{"id":"W4297179926","doi":"10.1016/j.imu.2022.101091","title":"Multi-view parallel vertebra segmentation and identification on computed tomography (CT) images","year":2022,"lang":"en","type":"article","venue":"Informatics in Medicine Unlocked","topic":"Medical Imaging and Analysis","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Memorial University of Newfoundland; Simon Fraser University","funders":"Alzheimer's Disease Research Center, Wake Forest School of Medicine; Canadian Institutes of Health Research; Claude Pepper Older Americans Independence Center, Wake Forest School of Medicine; Michael Smith Health Research BC; Natural Sciences and Engineering Research Council of Canada; Wake Forest School of Medicine; Compute Canada","keywords":"Artificial intelligence; Segmentation; Vertebra; Computer science; Convolutional neural network; Pixel; Pattern recognition (psychology); Sagittal plane; Coronal plane; Concatenation (mathematics); Identification (biology); Computer vision; Mathematics; Medicine; Anatomy","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":[0.001181996,0.001046636,0.000943209,0.00324982,0.000528697,0.001733511,0.001312686,0.001799946,0.002736078],"category_scores_gemma":[0.002293757,0.0006461426,0.001323537,0.001370906,0.0004473559,0.001000763,0.001130936,0.0007335428,0.002283053],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006233512,"about_ca_system_score_gemma":0.001103267,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007387032,"about_ca_topic_score_gemma":0.02147356,"domain_scores_codex":[0.9988512,0.0001070454,0.00008717368,0.0004232082,0.0004081311,0.0001232163],"domain_scores_gemma":[0.9992449,0.0001449645,0.0001327101,0.0001892264,0.0002437214,0.00004454789],"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":[0.0009149318,0.0003405923,0.02852246,0.0006527365,0.0005035397,0.0009601035,0.0002862284,0.06683319,0.1384733,0.001755938,0.01206554,0.7486914],"study_design_scores_gemma":[0.00005719181,0.0003561664,0.0386179,0.0001864898,0.0002437052,0.004200277,0.0002951874,0.8361598,0.1027964,0.003728461,0.01325975,0.00009864158],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2313031,0.002896985,0.7392464,0.000524438,0.0001910687,0.0006738389,0.005389411,0.01348969,0.006285184],"genre_scores_gemma":[0.4713068,0.001447555,0.509995,0.0002094158,0.00008943521,0.0002049429,0.01067404,0.0006710514,0.005401821],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007387032,"threshold_uncertainty_score":0.01468807,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0148186688981244,"score_gpt":0.2633636192872688,"score_spread":0.2485449503891444,"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."}}