{"id":"W3082023277","doi":"10.1109/embc44109.2020.9175489","title":"A Cascaded Deep-Learning Framework for Segmentation of Metastatic Brain Tumors Before and After Stereotactic Radiation Therapy","year":2020,"lang":"en","type":"article","venue":"","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Health Sciences Centre; Sunnybrook Health Science Centre; York University","funders":"","keywords":"Segmentation; Computer science; Context (archaeology); Radiation treatment planning; Radiation therapy; Artificial intelligence; Image segmentation; Deep learning; Magnetic resonance imaging; Medical imaging; Computer vision; Radiology; 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":[0.0002204863,0.00009867913,0.0002415158,0.0000554672,0.00003910379,0.00001972995,0.0000287896,0.0000351417,0.0001207591],"category_scores_gemma":[0.0009558719,0.00007657851,0.00005753456,0.0001162259,0.00004120706,0.00007790842,0.00001094955,0.0002357008,0.000001465981],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001695012,"about_ca_system_score_gemma":0.00002395143,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001343918,"about_ca_topic_score_gemma":0.000001215298,"domain_scores_codex":[0.999247,0.00006098732,0.0002327863,0.0001743867,0.0001536427,0.0001311733],"domain_scores_gemma":[0.9993537,0.0002971244,0.0001160755,0.00006150319,0.00003755961,0.0001340216],"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":[0.001363568,0.0001079064,0.1664208,0.0007768641,0.0004121149,0.00003754842,0.01970414,0.0001273,0.01079354,0.001626596,0.0002405089,0.7983891],"study_design_scores_gemma":[0.01585661,0.006117637,0.2984927,0.0005533932,0.0006026242,0.000143164,0.005211935,0.651592,0.0112149,0.005308642,0.004332058,0.0005743249],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7869893,0.0003358608,0.1989606,0.01308229,0.00003277966,0.0005188157,0.000001399502,0.00003738517,0.00004153257],"genre_scores_gemma":[0.9467444,0.00005434364,0.04749396,0.005445068,0.0001098634,0.00004184153,0.00002353208,0.00002340038,0.00006358238],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7978148,"threshold_uncertainty_score":0.3122781,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01450571880648044,"score_gpt":0.3106224994656707,"score_spread":0.2961167806591903,"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."}}