{"id":"W2954679106","doi":"10.59275/j.melba.2021-gfgg","title":"PathologyGAN: Learning deep representations of cancer tissue","year":2021,"lang":"en","type":"preprint","venue":"The Journal of Machine Learning for Biomedical Imaging","topic":"AI in cancer detection","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council; University of Glasgow","keywords":"Artificial intelligence; Cancer; Computer science; Breast cancer; Colorectal cancer; Deep learning; Feature (linguistics); Feature vector; Pattern recognition (psychology); Stromal cell; Machine learning; Medicine; Pathology; Internal medicine","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.0005291167,0.001006863,0.0004450646,0.0005675112,0.0001631696,0.0006408741,0.001469102,0.001174715,0.002150741],"category_scores_gemma":[0.001414396,0.0004704845,0.0008220526,0.0004580733,0.0004118941,0.0007717362,0.0007867306,0.001468307,0.0008564239],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008870744,"about_ca_system_score_gemma":0.0006828399,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005763921,"about_ca_topic_score_gemma":0.007961803,"domain_scores_codex":[0.9998249,0.00003995367,0.00000551868,0.00005579934,0.00004117902,0.00003269231],"domain_scores_gemma":[0.9997057,0.0001236187,0.00003400055,0.00005904819,0.00005291148,0.00002467928],"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":[0.0002248779,0.000160857,0.003607997,0.000147917,0.0001890091,0.0001788598,0.00006453774,0.8008083,0.0123056,0.005041827,0.01596143,0.1613089],"study_design_scores_gemma":[0.000007637248,0.00002757117,0.0002958961,0.00000805873,0.00000820545,0.00003543285,0.00000523559,0.9944702,0.00176625,0.002579236,0.0007904037,0.000005760677],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09678038,0.001512643,0.8857005,0.001040832,0.0002257685,0.0001387567,0.003271959,0.007852297,0.003476891],"genre_scores_gemma":[0.7604912,0.001008429,0.2140582,0.001261024,0.0001215655,0.0003506178,0.01144278,0.0005049367,0.01076137],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005763921,"threshold_uncertainty_score":0.01146072,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01430746497485931,"score_gpt":0.3381544727428638,"score_spread":0.3238470077680045,"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."}}