{"id":"W4416066425","doi":"10.1080/17686733.2025.2585417","title":"Optimising neural networks for perforator detection in DIEP flap breast reconstruction using dynamic infrared thermography","year":2025,"lang":"en","type":"article","venue":"Quantitative InfraRed Thermography Journal","topic":"Infrared Thermography in Medicine","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"Fonds Wetenschappelijk Onderzoek","keywords":"DIEP flap; Thermography; Artificial neural network; Signal reconstruction; Breast reconstruction; Convolutional neural network","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":[0.00127847,0.001157784,0.0006641431,0.0005541785,0.0002387652,0.0007272305,0.0008888812,0.001048566,0.0008138085],"category_scores_gemma":[0.002455752,0.0004649513,0.0005555096,0.0003291361,0.0003869348,0.0006186341,0.0005502231,0.0008018115,0.0003128445],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007624468,"about_ca_system_score_gemma":0.0007250603,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007108019,"about_ca_topic_score_gemma":0.005993579,"domain_scores_codex":[0.9996883,0.00008407843,0.00001876135,0.00009514595,0.00005371938,0.0000600149],"domain_scores_gemma":[0.9993274,0.0003989608,0.00006282832,0.00003316637,0.0001476185,0.0000301128],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005328765,0.0002392574,0.004487539,0.0001245844,0.0001223891,0.0001583867,0.0000576448,0.7863828,0.01088824,0.0003817401,0.001418352,0.1952061],"study_design_scores_gemma":[0.000006074535,0.00006549364,0.0004626726,0.000007498224,0.00001266746,0.00001312409,0.000009036404,0.9971288,0.002028255,0.0001688734,0.00009388119,0.000003706913],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.6886038,0.002901974,0.3012714,0.0005684795,0.00017149,0.0001465214,0.0002731163,0.002770975,0.003292419],"genre_scores_gemma":[0.9433494,0.0003828545,0.05356048,0.0002172723,0.00003197068,0.00008668868,0.0004249389,0.0000715212,0.001875006],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.007108019,"threshold_uncertainty_score":0.01413333,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01648069993112377,"score_gpt":0.3037793314567799,"score_spread":0.2872986315256562,"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."}}