{"id":"W3127471220","doi":"10.1109/tmi.2021.3056951","title":"A Deep Learning Framework for Spatiotemporal Ultrasound Localization Microscopy","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Medical Imaging","topic":"Photoacoustic and Ultrasonic Imaging","field":"Engineering","cited_by":96,"is_retracted":false,"has_abstract":true,"ca_institutions":"Montreal Heart Institute; Mila - Quebec Artificial Intelligence Institute; Polytechnique Montréal","funders":"Institut de Valorisation des Données; Canada First Research Excellence Fund; Institut TransMedTech; Fonds de recherche du Québec – Nature et technologies; Réseau en Bio-Imagerie du Quebec","keywords":"Microbubbles; Convolutional neural network; Computer science; Artificial intelligence; Deep learning; Ground truth; Microscopy; Computer vision; In silico; Ultrasound; Biomedical engineering; Pattern recognition (psychology); Physics; Optics; Chemistry; Acoustics; Medicine","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002158442,0.0002048602,0.0002153261,0.00009375846,0.0002900167,0.00009278878,0.0001231684,0.0001323932,0.0005776064],"category_scores_gemma":[0.0002425727,0.0002287091,0.000124803,0.0003037007,0.00008857541,0.00016747,9.026605e-7,0.0007227499,0.00002766212],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00011847,"about_ca_system_score_gemma":0.00009238068,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001241088,"about_ca_topic_score_gemma":0.00001194425,"domain_scores_codex":[0.9985723,0.00004586832,0.0003076966,0.0002888152,0.0003650167,0.0004203303],"domain_scores_gemma":[0.998777,0.0007065755,0.00003101923,0.0001818606,0.00009125825,0.0002123145],"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":[0.00003925146,0.000226741,0.0003933971,0.0003938502,0.0001976277,0.000116589,0.001708584,0.7310395,0.02781999,0.000245372,0.0008334087,0.2369857],"study_design_scores_gemma":[0.0005154722,0.00001175539,0.00002067021,0.0002680994,0.00006640932,0.0001104221,0.0005234948,0.9145478,0.08044079,0.0006817731,0.002540916,0.0002724055],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001991242,0.0004423929,0.9948916,0.000271376,0.001470003,0.000144159,0.00001078187,0.0004762474,0.0003022109],"genre_scores_gemma":[0.9694842,0.0002721189,0.02911966,0.0006908216,0.0001730821,0.00005871465,0.00002756973,0.0000752616,0.00009853882],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.967493,"threshold_uncertainty_score":0.9326489,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00682250544945267,"score_gpt":0.2567186391981233,"score_spread":0.2498961337486706,"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."}}