{"id":"W4285129920","doi":"10.54364/aaiml.2022.1128","title":"Lesion Segmentation in Paediatric Epilepsy Utilizing Deep Learning Approaches","year":2022,"lang":"en","type":"article","venue":"Advances in Artificial Intelligence and Machine Learning","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"SickKids Foundation; Ontario Tech University","funders":"Natural Sciences and Engineering Research Council of Canada; Epilepsy Research Program of the Ontario Brain Institute; Government of Ontario; Nvidia","keywords":"Cortical dysplasia; Epilepsy; Lesion; Fluid-attenuated inversion recovery; Sørensen–Dice coefficient; Artificial intelligence; Pattern recognition (psychology); Computer science; Segmentation; Sequence (biology); Medicine; Radiology; Magnetic resonance imaging; Image segmentation; Pathology","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":[],"consensus_categories":[],"category_scores_codex":[0.0006725586,0.0001683375,0.0001886672,0.0003409453,0.000576326,0.00006719968,0.0004009798,0.00003326442,0.0000182235],"category_scores_gemma":[0.0001218634,0.0001873263,0.00003443577,0.001488126,0.00005515563,0.0009182243,0.0005007371,0.0009741962,0.000008298432],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001014125,"about_ca_system_score_gemma":0.00001547909,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004329201,"about_ca_topic_score_gemma":0.0002332139,"domain_scores_codex":[0.9979882,0.0003529993,0.0004605195,0.0005822812,0.0002509872,0.0003650612],"domain_scores_gemma":[0.9991795,0.0003852471,0.0001935315,0.0001720913,0.00001545203,0.00005419277],"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":[0.000009613245,0.00003048843,0.009653405,0.000005845191,6.166819e-7,0.00000600977,0.000882314,0.4785976,0.0001551436,0.02026508,1.183945e-7,0.4903938],"study_design_scores_gemma":[0.00005732,0.0001333203,0.0005635092,0.00001188348,0.000002456502,0.00001313632,0.002882492,0.9585721,0.0008977607,0.03406978,0.002566855,0.0002293051],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04382475,0.00751043,0.9469053,0.0003866726,0.0001843034,0.0003525002,6.025569e-7,0.000152646,0.0006828125],"genre_scores_gemma":[0.9773515,0.002964722,0.01932965,0.00007360544,0.00004890058,0.000171127,0.00001538985,0.00001508342,0.00003004906],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9335267,"threshold_uncertainty_score":0.7638946,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07133549752918397,"score_gpt":0.313559818283957,"score_spread":0.242224320754773,"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."}}