{"id":"W4205428558","doi":"10.1016/j.ijmedinf.2021.104669","title":"Deep transfer learning based model for colorectal cancer histopathology segmentation: A comparative study of deep pre-trained models","year":2021,"lang":"en","type":"article","venue":"International Journal of Medical Informatics","topic":"AI in cancer detection","field":"Computer Science","cited_by":61,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Deep learning; Segmentation; Artificial intelligence; Computer science; Convolutional neural network; Encoder; Transfer of learning; Pattern recognition (psychology); Colorectal cancer; Histopathology; Machine learning; Cancer; Medicine; Pathology; Internal medicine","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001003189,0.0008588675,0.0006364823,0.0006068519,0.0002876286,0.0009137722,0.001255928,0.001205068,0.001957423],"category_scores_gemma":[0.00197671,0.0002793766,0.0006938223,0.0005238244,0.0002209156,0.000971075,0.0005335347,0.001106036,0.001079736],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009435842,"about_ca_system_score_gemma":0.001753249,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01936997,"about_ca_topic_score_gemma":0.01555923,"domain_scores_codex":[0.9997097,0.0000538908,0.00001671725,0.00008422187,0.00007587429,0.00005956828],"domain_scores_gemma":[0.9992411,0.0003007188,0.0000426623,0.00008577811,0.0002838415,0.0000459131],"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":[0.001084536,0.0006279218,0.007007145,0.0002632681,0.0003087264,0.0001747858,0.0001148547,0.4915062,0.01497575,0.001118854,0.006330473,0.4764875],"study_design_scores_gemma":[0.000007315393,0.0001215247,0.001215202,0.00001552525,0.00003812452,0.00003380491,0.00002009213,0.9939324,0.003682093,0.0004058665,0.0005174596,0.00001050408],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.546294,0.005762639,0.4263336,0.001136568,0.000650866,0.0002355173,0.001476432,0.009212357,0.00889798],"genre_scores_gemma":[0.9376696,0.00126994,0.04957354,0.00027563,0.00005907674,0.00008130685,0.00196184,0.0002946685,0.008814363],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01936997,"threshold_uncertainty_score":0.03851444,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04380224054322936,"score_gpt":0.3525245725941451,"score_spread":0.3087223320509158,"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."}}