{"id":"W4281736156","doi":"10.1016/j.bea.2022.100041","title":"A deep learning segmentation-classification pipeline for X-ray-based COVID-19 diagnosis","year":2022,"lang":"en","type":"article","venue":"Biomedical Engineering Advances","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":39,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lakehead University","funders":"","keywords":"Deep learning; Artificial intelligence; Segmentation; Computer science; Pipeline (software); Coronavirus disease 2019 (COVID-19); Classifier (UML); Machine learning; Focus (optics); Transfer of learning; Pattern recognition (psychology); Medicine; Pathology; Infectious disease (medical specialty)","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":[0.0005412312,0.0002063009,0.0003049025,0.0003874492,0.0003311976,0.00002318468,0.0001620927,0.00006652231,0.000395302],"category_scores_gemma":[0.003760424,0.0002143061,0.0001371883,0.0006972798,0.00008024611,0.00008662361,0.00005412243,0.0003113801,0.000008583987],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007773492,"about_ca_system_score_gemma":0.0003315134,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002239155,"about_ca_topic_score_gemma":0.000002141395,"domain_scores_codex":[0.9980833,0.00005187967,0.0004012825,0.0004640342,0.0006412891,0.0003581945],"domain_scores_gemma":[0.9974185,0.001707554,0.0001303542,0.0002235514,0.00006851183,0.000451501],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003480234,0.001048652,0.004364986,0.001927893,0.00009464657,0.00007441902,0.0005208604,0.8456902,0.01266366,0.0001874738,0.01288569,0.1201935],"study_design_scores_gemma":[0.001597083,0.0002424564,0.000401712,0.00003763426,0.00006149626,0.000007101706,0.0001708188,0.401942,0.0003308954,0.00001149317,0.5950467,0.0001506245],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004437157,0.00230842,0.9389464,0.05180098,0.0007627944,0.0009766332,0.0000550689,0.0007068174,0.000005744347],"genre_scores_gemma":[0.8439002,0.0005015454,0.1141371,0.02853156,0.001005336,0.009411748,0.00202928,0.0001798246,0.000303436],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.839463,"threshold_uncertainty_score":0.8739148,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02787527854984945,"score_gpt":0.3292621804004914,"score_spread":0.3013869018506419,"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."}}