{"id":"W4408416336","doi":"10.1038/s41598-025-92954-1","title":"A robust deep learning approach for segmenting cortical and trabecular bone from 3D high resolution µCT scans of mouse bone","year":2025,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Orthopedic Infections and Treatments","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"Australian Research Council","keywords":"Segmentation; Computer science; Deep learning; Convolutional neural network; Artificial intelligence; Robustness (evolution); Cortical bone; High resolution; Trabecular bone; Tibia; Pattern recognition (psychology); X-ray microtomography; Anatomy; Pathology; Biology; Medicine; Radiology; Osteoporosis","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008643162,0.001086962,0.0006729157,0.001134185,0.0002900496,0.0007363169,0.001605431,0.001409567,0.001149816],"category_scores_gemma":[0.001157968,0.000714008,0.001077612,0.0008000024,0.0004893617,0.0006726807,0.001252286,0.001405524,0.0006763416],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008566137,"about_ca_system_score_gemma":0.001415791,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008817908,"about_ca_topic_score_gemma":0.0229665,"domain_scores_codex":[0.9996265,0.00004624154,0.00001889233,0.0001396647,0.0001139312,0.00005465217],"domain_scores_gemma":[0.9996674,0.00009526091,0.00005420675,0.00004619045,0.0001024624,0.00003449664],"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":[0.0004322103,0.0002506023,0.006618177,0.000323181,0.0003143104,0.0003671722,0.0001337267,0.3913311,0.1019264,0.003461506,0.01090506,0.4839365],"study_design_scores_gemma":[0.00001522828,0.0000762486,0.001284496,0.00002300096,0.00004536443,0.0001737481,0.0000210457,0.9781287,0.0156823,0.002141953,0.002385691,0.00002215003],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03773071,0.0009134447,0.9538195,0.0002603506,0.00006831901,0.00008706575,0.0009730298,0.004696883,0.001450621],"genre_scores_gemma":[0.3906919,0.0009835084,0.5921544,0.0007336895,0.00007400297,0.000301504,0.006282813,0.0005916993,0.008186405],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008817908,"threshold_uncertainty_score":0.01753318,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01588835236038165,"score_gpt":0.245912051962133,"score_spread":0.2300236996017514,"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."}}