{"id":"W4393039554","doi":"10.1007/s13246-024-01408-x","title":"Semi-supervised learning towards automated segmentation of PET images with limited annotations: application to lymphoma patients","year":2024,"lang":"en","type":"article","venue":"Physical and Engineering Sciences in Medicine","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"Spinal Cord Injury BC; University of British Columbia; BC Cancer Agency","funders":"Canadian Institutes of Health Research; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Dice; Artificial intelligence; Segmentation; Computer science; Cluster analysis; Machine learning; Supervised learning; Pattern recognition (psychology); Convolutional neural network; Sørensen–Dice coefficient; Image segmentation; Artificial neural network; Mathematics; Statistics","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":[0.0002711946,0.0001111117,0.0002310481,0.0002660613,0.00004190364,0.00001841705,0.00006026841,0.00001461458,0.000003119136],"category_scores_gemma":[0.0002788013,0.00007330543,0.00001677327,0.0009426013,0.000156506,0.0001079188,0.00002043494,0.0001310858,0.000001626787],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003565173,"about_ca_system_score_gemma":0.00003322582,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000960225,"about_ca_topic_score_gemma":5.416694e-7,"domain_scores_codex":[0.9990619,0.00001601756,0.0001807028,0.0002463029,0.0003388494,0.0001561758],"domain_scores_gemma":[0.9996454,0.0001248609,0.00002573621,0.0000628807,0.00005126084,0.00008982631],"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":[0.0001464052,0.0004934811,0.06490903,0.002239774,0.0001175131,0.00007124314,0.01408601,0.1877971,0.2688762,0.001340214,0.0006434504,0.4592796],"study_design_scores_gemma":[0.0006722528,0.0005525595,0.1044522,0.0007935308,0.00003309075,0.00001306692,0.0002102138,0.8922732,0.0007001075,0.00002725742,0.0001923861,0.00008009678],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9844095,0.0001478013,0.01292753,0.001854632,0.00006796448,0.000208825,0.000001302352,0.0001834978,0.0001990026],"genre_scores_gemma":[0.9945994,0.00003544266,0.005064198,0.0001280937,0.00009044202,0.00002849336,0.00002427446,0.00001162732,0.0000180008],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7044761,"threshold_uncertainty_score":0.2989309,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006451226901158923,"score_gpt":0.2862585839268453,"score_spread":0.2798073570256864,"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."}}