{"id":"W4391819303","doi":"10.1016/j.compbiomed.2024.108153","title":"Deep integrated fusion of local and global features for cervical cell classification","year":2024,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"China Scholarship Council; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Convolutional neural network; Artificial intelligence; Computer science; Cervical cancer; Pattern recognition (psychology); Local binary patterns; Contextual image classification; Support vector machine; Feature extraction; Binary classification; Feature (linguistics); Image (mathematics); Medicine; Cancer; Histogram","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":[0.0004991547,0.0006863035,0.0007045047,0.001388596,0.0002349845,0.0004997322,0.0007785354,0.000539886,0.001274482],"category_scores_gemma":[0.0007674979,0.0001954826,0.0007090363,0.0009221596,0.0002439484,0.0009969244,0.001019716,0.0006260709,0.0004555343],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005553743,"about_ca_system_score_gemma":0.0007409041,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003905615,"about_ca_topic_score_gemma":0.006037166,"domain_scores_codex":[0.9996877,0.00002813924,0.00001637776,0.00007829609,0.0001183764,0.0000712493],"domain_scores_gemma":[0.9997672,0.0000419811,0.00003228197,0.00003929755,0.00009023085,0.00002892669],"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":[0.0003917705,0.0002536128,0.01040661,0.000120297,0.0001238492,0.0001957319,0.00007381252,0.04226469,0.08536346,0.001892857,0.004995493,0.8539178],"study_design_scores_gemma":[0.00003126787,0.0002329756,0.009080566,0.00001927195,0.00014512,0.0002559229,0.0000748533,0.92269,0.0597504,0.003624648,0.004062747,0.00003218267],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2579829,0.002346068,0.7290527,0.0005658059,0.0001555518,0.0001662981,0.001038331,0.0039728,0.004719649],"genre_scores_gemma":[0.8639258,0.0004590303,0.1303375,0.0002100931,0.00006390901,0.00007183414,0.001635841,0.00008354136,0.003212442],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003905615,"threshold_uncertainty_score":0.00776577,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0152893903122251,"score_gpt":0.3099968735585302,"score_spread":0.2947074832463051,"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."}}