":0.001160217,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006125904,"about_ca_topic_score_gemma":0.006806593,"domain_scores_codex":[0.9997963,0.00004028339,0.00001965498,0.00006111847,0.00005698008,0.00002567174],"domain_scores_gemma":[0.9995162,0.0001623122,0.00004455939,0.0000667664,0.0001760574,0.0000339514],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002628059,0.0002866364,0.01499759,0.0001325533,0.0001699494,0.0003064262,0.00008874036,0.5565022,0.01509479,0.003991373,0.008069937,0.400097],"study_design_scores_gemma":[0.000007303297,0.00002703268,0.0005745918,0.000004711695,0.00001120496,0.00003470763,0.00000877231,0.9956655,0.001708199,0.001300683,0.0006512475,0.000006114722],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07775002,0.0003557692,0.9163058,0.0006658936,0.0001064458,0.0001576168,0.0007394113,0.002551743,0.001367339],"genre_scores_gemma":[0.5454202,0.0005292855,0.4466365,0.0004792797,0.00008043463,0.0004454169,0.002657149,0.0001345374,0.00361705],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006125904,"threshold_uncertainty_score":0.01218051,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06940561362447524,"score_gpt":0.3424887587235138,"score_spread":0.2730831450990385,"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."}}