{"id":"W3115309267","doi":"10.21611/qirt.2020.146","title":"Thermal-driven biomarkers for breast cancer screening using dynamic infrared imaging modality","year":2020,"lang":"en","type":"article","venue":"Proceedings of the 2020 International Conference on Quantitative InfraRed Thermography","topic":"Infrared Thermography in Medicine","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Modality (human–computer interaction); Breast cancer; Infrared; Cancer; Computer science; Radiology; Medicine; Medical physics; Internal medicine; Artificial intelligence; Optics; Physics","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":[0.0005570307,0.0007431425,0.000533964,0.0007828191,0.0001615438,0.0005055279,0.0004440094,0.0005732627,0.0009751753],"category_scores_gemma":[0.001996926,0.0001918448,0.0006179137,0.0006147045,0.0002130969,0.0005902917,0.0003591171,0.0005896451,0.0005914681],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002489086,"about_ca_system_score_gemma":0.0004386544,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001574881,"about_ca_topic_score_gemma":0.003033216,"domain_scores_codex":[0.9996839,0.00009043128,0.00001258782,0.00009831775,0.00007988862,0.00003494985],"domain_scores_gemma":[0.9996383,0.000140326,0.0000686772,0.0000349712,0.00009778188,0.00001994371],"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":[0.0008965615,0.0003752086,0.0368579,0.0006438817,0.0002511973,0.0003254594,0.0001847434,0.09155799,0.1505922,0.00315893,0.009629044,0.7055269],"study_design_scores_gemma":[0.00003780421,0.0003302077,0.02606224,0.00007964337,0.00016792,0.0007775382,0.0001340485,0.9240856,0.03481438,0.005849595,0.007600128,0.00006090463],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1430218,0.005679755,0.8449558,0.0009914992,0.0002594528,0.0001214121,0.001459438,0.00127395,0.002236984],"genre_scores_gemma":[0.7569944,0.002559519,0.2341899,0.0004377661,0.0002977809,0.0001729957,0.002295401,0.00009150158,0.002960708],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001574881,"threshold_uncertainty_score":0.003262222,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05318185460259043,"score_gpt":0.3392309594270323,"score_spread":0.2860491048244418,"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."}}