{"id":"W6930829717","doi":"10.5281/zenodo.14755838","title":"Automatic segmentation of trabecular and cortical compartments in HR-pQCT images using an embedding-predicting U-Net and morphological post-processing","year":2025,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Sulfur Compounds in Biology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Segmentation; Image segmentation; Pattern recognition (psychology); Image processing; Medical imaging","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":[0.001508613,0.003798708,0.002416935,0.003485117,0.0008575113,0.002223802,0.004340092,0.003583892,0.01075065],"category_scores_gemma":[0.002550199,0.001180513,0.003177254,0.002777892,0.0007033974,0.000869918,0.002206439,0.001979929,0.01943634],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002175076,"about_ca_system_score_gemma":0.002188506,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02355983,"about_ca_topic_score_gemma":0.0717274,"domain_scores_codex":[0.9989613,0.0001335647,0.0001002429,0.0004264362,0.0002450882,0.0001332847],"domain_scores_gemma":[0.9991652,0.0002459392,0.00007002449,0.0002246582,0.0002387516,0.00005556578],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001494084,0.0004795907,0.01032091,0.003783121,0.000734157,0.0007003108,0.0001266366,0.01798134,0.009404504,0.001816451,0.8354084,0.1177504],"study_design_scores_gemma":[0.00242646,0.0006571488,0.04984603,0.001863159,0.001180475,0.004929712,0.0006421268,0.2252411,0.03973004,0.02475219,0.6481227,0.0006088057],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.01809651,0.003451754,0.02139718,0.0006619131,0.0004320847,0.0003607644,0.9331335,0.01878519,0.003681069],"genre_scores_gemma":[0.02032436,0.0005746683,0.02738868,0.0001972905,0.00004459491,0.0004182307,0.9478816,0.00070873,0.002461806],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.02355983,"threshold_uncertainty_score":0.04684544,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03152160334567312,"score_gpt":0.3105650486357605,"score_spread":0.2790434452900874,"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."}}