{"id":"W4297093096","doi":"10.1016/j.bone.2022.116571","title":"Open-source image analysis tool for the identification and quantification of cortical interruptions and bone erosions in high-resolution peripheral quantitative computed tomography images of patients with rheumatoid arthritis","year":2022,"lang":"en","type":"article","venue":"Bone","topic":"Rheumatoid Arthritis Research and Therapies","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Alberta Bone and Joint Health Institute; University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institutes of Health Research; Arthritis Society","keywords":"Bone erosion; Visualization; Quantitative computed tomography; Erosion; Medicine; Rheumatoid arthritis; Image analysis; Computer science; Image processing; Radiology; Computer vision; Artificial intelligence; Image (mathematics); Pathology; Digital image processing; Geology; Internal medicine; Bone density","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002261711,0.001264079,0.0009261801,0.003285463,0.0002855969,0.001014475,0.001222857,0.0008477943,0.01599556],"category_scores_gemma":[0.006598099,0.0007726284,0.001189419,0.001528932,0.0002862943,0.0008594175,0.001615732,0.0007592834,0.005783618],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003284834,"about_ca_system_score_gemma":0.0009149239,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009151105,"about_ca_topic_score_gemma":0.001817747,"domain_scores_codex":[0.9990202,0.0001706251,0.0001395627,0.0002234126,0.0003788702,0.00006733547],"domain_scores_gemma":[0.9964373,0.001673524,0.0005356147,0.0003293605,0.0008590394,0.0001652147],"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":[0.003268178,0.000519545,0.02606353,0.002146872,0.0006447176,0.001449205,0.0008457875,0.006513212,0.1179777,0.002168208,0.084437,0.753966],"study_design_scores_gemma":[0.001803205,0.00102727,0.2851094,0.001080131,0.0008182576,0.01139149,0.0004093447,0.2406197,0.2467739,0.009123224,0.2011131,0.0007310435],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0577969,0.001276829,0.7590944,0.000301648,0.0001604869,0.001434455,0.02074876,0.154239,0.004947503],"genre_scores_gemma":[0.1489609,0.0006305378,0.7992863,0.0003128501,0.0001077545,0.003099531,0.02303042,0.01822145,0.006350354],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01599556,"threshold_uncertainty_score":0.05351049,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01604795913147472,"score_gpt":0.2833327933662891,"score_spread":0.2672848342348144,"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."}}