{"id":"W4313562246","doi":"10.1038/s41598-022-27350-0","title":"Automatic segmentation of trabecular and cortical compartments in HR-pQCT images using an embedding-predicting U-Net and morphological post-processing","year":2023,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Medical Imaging Techniques and Applications","field":"Medicine","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"Alberta Bone and Joint Health Institute; University of Calgary","funders":"Canadian Institutes of Health Research; Arthritis Society; University of Calgary; Alberta Student Aid","keywords":"Embedding; Segmentation; Computer science; Artificial intelligence; Anatomy; Neuroscience; Pattern recognition (psychology); Biology","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":[0.001898204,0.0008827283,0.000769583,0.001344219,0.0004909866,0.001375571,0.001205513,0.001122179,0.001564691],"category_scores_gemma":[0.002918778,0.0004617806,0.0006662497,0.0006997004,0.0005973894,0.0007530169,0.0007907569,0.0005215093,0.0008022513],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006750594,"about_ca_system_score_gemma":0.001275853,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00525377,"about_ca_topic_score_gemma":0.008372825,"domain_scores_codex":[0.9993091,0.0001252671,0.00005632038,0.0002951255,0.0001539886,0.00006012238],"domain_scores_gemma":[0.9990786,0.0002998543,0.0001410296,0.0001359577,0.0003016276,0.00004281455],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001136709,0.0003193536,0.01183759,0.0002648627,0.0001531791,0.000361711,0.0002385916,0.1579471,0.1306361,0.001956454,0.003706392,0.691442],"study_design_scores_gemma":[0.00001112965,0.00006414097,0.003130742,0.0000128092,0.00001916109,0.0001087474,0.00002976121,0.970213,0.02509215,0.000558789,0.0007455577,0.00001406472],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1705765,0.0003455654,0.820498,0.0001627279,0.0001009253,0.0003256224,0.0004897378,0.006265953,0.001234961],"genre_scores_gemma":[0.3889352,0.0001302755,0.6071377,0.0001045454,0.00002609058,0.0002211134,0.0008450028,0.0002965016,0.002303619],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00525377,"threshold_uncertainty_score":0.01044637,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04897284393038666,"score_gpt":0.379313346704692,"score_spread":0.3303405027743054,"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."}}