{"id":"W4413998364","doi":"10.1002/mp.18064","title":"A novel federated learning framework for medical imaging: Resource‐efficient approach combining PCA with early stopping","year":2025,"lang":"en","type":"article","venue":"Medical Physics","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Robustness (evolution); Principal component analysis; Dimensionality reduction; Workflow; Cluster analysis; Raw data; Data mining; Process (computing); Independent and identically distributed random variables; Medical imaging; Machine learning; Artificial intelligence; Database; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005526667,0.001338245,0.002112614,0.001334472,0.0008097937,0.001823603,0.003566736,0.002153882,0.002133697],"category_scores_gemma":[0.009394991,0.0007640422,0.001380916,0.001389765,0.001524706,0.002503959,0.003028157,0.002440771,0.0006371493],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001393743,"about_ca_system_score_gemma":0.003030238,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004786084,"about_ca_topic_score_gemma":0.003863134,"domain_scores_codex":[0.9974725,0.001114496,0.0001250978,0.0005636597,0.0004605725,0.0002637888],"domain_scores_gemma":[0.9955538,0.002277725,0.0003883326,0.0004955445,0.001006507,0.0002780622],"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":[0.0001835656,0.0001343155,0.001269947,0.00008065267,0.00007884561,0.0001426804,0.00009939321,0.8699196,0.001339367,0.0152268,0.002803204,0.1087215],"study_design_scores_gemma":[0.000006972412,0.00001737653,0.00003705251,0.000003422967,0.000004120312,0.00001373597,0.000004272532,0.9945183,0.0002311689,0.004904496,0.0002549779,0.00000402786],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003037543,0.0001436425,0.9957803,0.0001909838,0.00001730994,0.00002873777,0.00003400132,0.0004199359,0.0003474817],"genre_scores_gemma":[0.4678355,0.0003992303,0.5272002,0.0005314148,0.0001630445,0.0003818398,0.0004168911,0.0002559195,0.002816019],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005526667,"threshold_uncertainty_score":0.02922815,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02428357692321545,"score_gpt":0.2829295748141287,"score_spread":0.2586459978909132,"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."}}