{"id":"W3193929012","doi":"10.1101/2021.08.17.21262189","title":"Detecting orientation of Brain MR scans using deep learning","year":2021,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Orientation (vector space); Coronal plane; Artificial intelligence; Rendering (computer graphics); Computer science; Sagittal plane; DICOM; Inference; Deep learning; Neuroimaging; Computer vision; Pattern recognition (psychology); Psychology; Medicine; Radiology; Neuroscience; Mathematics","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":[0.0003890612,0.0008667946,0.0004732258,0.001696852,0.0002584244,0.0007920684,0.000693658,0.001176913,0.0009777881],"category_scores_gemma":[0.001707592,0.0003856921,0.0004728957,0.0009750206,0.0004712386,0.0006313451,0.0006764144,0.0009645724,0.001002751],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000540306,"about_ca_system_score_gemma":0.0007039255,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00345639,"about_ca_topic_score_gemma":0.006006661,"domain_scores_codex":[0.99975,0.00004539083,0.00001469159,0.0000747833,0.00007089537,0.00004431267],"domain_scores_gemma":[0.9995703,0.0001220555,0.0001103352,0.00006250081,0.00009491958,0.00003976182],"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":[0.0003307864,0.0002135334,0.008434459,0.0001313123,0.00009361673,0.0004692746,0.0001231829,0.149492,0.08147266,0.005115709,0.01283741,0.741286],"study_design_scores_gemma":[0.000008288019,0.00006204117,0.002437512,0.0000308144,0.00001962928,0.0003690613,0.00003534305,0.9671053,0.01878798,0.008483573,0.002642412,0.00001814224],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06743719,0.001590478,0.9239835,0.0009174042,0.0001248745,0.00007083501,0.0005462344,0.002965525,0.002363962],"genre_scores_gemma":[0.5704586,0.00170701,0.4201734,0.0006850237,0.0002740232,0.00009869271,0.001752699,0.0002648211,0.004585682],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00345639,"threshold_uncertainty_score":0.006872535,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0316864565828732,"score_gpt":0.3202824895758404,"score_spread":0.2885960329929672,"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."}}