{"id":"W4391871413","doi":"10.48550/arxiv.2402.09359","title":"Pruning Sparse Tensor Neural Networks Enables Deep Learning for 3D Ultrasound Localization Microscopy","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Montreal Heart Institute; Minnow Environmental (Canada); Polytechnique Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Alliance de recherche numérique du Canada; Institut de Valorisation des Données; Canada First Research Excellence Fund","keywords":"Pruning; Artificial neural network; Deep neural networks; Artificial intelligence; Microscopy; Deep learning; Computer science; Tensor (intrinsic definition); Pattern recognition (psychology); Mathematics; Physics; Biology; Optics; Geometry","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004306485,0.0004224693,0.0005862369,0.0003137489,0.0003096061,0.000157804,0.000283857,0.0004304058,0.00007862012],"category_scores_gemma":[0.0005304645,0.0004422809,0.0003186699,0.000401634,0.0002170761,0.00007891614,0.0004304392,0.002159446,0.00001867702],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002635962,"about_ca_system_score_gemma":0.0001280143,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001236215,"about_ca_topic_score_gemma":0.00001461251,"domain_scores_codex":[0.9978433,0.0001244894,0.0003200781,0.001034566,0.0001122772,0.0005652444],"domain_scores_gemma":[0.9985011,0.0003409898,0.000242054,0.0004323309,0.0001982984,0.0002852821],"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":[0.0001902003,0.00005704679,0.01691684,0.000779699,0.0002441315,0.0003471369,0.0002368594,0.9766619,0.0002792573,0.001261368,0.0006686777,0.002356914],"study_design_scores_gemma":[0.0009611238,0.0001240182,0.000382074,0.0007096585,0.0008620392,0.00005856255,0.0002361692,0.9882215,0.00004006748,0.001953801,0.006045135,0.0004059027],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2450547,0.001153505,0.750313,0.0002340049,0.001145269,0.0007712592,0.000006622899,0.0003885678,0.0009331093],"genre_scores_gemma":[0.9897051,0.0005908931,0.003164927,0.0003812831,0.0006791463,0.000004466187,0.0004009897,0.0001231599,0.004950063],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7471481,"threshold_uncertainty_score":0.9998029,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03063624820363587,"score_gpt":0.2271634436559196,"score_spread":0.1965271954522838,"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."}}