{"id":"W4389213238","doi":"10.1007/978-3-031-47401-9_12","title":"Cross-Task Attention Network: Improving Multi-task Learning for Medical Imaging Applications","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":16,"is_retracted":false,"has_abstract":false,"ca_institutions":"Vector Institute; Princess Margaret Cancer Centre; University Health Network; University of Toronto","funders":"","keywords":"Computer science; Leverage (statistics); Multi-task learning; Artificial intelligence; Task (project management); Medical imaging; Machine learning; Deep learning; Segmentation","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":[0.002053461,0.002118993,0.001600174,0.0009767374,0.0004722522,0.000999663,0.00287637,0.002570414,0.006928454],"category_scores_gemma":[0.003428447,0.0006671854,0.001130278,0.001400702,0.0004003391,0.001763845,0.002001054,0.002848304,0.002918087],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007228526,"about_ca_system_score_gemma":0.0009266303,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01035317,"about_ca_topic_score_gemma":0.01081907,"domain_scores_codex":[0.9992893,0.000151431,0.0000308928,0.0002449818,0.0001746653,0.0001087884],"domain_scores_gemma":[0.998836,0.0005546091,0.00005813226,0.0001505665,0.0003193922,0.00008145258],"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":[0.0003376484,0.0002687904,0.0006406389,0.0001295465,0.0002088163,0.0001037489,0.000042637,0.108401,0.01602552,0.001685753,0.01882384,0.853332],"study_design_scores_gemma":[0.0000141613,0.00006303508,0.0003482362,0.00001070531,0.0000483594,0.00004447839,0.00000753849,0.99072,0.004767852,0.002332695,0.001631855,0.00001103555],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01623016,0.00349532,0.9706692,0.0003951188,0.0005332904,0.000068249,0.0003678239,0.005118897,0.00312195],"genre_scores_gemma":[0.3382053,0.002764333,0.624228,0.001540304,0.0008551339,0.000307262,0.002724348,0.001519576,0.02785577],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01035317,"threshold_uncertainty_score":0.02317798,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01318802528416951,"score_gpt":0.3121318425278408,"score_spread":0.2989438172436713,"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."}}