{"id":"W3214583359","doi":"10.3390/diagnostics11112109","title":"Ten Fast Transfer Learning Models for Carotid Ultrasound Plaque Tissue Characterization in Augmentation Framework Embedded with Heatmaps for Stroke Risk Stratification","year":2021,"lang":"en","type":"article","venue":"Diagnostics","topic":"Ultrasound Imaging and Elastography","field":"Medicine","cited_by":57,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Risk stratification; Ultrasound; Medicine; Stroke (engine); Stratification (seeds); Stroke risk; Transfer of learning; Cardiology; Radiology; Internal medicine; Computer science; Artificial intelligence; Ischemic stroke; Engineering; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001516926,0.0001812348,0.0002656017,0.0001230591,0.0001506922,0.00007784925,0.00004272432,0.0001336423,0.00001396565],"category_scores_gemma":[0.0007549094,0.0001754732,0.00006828339,0.0002753088,0.00004289961,0.000189219,0.000002844599,0.0002722228,0.000001663494],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005683819,"about_ca_system_score_gemma":0.0001130918,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002384839,"about_ca_topic_score_gemma":0.00006226667,"domain_scores_codex":[0.9988433,0.00005923586,0.0003029025,0.0003451255,0.0001831047,0.0002663524],"domain_scores_gemma":[0.9980299,0.001338979,0.00007354878,0.0001811316,0.0002899285,0.00008653205],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0008407322,0.0009880987,0.4858517,0.0006052243,0.0003136578,0.000006769301,0.01237192,0.03029089,0.4583287,0.002758055,0.0001161516,0.007528145],"study_design_scores_gemma":[0.01724837,0.004683009,0.4329126,0.002527097,0.002474772,0.000161245,0.01302583,0.02213919,0.4932098,0.005543625,0.004350458,0.001723996],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3866344,0.00005230926,0.6116297,0.0002314212,0.00009165316,0.0008274142,0.0004510294,0.00004454512,0.00003752917],"genre_scores_gemma":[0.9423137,0.0007210249,0.04906887,0.0001507452,0.000173965,0.0004863953,0.006883745,0.00005225969,0.000149267],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5625608,"threshold_uncertainty_score":0.7155588,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01347588049232048,"score_gpt":0.2629697538103812,"score_spread":0.2494938733180607,"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."}}