{"id":"W4405387929","doi":"10.1093/noajnl/vdae205","title":"Pediatric brain tumor classification using deep learning on MR images with age fusion","year":2024,"lang":"en","type":"article","venue":"Neuro-Oncology Advances","topic":"Brain Tumor Detection and Classification","field":"Neuroscience","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Engineering Link (Canada)","funders":"Linköpings Universitet; Barncancerfonden; Region Östergötland","keywords":"Artificial intelligence; Medulloblastoma; Magnetic resonance imaging; Brain tumor; Principal component analysis; Deep learning; Pattern recognition (psychology); Computer science; Feature (linguistics); Contrast (vision); Medicine; Nuclear medicine; Radiology; Pathology","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":[0.0002536974,0.0002306154,0.0002050785,0.0003439366,0.0004815191,0.0001316315,0.0002152245,0.00008859092,0.00008119553],"category_scores_gemma":[0.000984457,0.0001930665,0.0000618941,0.0009334698,0.0002410729,0.0005097309,0.00004000753,0.0007025162,0.0001701779],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001596786,"about_ca_system_score_gemma":0.0001004945,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001932917,"about_ca_topic_score_gemma":0.00001005813,"domain_scores_codex":[0.9976117,0.0005571037,0.0002934817,0.0008725999,0.0003253085,0.0003398129],"domain_scores_gemma":[0.9977363,0.001687331,0.0002043546,0.0002367681,0.00003874199,0.00009649516],"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":[0.0001253555,0.00008170162,0.0006362526,0.00005370339,0.000001913998,0.0004002453,0.0001568441,0.001611807,0.9488258,0.001594384,0.000168089,0.04634389],"study_design_scores_gemma":[0.00150901,0.003413835,0.01466985,0.00009979122,0.0001240755,0.00153114,0.0008144442,0.08546954,0.4681138,0.001328086,0.4219275,0.0009989403],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9770474,0.0005849238,0.006767571,0.00378165,0.001936903,0.0005370129,0.000006145735,0.001002667,0.008335756],"genre_scores_gemma":[0.9965027,0.000376437,0.0003876797,0.001907301,0.0003941419,0.00006399306,0.000004184721,0.00004984932,0.0003137069],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4807121,"threshold_uncertainty_score":0.7873023,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03553759199890959,"score_gpt":0.3162248819851182,"score_spread":0.2806872899862086,"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."}}