{"id":"W4210461044","doi":"10.1101/2022.01.25.477747","title":"Deep Learning Characterization of Brain Tumours With Diffusion Weighted Imaging","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Mathematical Biology Tumor Growth","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"St. Michael's Hospital; Artificial Intelligence in Medicine (Canada); University of Toronto; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Deep learning; Glioblastoma; Preprocessor; Computer science; Pipeline (software); Segmentation; Relevance (law); Machine learning; Projection (relational algebra); Diffusion MRI; Pattern recognition (psychology); Medicine; Radiology; Cancer research; Magnetic resonance imaging; Algorithm","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001073448,0.0006581665,0.001022332,0.0004123563,0.0002572754,0.00008478879,0.0006982253,0.0002832059,0.0004956651],"category_scores_gemma":[0.0008669422,0.0006092096,0.0001708703,0.0005997542,0.000212719,0.0001345473,0.0009647302,0.001396335,0.00001512157],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000250967,"about_ca_system_score_gemma":0.0002381993,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001030234,"about_ca_topic_score_gemma":8.083082e-7,"domain_scores_codex":[0.9963968,0.0005165334,0.0009024512,0.0009580177,0.0006417859,0.0005843745],"domain_scores_gemma":[0.9963903,0.0004840145,0.001396775,0.001138183,0.0003913311,0.0001994147],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001059215,0.0004266186,0.03857368,0.001828445,0.0001524845,0.0001025856,0.00009359651,0.000009250413,0.9426088,0.01605527,0.00003971637,0.000003688624],"study_design_scores_gemma":[0.005082958,0.0007445151,0.368872,0.0046877,0.001499289,9.176244e-7,0.0001225975,0.03728847,0.5716503,0.00143812,0.002790802,0.005822353],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9749314,0.00008760977,0.02272559,0.0003492767,0.00030571,0.000926605,0.00007396423,0.0005547507,0.00004509638],"genre_scores_gemma":[0.9851519,0.00003417392,0.01406102,0.0001015696,0.0001485991,0.0002507479,0.000003781678,0.0002265449,0.00002163838],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3709584,"threshold_uncertainty_score":0.9996359,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01084127584410077,"score_gpt":0.2265560742300785,"score_spread":0.2157147983859777,"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."}}