{"id":"W3207280867","doi":"10.18280/rces.080302","title":"A Combined Image Segmentation and Classification Approach for COVID-19 Infected Lungs","year":2021,"lang":"en","type":"article","venue":"Review of Computer Engineering Studies","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Coronavirus disease 2019 (COVID-19); Pneumonia; Image segmentation; Artificial intelligence; Segmentation; Computed tomography; Computer science; Pattern recognition (psychology); Image (mathematics); Lung; Computer vision; Medicine; Radiology; Disease; Pathology; Internal medicine; Infectious disease (medical specialty)","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002686109,0.0001383416,0.0005397807,0.00007474735,0.00003754229,0.00001121734,0.00003530649,0.00002803815,0.000002626394],"category_scores_gemma":[0.0009277608,0.0001271047,0.00008965354,0.0002522524,0.00003500116,0.00005193659,0.0000622609,0.00005960841,7.292443e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001268413,"about_ca_system_score_gemma":0.00009086129,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001595982,"about_ca_topic_score_gemma":1.162481e-7,"domain_scores_codex":[0.9991587,0.00003110944,0.0003336317,0.0002348902,0.0001299398,0.0001117284],"domain_scores_gemma":[0.9988418,0.000453041,0.0001049931,0.0001938681,0.0003350964,0.00007121608],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007590537,0.0009034592,0.0041224,0.7979787,0.002470151,0.00003000607,0.002253204,0.002619431,0.02915548,0.002045615,0.1243555,0.03399015],"study_design_scores_gemma":[0.01424816,0.001518754,0.08487643,0.06350399,0.004550377,0.0002344735,0.0003021921,0.5394154,0.00921031,0.0001082138,0.2804935,0.001538218],"study_design_candidate":"systematic_review","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004675453,0.1410756,0.8349072,0.01735953,0.0001800575,0.001593104,0.00001232375,0.0001862795,0.00001042931],"genre_scores_gemma":[0.02907761,0.2420462,0.7019736,0.02520753,0.0003224407,0.0008059666,0.0004339206,0.00007673817,0.00005598464],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7344747,"threshold_uncertainty_score":0.5183178,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05107939260949537,"score_gpt":0.3645067333006402,"score_spread":0.3134273406911448,"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."}}