{"id":"W4408810153","doi":"10.1109/tip.2025.3552198","title":"Pruning Sparse Tensor Neural Networks Enables Deep Learning for 3D Ultrasound Localization Microscopy","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; Polytechnique Montréal","funders":"Canadian Institutes of Health Research; Alliance de recherche numérique du Canada; Institut TransMedTech; Natural Sciences and Engineering Research Council of Canada; Institut de Valorisation des Données; Canada First Research Excellence Fund; Canada Foundation for Innovation","keywords":"Artificial intelligence; Artificial neural network; Computer science; Pruning; Deep learning; Pattern recognition (psychology); Microscopy; Computer vision; Optics; Biology; Physics","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":[0.0003394563,0.0002541864,0.0003472521,0.000291796,0.0009413706,0.0002395454,0.0001079665,0.0001367472,0.00004472413],"category_scores_gemma":[0.0001961234,0.0002412849,0.0001337271,0.0005220953,0.0001836338,0.0002735651,0.000001813365,0.0008447422,0.000003114716],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001159758,"about_ca_system_score_gemma":0.0001071964,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002205347,"about_ca_topic_score_gemma":0.000005530098,"domain_scores_codex":[0.9984428,0.00006528979,0.0003939384,0.0004434936,0.000191821,0.0004626522],"domain_scores_gemma":[0.9990482,0.0002843545,0.0001288864,0.0001727777,0.0002355259,0.000130281],"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":[0.0003741214,0.0002225166,0.0009025164,0.0007837853,0.0000930941,0.00001634232,0.0004935405,0.5287212,0.03289494,0.000007513082,0.0001996835,0.4352908],"study_design_scores_gemma":[0.001515781,0.0001196908,0.0001262531,0.0006996114,0.0002951155,0.0000622208,0.0003041176,0.9853074,0.008866858,0.00004353729,0.002450913,0.0002085136],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006897564,0.0007260663,0.9899611,0.0006935418,0.0004537438,0.0004715523,0.000001650265,0.0002718868,0.0005228517],"genre_scores_gemma":[0.9299189,0.0001117407,0.06630735,0.001383732,0.000161789,0.00008786558,0.00002858393,0.00007011519,0.001929876],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9236538,"threshold_uncertainty_score":0.9839314,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008951995204154253,"score_gpt":0.2945132598188118,"score_spread":0.2855612646146575,"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."}}