{"id":"W3012075782","doi":"10.1002/mp.14127","title":"Creation of an anthropomorphic CT head phantom for verification of image segmentation","year":2020,"lang":"en","type":"article","venue":"Medical Physics","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of Biomedical Imaging and Bioengineering; Canadian Institutes of Health Research; Genentech; National Institutes of Health; University of Liverpool; National Institute on Aging; National Institute for Health and Care Research; Northern California Institute for Research and Education; Alzheimer's Disease Neuroimaging Initiative; GE Healthcare; Pfizer; Biogen; BioClinica; Roche; University of Southern California; Novartis Pharmaceuticals Corporation; U.S. Department of Defense; Eli Lilly and Company; Bristol-Myers Squibb; Merck; Alzheimer's Drug Discovery Foundation; Takeda Pharmaceutical Company; AbbVie; Fujirebio Europe; Alzheimer's Association","keywords":"Imaging phantom; Segmentation; Hounsfield scale; Computer science; Artificial intelligence; Voxel; Contouring; Image segmentation; Biomedical engineering; Computer vision; Nuclear medicine; Medicine; Computed tomography; Radiology; Computer graphics (images)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003021264,0.00008482189,0.0001915012,0.00002653297,0.00003475026,0.00001721425,0.0004261464,0.00003398071,0.00006127847],"category_scores_gemma":[0.0003875599,0.00008061963,0.00005289223,0.0003026458,0.0002184361,0.0005745236,0.00004824643,0.00007571588,0.000004358589],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001925714,"about_ca_system_score_gemma":0.0001122308,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003089157,"about_ca_topic_score_gemma":9.374166e-7,"domain_scores_codex":[0.9985187,0.00007255071,0.0003787339,0.0002377396,0.0006829404,0.0001093391],"domain_scores_gemma":[0.9990388,0.0001274334,0.0002418245,0.0002322081,0.0001876149,0.0001720794],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002700992,0.0003722603,0.00008514935,0.0002399116,0.00001740857,0.00000295145,0.001344199,0.000004599043,0.2273429,0.002467212,0.0009842872,0.7671121],"study_design_scores_gemma":[0.0005704814,0.0003765909,0.0001911805,0.00003507842,0.00001092296,0.000001003878,0.00005256821,0.04746135,0.9486671,0.002524024,0.00003691951,0.0000727697],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01374704,0.0000152331,0.9842497,0.001366106,0.00006933596,0.0003383411,0.00001447099,0.0001031357,0.00009662637],"genre_scores_gemma":[0.7911761,0.00002732503,0.2077852,0.0006932488,0.0001339465,0.00004049778,0.0001293853,0.0000101136,0.000004207931],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.777429,"threshold_uncertainty_score":0.3287573,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04015493706732023,"score_gpt":0.360070164925745,"score_spread":0.3199152278584247,"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."}}