{"id":"W4308170338","doi":"10.48550/arxiv.2111.14959","title":"Improving the Segmentation of Pediatric Low-Grade Gliomas through\\n Multitask Learning","year":2021,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Brain Tumor Detection and Classification","field":"Neuroscience","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Segmentation; Deep learning; Computer science; Magnetic resonance imaging; Artificial intelligence; Multi-task learning; Neuroradiology; Glioma; Task (project management); Brain tumor; Classifier (UML); Machine learning; Medicine; Radiology; Psychology; Neuroscience; Pathology; Neurology; Engineering","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005503664,0.000890399,0.000431062,0.0007043775,0.0003115498,0.0007015123,0.0008849001,0.001093342,0.0009542056],"category_scores_gemma":[0.00159435,0.000288678,0.0008128498,0.0004708518,0.0003185627,0.0006708138,0.000862111,0.0008364441,0.0007564851],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000745302,"about_ca_system_score_gemma":0.001009863,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008681943,"about_ca_topic_score_gemma":0.01537174,"domain_scores_codex":[0.9997402,0.00004324329,0.0000147168,0.0001028382,0.00004694158,0.00005217022],"domain_scores_gemma":[0.9995568,0.0001683943,0.0000688715,0.00005218404,0.0001025313,0.0000511587],"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":[0.0003904807,0.0003200189,0.02000168,0.0001933556,0.0001748971,0.0004715377,0.000268341,0.3839628,0.04393149,0.00279245,0.01273861,0.5347543],"study_design_scores_gemma":[0.00001000628,0.00006796391,0.002568771,0.00001396594,0.00002321944,0.0001159817,0.00002929764,0.9844515,0.009348617,0.001899866,0.001460412,0.00001046408],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3236006,0.001636782,0.6626109,0.001061818,0.0001613084,0.0001313124,0.001061997,0.005777523,0.003957762],"genre_scores_gemma":[0.8449008,0.0006064537,0.1450305,0.0005125217,0.0001193923,0.0001190633,0.003194565,0.0003553893,0.005161397],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008681943,"threshold_uncertainty_score":0.01726282,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0848843780880784,"score_gpt":0.212624299505927,"score_spread":0.1277399214178486,"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."}}