{"id":"W2844479918","doi":"10.1016/j.semcancer.2018.07.001","title":"Scoring of tumor-infiltrating lymphocytes: From visual estimation to machine learning","year":2018,"lang":"en","type":"review","venue":"Seminars in Cancer Biology","topic":"Cancer Immunotherapy and Biomarkers","field":"Medicine","cited_by":166,"is_retracted":false,"has_abstract":false,"ca_institutions":"Vector Institute; Princess Margaret Cancer Centre; University Health Network; University of Toronto; Ontario Institute for Cancer Research; McGill University; University of British Columbia","funders":"Institute for Information and Communications Technology Promotion; Deutschen Konsortium für Translationale Krebsforschung; Berlin Center for Machine Learning; Deutsche Forschungsgemeinschaft; National Research Foundation; Banting and Best Diabetes Centre, University of Toronto; National Research Foundation of Korea; World Health Organization; Ministry of Science and ICT, South Korea; Breast Cancer Research Foundation","keywords":"Machine learning; Artificial intelligence; Computer science; Tumor-infiltrating lymphocytes; Standardization; Segmentation; Cancer; Medicine; Immunotherapy","routes":{"ca_aff":true,"ca_fund":true,"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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004310509,0.0003635956,0.001648415,0.0003737691,0.00004880818,0.000008742718,0.0001853201,0.0003141664,0.0002894546],"category_scores_gemma":[0.0002184293,0.0003018547,0.0002525705,0.0005651063,0.0001516519,0.00003173117,0.00008887738,0.0003568835,0.00001574474],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008329406,"about_ca_system_score_gemma":0.0006959586,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004083268,"about_ca_topic_score_gemma":0.0003080229,"domain_scores_codex":[0.9979191,0.0001757229,0.0008998338,0.0005421177,0.0001256778,0.0003374942],"domain_scores_gemma":[0.9987405,0.0003151928,0.0005518833,0.0002603713,0.00005893547,0.00007312226],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003205182,0.00003497437,0.002158527,0.003018604,0.0001931361,0.00001105254,0.0002265715,0.000008511338,0.0006611685,0.000002247261,0.00008994447,0.9932747],"study_design_scores_gemma":[0.001351377,0.001542416,0.0001557993,0.103441,0.0005006572,0.00007594097,0.00008654453,0.0006664867,0.001138179,0.00002222809,0.8904933,0.0005260484],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.007165326,0.9910426,0.0001053853,0.0000251355,0.0006787039,0.0006460788,0.0001106089,0.00003557726,0.0001906589],"genre_scores_gemma":[0.001064643,0.9953529,0.002294275,0.0001418987,0.0004336834,0.0001805669,0.0003783435,0.00005449351,0.00009917742],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9927487,"threshold_uncertainty_score":0.9999434,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04520917337671387,"score_gpt":0.404199645825318,"score_spread":0.3589904724486041,"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."}}