{"id":"W4384133781","doi":"10.1016/j.jvcir.2023.103896","title":"DB-TASNet for disease diagnosis and lesion segmentation in medical images","year":2023,"lang":"en","type":"article","venue":"Journal of Visual Communication and Image Representation","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Sherbrooke","funders":"China Scholarship Council; Natural Science Foundation of Hebei Province","keywords":"Segmentation; Computer science; Artificial intelligence; Deep learning; Image segmentation; Convolutional neural network; Medical imaging; Machine learning; Scale-space segmentation; Pattern recognition (psychology); Computer vision","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":[0.0008586863,0.00008636,0.0002199371,0.0003756857,0.000092866,0.00006605444,0.00007892062,0.0000515328,0.00002495893],"category_scores_gemma":[0.002007199,0.00007861543,0.00005662827,0.0003096187,0.0001060997,0.0004224879,0.00008532909,0.0001655218,0.000002291124],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006526959,"about_ca_system_score_gemma":0.0001044057,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004773475,"about_ca_topic_score_gemma":0.000009999836,"domain_scores_codex":[0.9987059,0.0002113504,0.000471641,0.0001355866,0.0003699285,0.0001056051],"domain_scores_gemma":[0.9979181,0.00122632,0.0002630403,0.000173088,0.0002354089,0.0001840923],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.002035657,0.001573827,0.3870536,0.00104317,0.0001295773,0.0001428845,0.003188761,0.00006498515,0.03774455,0.0001422842,0.056301,0.5105797],"study_design_scores_gemma":[0.00640434,0.0005869828,0.9505041,0.001168071,0.0002076386,0.00006653392,0.002005966,0.02513924,0.009270719,0.000938851,0.003535113,0.000172423],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9168769,0.001473637,0.001987165,0.07896814,0.00006581775,0.0005659543,0.000008374848,0.0000301035,0.00002393128],"genre_scores_gemma":[0.9608247,0.0340368,0.003087297,0.001719956,0.00008250388,0.00007218283,0.0001197942,0.00001800534,0.00003880172],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5634505,"threshold_uncertainty_score":0.3205844,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08127157243748095,"score_gpt":0.4802407696857158,"score_spread":0.3989691972482348,"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."}}