{"id":"W4415117676","doi":"10.1093/ehjdh/ztaf116","title":"Deep learning-based quantification of epicardial adipose tissue volume from non-contrast computed tomography images: a multi-centre study","year":2025,"lang":"en","type":"article","venue":"European Heart Journal - Digital Health","topic":"Cardiovascular Disease and Adiposity","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Naval Medical Research Center; National Medical Research Council; Medical Research Council; Singapore Energy Centre; Duke-NUS Medical School","keywords":"Computed tomography; Volume (thermodynamics); Adipose tissue; Epicardial adipose tissue; Tomography","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":[0.0007006228,0.0002368281,0.0007383493,0.0002978363,0.0002749841,0.0001747996,0.000147756,0.00004004159,0.00002438393],"category_scores_gemma":[0.000140747,0.0002222138,0.0006362858,0.0004342637,0.00008586911,0.0001877927,0.00005850002,0.0005981618,0.00008671078],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006630408,"about_ca_system_score_gemma":0.0002885253,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007705409,"about_ca_topic_score_gemma":0.000006734107,"domain_scores_codex":[0.997255,0.0007692883,0.0007735281,0.000395924,0.0004321954,0.0003741088],"domain_scores_gemma":[0.9984161,0.0001085593,0.0002539473,0.0004280709,0.000249756,0.0005436274],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001364129,0.006524192,0.8834128,0.0003805685,0.002202412,0.000916846,0.000992307,0.002387827,0.0012994,0.000002351963,0.004343104,0.09617404],"study_design_scores_gemma":[0.005791534,0.0007602127,0.9835863,0.0005654996,0.0003706189,0.00006099024,0.0004125907,0.003050819,0.0002536946,0.000002322993,0.004973351,0.0001720936],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9038321,0.006962264,0.08417892,0.001799004,0.0005750919,0.001645045,0.0001335643,0.000155067,0.0007189345],"genre_scores_gemma":[0.9980915,0.00002734405,0.0006794172,0.0004346999,0.0002904614,0.000001755278,0.0001714354,0.00004044876,0.0002629973],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1001735,"threshold_uncertainty_score":0.9061617,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01761559718864034,"score_gpt":0.2934292360366167,"score_spread":0.2758136388479764,"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."}}