{"id":"W4387422461","doi":"10.1007/978-3-031-44917-8_16","title":"Combining Weakly Supervised Segmentation with Multitask Learning for Improved 3D MRI Brain Tumour Classification","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Vector Institute; University of Toronto; Hospital for Sick Children","funders":"","keywords":"Computer science; Artificial intelligence; Segmentation; Leverage (statistics); Pipeline (software); Focus (optics); Pattern recognition (psychology); Machine learning; Multi-task learning; Image segmentation; Contextual image classification; Pixel; Region of interest; Deep learning; Task (project management); Medical imaging; Computer vision; Image (mathematics)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002087502,0.001929131,0.002632452,0.002329706,0.0007234218,0.00223264,0.002628362,0.00261501,0.003086961],"category_scores_gemma":[0.003206838,0.000883048,0.002400407,0.002411028,0.0006704889,0.001694878,0.002961997,0.00163909,0.003344752],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005373931,"about_ca_system_score_gemma":0.001118067,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003873558,"about_ca_topic_score_gemma":0.006879127,"domain_scores_codex":[0.9988481,0.0002725171,0.00008005389,0.000312384,0.0003225157,0.0001643712],"domain_scores_gemma":[0.9980975,0.0007618242,0.0001381646,0.0003673965,0.0005103048,0.0001248258],"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":[0.0004974168,0.000308778,0.001873946,0.0003442631,0.0002990434,0.0001767881,0.0001379318,0.08503418,0.06549351,0.002175665,0.009116656,0.834542],"study_design_scores_gemma":[0.00001203933,0.00007135051,0.0007040455,0.00001498926,0.00005359637,0.000108898,0.00002349363,0.9846148,0.008947697,0.00394828,0.001479966,0.000020805],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01827975,0.0007354716,0.9761335,0.0002208307,0.0001248477,0.00007162366,0.0003234605,0.00289236,0.001218114],"genre_scores_gemma":[0.2828078,0.0007953088,0.7027237,0.000600604,0.0004556116,0.0002979067,0.003599111,0.001250993,0.007468885],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003873558,"threshold_uncertainty_score":0.01103991,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0275006106379515,"score_gpt":0.2729937628709777,"score_spread":0.2454931522330261,"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."}}