{"id":"W4393204089","doi":"10.1016/j.compmedimag.2024.102372","title":"Unsupervised classification of multi-contrast magnetic resonance histology of peripheral arterial disease lesions using a convolutional variational autoencoder with a Gaussian mixture model in latent space: A technical feasibility study","year":2024,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Peripheral Artery Disease Management","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":false,"ca_institutions":"Sunnybrook Hospital; Sunnybrook Health Science Centre","funders":"Jerold B. Katz Foundation","keywords":"Autoencoder; Artificial intelligence; Pattern recognition (psychology); Convolutional neural network; Mixture model; Contrast (vision); Magnetic resonance imaging; Computer science; Gaussian; Mathematics; Deep learning; Computer vision; Physics; Medicine; Radiology","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":[0.000334479,0.0001918925,0.0004300764,0.0002172859,0.00005553128,0.00002067691,0.000104378,0.00007472069,0.00003477881],"category_scores_gemma":[0.00007687835,0.0001525561,0.00008542692,0.000340168,0.0005853306,0.00008184103,0.00008309219,0.0002820759,1.65568e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001145564,"about_ca_system_score_gemma":0.0006452588,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004075559,"about_ca_topic_score_gemma":0.00004077466,"domain_scores_codex":[0.9980713,0.0001604023,0.0005128295,0.0004926478,0.0005425723,0.0002202728],"domain_scores_gemma":[0.9992034,0.00006613687,0.00007023803,0.0002495908,0.0001154811,0.0002951504],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.01281091,0.02110917,0.8736448,0.003417486,0.0004214723,0.002133219,0.004248326,0.003664421,0.03638453,0.0198598,0.0004508826,0.02185502],"study_design_scores_gemma":[0.003126318,0.00009609799,0.4467706,0.0003652585,0.0001073408,0.00002847948,0.00003000806,0.5491862,4.604283e-7,0.000197327,0.00001627068,0.00007566582],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7841792,0.001647663,0.2098586,0.003275272,0.000119524,0.000797992,0.00005536853,0.00006063266,0.000005751987],"genre_scores_gemma":[0.9819888,0.00003775698,0.01760909,0.0001937295,0.00004838191,0.00004792159,0.00004793233,0.000016125,0.00001021006],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5455217,"threshold_uncertainty_score":0.6221056,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03333688675085013,"score_gpt":0.3044555971099686,"score_spread":0.2711187103591184,"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."}}