{"id":"W4400575212","doi":"10.1007/s10278-024-01182-y","title":"Summary of the National Cancer Institute 2023 Virtual Workshop on Medical Image De-identification—Part 1: Report of the MIDI Task Group - Best Practices and Recommendations, Tools for Conventional Approaches to De-identification, International Approaches to De-identification, and Industry Panel on Image De-identification","year":2024,"lang":"en","type":"editorial","venue":"Journal of Imaging Informatics in Medicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"National Institutes of Health; National Cancer Institute; Frederick National Laboratory for Cancer Research","keywords":"Identification (biology); Task (project management); MIDI; Task group; Computer science; Best practice; Informatics; Data science; Engineering management; Engineering; Political science; Systems engineering","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":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.01423438,0.0003633729,0.0005350548,0.0009965828,0.0003116859,0.0006879638,0.00198134,0.0004601236,0.00001631747],"category_scores_gemma":[0.02489419,0.0002869099,0.0001623435,0.001027377,0.0006246411,0.002217868,0.0004366868,0.001858079,0.00000321522],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001510694,"about_ca_system_score_gemma":0.002499583,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00010873,"about_ca_topic_score_gemma":0.00008902637,"domain_scores_codex":[0.9925746,0.0003566507,0.003450581,0.0004980473,0.00277344,0.0003467075],"domain_scores_gemma":[0.9895926,0.002347783,0.005594341,0.0006869339,0.001543304,0.0002350552],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000224659,0.0004367955,0.001059025,0.001102487,0.0004385569,0.00001073567,0.007425613,0.002760163,0.001695053,0.004857871,0.9426001,0.03738897],"study_design_scores_gemma":[0.00555549,0.0005473681,0.03266769,0.02705642,0.001496739,0.001984831,0.01580784,0.1945974,0.009113539,0.02118929,0.6881061,0.001877207],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01276122,0.0006076318,0.6148096,0.1473469,0.2205787,0.002488405,0.0007055784,0.00005706274,0.0006449274],"genre_scores_gemma":[0.4682956,0.00916019,0.1643813,0.007429032,0.3278109,0.004995167,0.003206646,0.0005251821,0.01419593],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4555344,"threshold_uncertainty_score":0.9999583,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1616151152043639,"score_gpt":0.3749821189076779,"score_spread":0.213367003703314,"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."}}