{"id":"W2975180264","doi":"10.1016/j.media.2021.101996","title":"Multi-scale fully convolutional neural networks for histopathology image segmentation: From nuclear aberrations to the global tissue architecture","year":2021,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"AI in cancer detection","field":"Computer Science","cited_by":109,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Olympus","keywords":"Convolutional neural network; Artificial intelligence; Segmentation; Computer science; Pattern recognition (psychology); Scale (ratio); Histopathology; Image segmentation; Image (mathematics); Computer vision; Architecture; Pathology; Cartography; Medicine; Geography","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":[],"consensus_categories":[],"category_scores_codex":[0.0003679581,0.0001507998,0.0002644733,0.00007124744,0.0003693546,0.0001876396,0.0007086787,0.0001168719,0.0007389437],"category_scores_gemma":[0.0003311467,0.0001245309,0.0002299606,0.001443814,0.0001445301,0.000206634,0.000292415,0.0002419053,0.00004647494],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002097854,"about_ca_system_score_gemma":0.0001201512,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002081069,"about_ca_topic_score_gemma":0.003605209,"domain_scores_codex":[0.9979447,0.0003055212,0.0003305169,0.0006006903,0.0005202168,0.0002983858],"domain_scores_gemma":[0.9985874,0.0002314904,0.00009587428,0.0005849956,0.0002701172,0.000230132],"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":[0.0003046632,0.001239329,0.008394262,0.00004987061,0.002674116,0.001243953,0.008800188,0.1733378,0.04142732,0.002333329,0.1405232,0.619672],"study_design_scores_gemma":[0.0003796519,0.00004834785,0.01286996,0.000003835358,0.0003292808,0.00004356608,0.00009483048,0.975547,0.0001960532,0.0003321349,0.01000017,0.0001551384],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002886471,0.0002119918,0.961089,0.03478786,0.0006040718,0.0001763046,0.00006849968,0.0000948513,0.00008095775],"genre_scores_gemma":[0.1691962,0.00001654714,0.8188562,0.01007184,0.001023433,0.0001563378,0.0002946189,0.00001797916,0.0003668166],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8022093,"threshold_uncertainty_score":0.8090916,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00989152442796864,"score_gpt":0.2867536830453873,"score_spread":0.2768621586174187,"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."}}