{"id":"W4312408638","doi":"10.1007/978-3-031-17899-3_7","title":"Weakly Supervised Intracranial Hemorrhage Segmentation Using Hierarchical Combination of Attention Maps from a Swin Transformer","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Intracerebral and Subarachnoid Hemorrhage Research","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Segmentation; Artificial intelligence; Computer science; Binary classification; Transformer; Pattern recognition (psychology); Categorical variable; Supervised learning; Machine learning; Artificial neural network; Support vector machine","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":[0.0005026262,0.0009196624,0.001148449,0.001110822,0.0003637196,0.001095812,0.001072627,0.001010511,0.00221836],"category_scores_gemma":[0.001038237,0.0004807115,0.00112035,0.001008632,0.000382344,0.001112667,0.001089006,0.000896442,0.001167867],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004071679,"about_ca_system_score_gemma":0.0008084317,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003694179,"about_ca_topic_score_gemma":0.006377757,"domain_scores_codex":[0.9997666,0.00004242358,0.00001276678,0.0000731403,0.000053541,0.00005149803],"domain_scores_gemma":[0.9995782,0.0001753153,0.00003005408,0.00005203586,0.0001270386,0.00003744544],"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":[0.0007508915,0.0001850682,0.001730478,0.0002242398,0.0001813734,0.0003424578,0.0001260316,0.1146809,0.07152059,0.007553687,0.008643401,0.7940608],"study_design_scores_gemma":[0.000008540181,0.00005464139,0.0004556805,0.000009982094,0.00003879084,0.0001192988,0.00001955419,0.9853619,0.008573635,0.004474611,0.0008736663,0.000009643528],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02239564,0.0005905871,0.9728413,0.0001540538,0.00007173006,0.00004726517,0.0002703035,0.001564492,0.002064568],"genre_scores_gemma":[0.6283455,0.0008045045,0.3611036,0.0002746754,0.0002291902,0.00008942664,0.001485697,0.0005653203,0.007102237],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003694179,"threshold_uncertainty_score":0.007421196,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0213178867959653,"score_gpt":0.2757775245749672,"score_spread":0.2544596377790019,"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."}}