{"id":"W4417472315","doi":"10.1109/nss/mic/rtsd57106.2025.11286706","title":"Semi-Supervised Learning for Improved Radiomics-Based Outcome Prediction from Lymphoma [${ }^{18}\\mathrm{F}]\\text{FDG}$ PET Images","year":2025,"lang":"","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Teck (Canada)","funders":"","keywords":"Feature selection; Radiomics; Pattern recognition (psychology); Logistic regression; Feature extraction; Feature (linguistics); Lymphoma; Dimensionality reduction","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003306086,0.000808236,0.00115961,0.0009993527,0.0003405995,0.0007849699,0.001132173,0.0006620122,0.0006273279],"category_scores_gemma":[0.005087499,0.0002595109,0.001157541,0.0005397769,0.0004652228,0.0006617842,0.0007594925,0.0009365763,0.0004523844],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004981174,"about_ca_system_score_gemma":0.0009461738,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00239587,"about_ca_topic_score_gemma":0.002684286,"domain_scores_codex":[0.9982582,0.0009177306,0.000111826,0.0003747895,0.0002132273,0.0001241706],"domain_scores_gemma":[0.9971514,0.001480959,0.0003212597,0.0003911003,0.0005527525,0.0001024604],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001376416,0.001204658,0.0312043,0.0003181634,0.0005243137,0.0002652371,0.0003380465,0.3238943,0.01919023,0.001649638,0.0070466,0.6129882],"study_design_scores_gemma":[0.00002640305,0.0001044157,0.003044888,0.000009278531,0.00003071882,0.000052965,0.00002458788,0.9909124,0.003819224,0.001552709,0.0004081991,0.00001416527],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5180417,0.001348786,0.4721119,0.0004475482,0.00007052511,0.0002066877,0.001043704,0.004969027,0.001760069],"genre_scores_gemma":[0.9294859,0.000148592,0.06735609,0.0001208803,0.00006515942,0.0001571188,0.001850213,0.00009324314,0.0007228242],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003306086,"threshold_uncertainty_score":0.01748449,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01290057375386634,"score_gpt":0.2985677988252848,"score_spread":0.2856672250714185,"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."}}