{"id":"W4411331319","doi":"10.1016/j.compmedimag.2025.102578","title":"Classification of glioma grade and Ki-67 level prediction in MRI data: A SHAP-driven interpretation","year":2025,"lang":"en","type":"article","venue":"Computerized Medical Imaging and Graphics","topic":"Brain Tumor Detection and Classification","field":"Neuroscience","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Regina","funders":"","keywords":"Glioma; Interpretation (philosophy); Computer science; Artificial intelligence; Nuclear medicine; Pattern recognition (psychology); Medicine; Cancer research","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":[0.0004363315,0.0001079102,0.0001710962,0.0003926025,0.00009959788,0.00005844073,0.0002392197,0.00007952107,0.000004393633],"category_scores_gemma":[0.0006042126,0.0001049441,0.0000222311,0.0006278666,0.0004506463,0.0002628642,0.0001636718,0.000254144,6.12497e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001649499,"about_ca_system_score_gemma":0.000060521,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001923156,"about_ca_topic_score_gemma":0.00001395377,"domain_scores_codex":[0.9985511,0.0001932286,0.0003781763,0.0004777889,0.000268202,0.0001314711],"domain_scores_gemma":[0.9991564,0.0003078809,0.0001194629,0.0002875927,0.00003949796,0.00008921437],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002753309,0.0004921085,0.0340692,0.0005022084,0.00002846789,0.00003547762,0.00147199,0.00001254863,0.505501,0.04415229,0.002333385,0.411126],"study_design_scores_gemma":[0.00099655,0.00001878748,0.1595871,0.0002370669,0.0000135202,0.00004302296,0.00008703419,0.8343628,0.001847463,0.001946348,0.0007834909,0.00007684158],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6027483,0.0002375495,0.3862014,0.009388488,0.0007409378,0.0003037636,0.00005141366,0.0001308073,0.0001974156],"genre_scores_gemma":[0.9982594,0.0003067517,0.0006381698,0.000693312,0.00003163135,0.00001409091,0.00003350289,0.000006668708,0.00001651628],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8343503,"threshold_uncertainty_score":0.4279495,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06090363175672895,"score_gpt":0.322569541592251,"score_spread":0.261665909835522,"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."}}