{"id":"W3158565540","doi":"10.1038/s41598-021-93804-6","title":"Distinct tumor signatures using deep learning-based characterization of the peritumoral microenvironment in glioblastomas and brain metastases","year":2021,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Advanced Neuroimaging Techniques and Applications","field":"Medicine","cited_by":31,"is_retracted":false,"has_abstract":true,"ca_institutions":"Synaptive (Canada)","funders":"National Institute of Neurological Disorders and Stroke; National Institutes of Health","keywords":"Diffusion MRI; Medicine; Convolutional neural network; Tumour heterogeneity; Pathology; Radiology; Magnetic resonance imaging; Artificial intelligence; Computer science; Cancer; Internal medicine","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":[0.0002400532,0.0000744338,0.0001334822,0.00006076681,0.0001272466,0.00003080069,0.00003228754,0.00001463991,0.00002777333],"category_scores_gemma":[0.0001731177,0.00005757415,0.00004334691,0.0003218406,0.0002256576,0.00004198974,0.00006221265,0.0001143756,1.490358e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003054733,"about_ca_system_score_gemma":0.00006499646,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004627392,"about_ca_topic_score_gemma":0.000007158564,"domain_scores_codex":[0.9990734,0.00005096623,0.0002448327,0.0003422796,0.0001801933,0.0001082637],"domain_scores_gemma":[0.9993588,0.00002036761,0.000198837,0.0003441839,0.00004199018,0.000035774],"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":[0.000006134534,0.00007864759,0.0401833,0.00003183356,0.000001850229,0.0001872485,0.00003572743,0.0002208093,0.9587542,0.000009830687,0.0000179398,0.0004724651],"study_design_scores_gemma":[0.0001609162,0.00002474693,0.2344875,0.0001411354,0.00003174422,0.0005010644,0.00003193146,0.005199753,0.7512062,0.0002326657,0.007898613,0.00008366536],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9958059,0.000096194,0.003158188,0.0005400798,0.0001249582,0.0002371029,0.000003902457,0.00002202323,0.00001164117],"genre_scores_gemma":[0.9972438,0.000001339511,0.002412297,0.00009598523,0.000009218697,0.00001176399,0.0000529988,0.000009890321,0.0001626906],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.207548,"threshold_uncertainty_score":0.2347806,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02172553104651112,"score_gpt":0.2862008277712664,"score_spread":0.2644752967247553,"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."}}