{"id":"W2949003314","doi":"10.1155/2019/3041250","title":"Direct Cellularity Estimation on Breast Cancer Histopathology Images Using Transfer Learning","year":2019,"lang":"en","type":"article","venue":"Computational and Mathematical Methods in Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Science and Technology Planning Project of Guangdong Province; National Cancer Institute; National Institutes of Health; Natural Science Foundation of Guangdong Province; Canadian Cancer Society; Sunnybrook Research Institute; SPIE; Guangzhou Science and Technology Program key projects; American Association of Physicists in Medicine","keywords":"Artificial intelligence; Intraclass correlation; Breast cancer; Histopathology; Support vector machine; Pattern recognition (psychology); Segmentation; Correlation; H&E stain; Medicine; Gradient boosting; Mathematics; Cancer; Computer science; Statistics; Pathology; Reproducibility; Random forest; Internal medicine","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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":[0.000850088,0.0004959057,0.0004544963,0.001736576,0.0001508711,0.000495762,0.0004051464,0.0004961696,0.0007379892],"category_scores_gemma":[0.002284678,0.0002327731,0.0003610171,0.0005691919,0.0003420415,0.0006680313,0.0005465033,0.0003101338,0.000464903],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003241113,"about_ca_system_score_gemma":0.0002670148,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009575425,"about_ca_topic_score_gemma":0.001528239,"domain_scores_codex":[0.9996367,0.00009068722,0.00002008687,0.0001065442,0.0001104439,0.00003545335],"domain_scores_gemma":[0.999003,0.0003719818,0.000232836,0.0001330468,0.00022065,0.00003849956],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004788864,0.0001796659,0.05535597,0.0003299224,0.0002519863,0.0003130607,0.0002615792,0.1077405,0.1928875,0.001332905,0.001221877,0.6396462],"study_design_scores_gemma":[0.00001827802,0.0002951744,0.03880228,0.00002462515,0.00008851608,0.0006274591,0.00008445395,0.9016592,0.05433633,0.002738117,0.00128543,0.00004022486],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3538936,0.001006728,0.6418197,0.00009872512,0.00003079372,0.00009638492,0.000189979,0.001460655,0.00140344],"genre_scores_gemma":[0.8904504,0.0004825168,0.1074251,0.00005251076,0.00003908727,0.00005684627,0.0002623271,0.00006995352,0.001161327],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001736576,"threshold_uncertainty_score":0.00449574,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04572080182304022,"score_gpt":0.3950865060725673,"score_spread":0.3493657042495271,"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."}}