{"id":"W2982011997","doi":"10.3389/fbioe.2019.00300","title":"Assessing the Impact of Color Normalization in Convolutional Neural Network-Based Nuclei Segmentation Frameworks","year":2019,"lang":"en","type":"article","venue":"Frontiers in Bioengineering and Biotechnology","topic":"AI in cancer detection","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"ca_institutions":"St. Michael's Hospital; Toronto Metropolitan University","funders":"Mitacs","keywords":"Convolutional neural network; Segmentation; Normalization (sociology); Preprocessor; Computer science; Artificial intelligence; Deep learning; Pattern recognition (psychology); Image segmentation; Data pre-processing; Digital pathology; Machine learning","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":[0.006717741,0.002017431,0.0006885194,0.001383254,0.0007014056,0.001470363,0.001790635,0.001433079,0.00136644],"category_scores_gemma":[0.01773708,0.0003953454,0.0007231199,0.0009809817,0.001143476,0.002637734,0.001816079,0.001483713,0.0004531004],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002677666,"about_ca_system_score_gemma":0.002408837,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02440884,"about_ca_topic_score_gemma":0.02063697,"domain_scores_codex":[0.9976131,0.0006265038,0.0001189877,0.0004903188,0.0007849617,0.0003662246],"domain_scores_gemma":[0.9939122,0.002758427,0.0006315921,0.0008550707,0.001576221,0.0002665194],"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":[0.001462311,0.0004869995,0.01411887,0.000566231,0.0004106392,0.0001100781,0.0001335055,0.7353565,0.02038393,0.009316592,0.003612938,0.2140414],"study_design_scores_gemma":[0.000027914,0.0003274109,0.003248399,0.00006073834,0.00009396937,0.00005280749,0.00005335537,0.9691403,0.02284241,0.002595398,0.001529461,0.00002785024],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.675229,0.007225526,0.2936532,0.001483803,0.0004423622,0.0003585291,0.0009893737,0.006063635,0.01455463],"genre_scores_gemma":[0.8969237,0.001301002,0.09765748,0.0003811625,0.00007337265,0.0000936765,0.0009462164,0.000565947,0.002057535],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.02440884,"threshold_uncertainty_score":0.04853356,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006116925565723242,"score_gpt":0.2438065164057799,"score_spread":0.2376895908400566,"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."}}