{"id":"W4414603236","doi":"10.1109/jbhi.2025.3614546","title":"A Review of Methods for Trustworthy AI in Medical Imaging: The FUTURE-AI Guidelines","year":2025,"lang":"en","type":"review","venue":"IEEE Journal of Biomedical and Health Informatics","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Guideline; Set (abstract data type); Domain (mathematical analysis); Trustworthiness; Medical imaging; Health care; Resource (disambiguation)","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":[0.01367048,0.0002407823,0.002590706,0.0005263152,0.00008672072,0.0000134916,0.0003031902,0.0003317932,0.00003365391],"category_scores_gemma":[0.003099497,0.0001230604,0.0004562438,0.0007282997,0.0002218081,0.00009678514,0.00003695648,0.001253484,0.0000011916],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00016035,"about_ca_system_score_gemma":0.01095533,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000035908,"about_ca_topic_score_gemma":0.000007143854,"domain_scores_codex":[0.9915115,0.0002789139,0.007243574,0.00009247263,0.0005382795,0.0003352808],"domain_scores_gemma":[0.9944137,0.001184601,0.002563566,0.0002403105,0.001047807,0.0005499772],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001083109,0.00004368921,0.000003900458,0.2720052,0.00003069529,0.000001142499,0.0001902836,1.582603e-8,3.313132e-9,0.00003909379,0.09196733,0.6357079],"study_design_scores_gemma":[0.0000853803,0.0002184469,0.000001495578,0.2669499,0.000260321,0.0004223377,0.0002747052,0.0003590021,2.158152e-7,0.0002298433,0.7311367,0.00006166727],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[3.497224e-7,0.8458936,0.01838412,0.1324892,0.002188026,0.001013004,0.00001111701,0.000003886189,0.00001670082],"genre_scores_gemma":[2.022416e-7,0.9153584,0.01387489,0.06867538,0.00200194,0.00003454651,0.00002829348,0.00001027748,0.00001603125],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.6391694,"threshold_uncertainty_score":0.9946516,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.319451869429438,"score_gpt":0.634220598539761,"score_spread":0.3147687291103229,"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."}}