{"id":"W4412805201","doi":"10.1016/j.compmedimag.2025.102615","title":"IgCONDA-PET: Weakly-supervised PET anomaly detection using implicitly-guided attention-conditional counterfactual diffusion modeling — a multi-center, multi-cancer, and multi-tracer study","year":2025,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia; BC Cancer Agency","funders":"Canadian Institutes of Health Research","keywords":"Computer science; Artificial intelligence; Anomaly detection; Thresholding; Deep learning; Pattern recognition (psychology); Ground truth; Autoencoder; Machine learning; Image (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":[0.004234423,0.001147622,0.001687856,0.0006409321,0.0004381105,0.001665899,0.002921256,0.001647475,0.0009136365],"category_scores_gemma":[0.01009406,0.0007096106,0.001119976,0.0005184591,0.0008923805,0.001249885,0.001554034,0.001988827,0.0002645111],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008334844,"about_ca_system_score_gemma":0.001405416,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006807306,"about_ca_topic_score_gemma":0.006209105,"domain_scores_codex":[0.9987576,0.0007800877,0.0000325751,0.0002484789,0.0001007061,0.00008046193],"domain_scores_gemma":[0.9944578,0.003895311,0.0003497028,0.0007549856,0.000338802,0.0002033608],"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":[0.004055057,0.0009632017,0.02545767,0.0003886676,0.001946906,0.0006173793,0.0002665177,0.6211416,0.01506321,0.01894145,0.009021298,0.302137],"study_design_scores_gemma":[0.0000322997,0.00005968172,0.0007547341,0.000004983269,0.00003986218,0.00008867298,0.000006078189,0.9939062,0.001274924,0.003429416,0.0003900458,0.00001303828],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1785738,0.001517283,0.8146634,0.0007927413,0.00009802359,0.0001564727,0.0004835204,0.002439228,0.001275608],"genre_scores_gemma":[0.8479627,0.0003589871,0.1473238,0.0003010666,0.00009225004,0.0001218883,0.00114734,0.0003821297,0.002309837],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006807306,"threshold_uncertainty_score":0.022394,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02899151447484044,"score_gpt":0.3455330713684343,"score_spread":0.3165415568935939,"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."}}