{"id":"W3158042586","doi":"10.21203/rs.3.rs-225323/v1","title":"Deep learning-based tumor segmentation on digital images of histopathology slides for microdosimetry applications","year":2021,"lang":"en","type":"preprint","venue":"Research Square","topic":"AI in cancer detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Canada First Research Excellence Fund; University of Toronto; Government of Ontario; Canada Research Chairs; McGill University","keywords":"Computer science; Digital pathology; Artificial intelligence; Deep learning; Segmentation; Convolutional neural network; Pattern recognition (psychology); Artificial neural network; Process (computing); Overfitting","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006077619,0.0004410917,0.0003006633,0.0007309358,0.0001839141,0.000537216,0.0005099458,0.0005186062,0.001475726],"category_scores_gemma":[0.001301636,0.0002983886,0.0003546344,0.0004332813,0.0002553497,0.0004450003,0.0004219583,0.0004507764,0.0004462698],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009314313,"about_ca_system_score_gemma":0.0008061369,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003367565,"about_ca_topic_score_gemma":0.005935929,"domain_scores_codex":[0.9997906,0.00003387149,0.00001412799,0.00006078678,0.00007303972,0.00002748509],"domain_scores_gemma":[0.9995677,0.0001408447,0.00006731585,0.00006446274,0.0001412811,0.00001838608],"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":[0.0004832866,0.000142375,0.005452734,0.0002183167,0.00008136905,0.0002160873,0.0001438619,0.2531937,0.3063581,0.001427904,0.002172479,0.4301098],"study_design_scores_gemma":[0.000006112851,0.00006416628,0.002455816,0.00001098938,0.00001298128,0.00008637944,0.0000224028,0.9238317,0.07183991,0.0006626953,0.0009955211,0.00001138041],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2761365,0.0004775251,0.7161888,0.0003236809,0.00004683524,0.0001558403,0.000445078,0.004300082,0.001925674],"genre_scores_gemma":[0.6492586,0.0003359514,0.3467044,0.0001285591,0.00001190674,0.0001041015,0.0005917734,0.0001620661,0.00270253],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003367565,"threshold_uncertainty_score":0.006758034,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03680772350701274,"score_gpt":0.3720991712101173,"score_spread":0.3352914477031046,"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."}}