{"id":"W4281263011","doi":"10.1016/j.compbiomed.2022.105571","title":"Eight pruning deep learning models for low storage and high-speed COVID-19 computed tomography lung segmentation and heatmap-based lesion localization: A multicenter study using COVLIAS 2.0","year":2022,"lang":"en","type":"article","venue":"Computers in Biology and Medicine","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":54,"is_retracted":false,"has_abstract":false,"ca_institutions":"AllerGen; Queen's University","funders":"","keywords":"Pruning; Segmentation; Particle swarm optimization; Pattern recognition (psychology); Artificial intelligence; Deep learning; Computer science; Differential evolution; Algorithm; Biology","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":[0.002507891,0.001323512,0.001379897,0.0008975129,0.0004283297,0.001221283,0.002123663,0.001244516,0.001618816],"category_scores_gemma":[0.005848009,0.0005916683,0.001252125,0.0008603024,0.0003333792,0.0009413402,0.00108612,0.001421046,0.0006515486],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001464732,"about_ca_system_score_gemma":0.002111372,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02004902,"about_ca_topic_score_gemma":0.01514747,"domain_scores_codex":[0.9994416,0.0001690013,0.0000473588,0.0001580267,0.0001006792,0.00008344722],"domain_scores_gemma":[0.9985305,0.0007593695,0.00008741264,0.0001611865,0.0003550355,0.0001065221],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.009001027,0.002884948,0.05609187,0.0007384322,0.001599106,0.0003575879,0.0002210723,0.2464694,0.009222665,0.001476808,0.02648216,0.6454548],"study_design_scores_gemma":[0.0005615248,0.001414126,0.01031581,0.0001452845,0.0006440431,0.0002200897,0.00009812485,0.9753318,0.006993616,0.001699505,0.002516857,0.00005907984],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8826681,0.006449129,0.09790489,0.001158751,0.0003205523,0.0004425221,0.003597742,0.004428807,0.003029528],"genre_scores_gemma":[0.9168715,0.001296836,0.07058518,0.0003767388,0.00008348185,0.0004484862,0.007405519,0.0004666927,0.002465522],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02004902,"threshold_uncertainty_score":0.03986466,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04998625163877202,"score_gpt":0.3604398528782313,"score_spread":0.3104536012394593,"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."}}