{"id":"W3149262220","doi":"10.21203/rs.3.rs-600363/v1","title":"TB-Net: A Tailored, Self-Attention Deep Convolutional Neural Network Design For Detection of Tuberculosis Cases From Chest X-Ray Images","year":2021,"lang":"en","type":"preprint","venue":"Research Square","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Thunder Bay Regional Health Sciences Centre; McMaster University; University of Waterloo","funders":"","keywords":"Convolutional neural network; Artificial intelligence; Deep learning; Tuberculosis; Machine learning; Medicine; Computer science; Cohort; Artificial neural network; Pathology","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":[0.0004988035,0.000519462,0.0002007203,0.0002685018,0.0001452487,0.0002944416,0.0009903965,0.0005699967,0.001703716],"category_scores_gemma":[0.0009894487,0.0002759894,0.0003979884,0.0001107134,0.0002903778,0.0004247573,0.0004469259,0.0006244087,0.0003062174],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006675432,"about_ca_system_score_gemma":0.0006068479,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004009214,"about_ca_topic_score_gemma":0.007233887,"domain_scores_codex":[0.9998685,0.00002842866,0.000006778567,0.00004373345,0.00003175241,0.00002075795],"domain_scores_gemma":[0.9997503,0.0001068273,0.00002990288,0.00001853165,0.00007691874,0.00001758034],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000247258,0.0001797849,0.004408193,0.0001276774,0.00007825054,0.0001739145,0.00006614502,0.8512418,0.0241411,0.002188136,0.002077724,0.1150701],"study_design_scores_gemma":[0.000008486802,0.00006739822,0.0003178532,0.000006082761,0.000009385445,0.00001838054,0.000003244665,0.995748,0.003072434,0.0004191445,0.0003264853,0.000003079443],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2685672,0.0007887207,0.7186033,0.000503066,0.0001146184,0.0002508799,0.0004908811,0.003710933,0.006970472],"genre_scores_gemma":[0.8573219,0.0001635014,0.1368769,0.0002574727,0.00001809129,0.0001846702,0.0005024,0.0001131153,0.004561892],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004009214,"threshold_uncertainty_score":0.007971764,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08359636210538827,"score_gpt":0.3844175795535964,"score_spread":0.3008212174482081,"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."}}