{"id":"W4389340115","doi":"10.7717/peerj-cs.1651","title":"A deep learning approach for the detection and counting of colon cancer cells (HT-29 cells) bunches and impurities","year":2023,"lang":"en","type":"article","venue":"PeerJ Computer Science","topic":"AI in cancer detection","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Moncton","funders":"","keywords":"Deep learning; Artificial intelligence; Colorectal cancer; Computer science; Pattern recognition (psychology); Cancer cell; Cancer; Machine learning; Medicine; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00147125,0.0001381707,0.0001665632,0.0002005975,0.0008292056,0.0004173006,0.0006750575,0.0000465036,5.345106e-7],"category_scores_gemma":[0.00002799058,0.0001117364,0.00003620745,0.001156187,0.0005093088,0.0006343332,0.0006015281,0.0001582765,9.169589e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007303944,"about_ca_system_score_gemma":0.00008298049,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002088017,"about_ca_topic_score_gemma":0.00004065672,"domain_scores_codex":[0.9983542,0.00004446499,0.0002040306,0.0005862041,0.0004431122,0.0003679937],"domain_scores_gemma":[0.9988626,0.0004151881,0.0001651273,0.0002718553,0.0002220714,0.00006317568],"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":[0.00001600782,0.00001772612,0.0005488247,0.0002290732,0.00001999267,9.435665e-7,0.006638397,0.09958635,0.1238732,0.0004722702,0.0001028871,0.7684943],"study_design_scores_gemma":[0.0001746801,0.0001335827,0.002625102,0.00001823535,0.000008757621,0.00000945608,0.0001415616,0.9399213,0.05609362,0.0002289278,0.000516864,0.0001278938],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1053801,0.000470912,0.8925881,0.0001603736,0.0009090231,0.0003107623,0.00000129304,0.0001546423,0.00002474409],"genre_scores_gemma":[0.9440735,0.000215114,0.05532947,0.00006387904,0.000169823,0.00009019166,2.453272e-7,0.000009459727,0.00004834985],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.840335,"threshold_uncertainty_score":0.6377663,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01881575428924857,"score_gpt":0.2453289860026231,"score_spread":0.2265132317133745,"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."}}