{"id":"W4404421282","doi":"10.1016/j.jbo.2024.100649","title":"A patch-based deep learning MRI segmentation model for improving efficiency and clinical examination of the spinal tumor","year":2024,"lang":"en","type":"article","venue":"Journal of bone oncology","topic":"Medical Imaging and Analysis","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"Xiangya Hospital, Central South University; Central South University","keywords":"Medicine; Segmentation; Deep learning; Magnetic resonance imaging; Radiology; Medical physics; Artificial intelligence","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001262521,0.00005085869,0.0001986111,0.0001015543,0.00003278155,0.00001389149,0.00004573239,0.00004285551,0.000003424322],"category_scores_gemma":[0.0002738604,0.00003489749,0.0001191848,0.0001005367,0.00005311776,0.00005674,0.000009481673,0.0002656174,2.614405e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006479854,"about_ca_system_score_gemma":0.00008320347,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002457507,"about_ca_topic_score_gemma":0.000004103213,"domain_scores_codex":[0.9991984,0.00007434491,0.0004550602,0.00006354327,0.0001240118,0.0000845979],"domain_scores_gemma":[0.9995071,0.000193658,0.0001535431,0.000035938,0.00006719708,0.00004258841],"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":[0.00003202725,0.00009047221,0.001478636,0.0004845474,0.0000809384,0.00002392643,0.0005415559,0.3721224,0.02068719,0.00005005853,0.00007236496,0.6043358],"study_design_scores_gemma":[0.0004226909,0.0003088761,0.0008423051,0.00009881784,0.0001636007,0.00002914873,0.0001396879,0.9974245,0.0003973541,0.00006487838,0.000073393,0.00003476902],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4099097,0.0006381874,0.5888919,0.0002754477,0.000204014,0.00003901725,4.910988e-7,0.00000978328,0.00003145373],"genre_scores_gemma":[0.9938242,0.00003839967,0.005962785,0.00003783089,0.0001044086,0.000002070079,5.122158e-7,0.000007900289,0.00002189223],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6253021,"threshold_uncertainty_score":0.1423078,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01785050868998586,"score_gpt":0.3220740754942212,"score_spread":0.3042235668042354,"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."}}