{"id":"W4399866885","doi":"10.1007/s11548-024-03213-z","title":"Using diffusion models to generate synthetic labeled data for medical image segmentation","year":2024,"lang":"en","type":"article","venue":"International Journal of Computer Assisted Radiology and Surgery","topic":"AI in cancer detection","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":false,"ca_institutions":"Ontario Institute for Cancer Research; University of Toronto","funders":"","keywords":"Computer science; Artificial intelligence; Segmentation; Pipeline (software); Dice; Synthetic data; Image segmentation; Pattern recognition (psychology); Similarity (geometry); Image (mathematics); Machine learning; Computer vision; Data mining","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001283075,0.0001056633,0.0002337544,0.0004179128,0.00006538683,0.0002177174,0.0007360487,0.00008994321,0.00000829744],"category_scores_gemma":[0.00007249267,0.00008831103,0.00008520706,0.0001404479,0.00004540517,0.0008559719,0.0002841815,0.000158738,0.000001380787],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001073566,"about_ca_system_score_gemma":0.0002585685,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005632933,"about_ca_topic_score_gemma":0.000002011625,"domain_scores_codex":[0.9985334,0.0001576972,0.0004998088,0.0002938065,0.0003766595,0.0001385907],"domain_scores_gemma":[0.9983222,0.0009390184,0.000154111,0.0001951188,0.0002764409,0.0001131068],"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":[0.0002898562,0.0001250277,0.0003204977,0.00007211678,0.0009278496,0.0008561129,0.000621521,0.008608984,0.01886452,0.003793745,0.02240934,0.9431104],"study_design_scores_gemma":[0.0002255722,0.00005631435,0.0002689411,0.0002013176,0.00002081987,0.003766882,0.000004908804,0.9917446,0.0004380699,0.001644687,0.00152989,0.00009803163],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09687656,0.0005757566,0.8923731,0.003731698,0.006326561,0.00006726177,0.00001218049,0.00003073634,0.000006086472],"genre_scores_gemma":[0.6597542,0.0003285255,0.3366081,0.001314929,0.001934437,0.000005918014,0.00002495626,0.00001616604,0.00001279463],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9831356,"threshold_uncertainty_score":0.3601219,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08073924164035598,"score_gpt":0.3441608482959532,"score_spread":0.2634216066555972,"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."}}