{"id":"W4288757744","doi":"10.1016/j.bspc.2022.104021","title":"A multi-branch hierarchical attention network for medical target segmentation","year":2022,"lang":"en","type":"article","venue":"Biomedical Signal Processing and Control","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"Six Talent Peaks Project in Jiangsu Province; Natural Science Foundation of Jiangsu Province; National Natural Science Foundation of China","keywords":"Computer science; Feature (linguistics); Segmentation; Artificial intelligence; Upsampling; Context (archaeology); Pattern recognition (psychology); Perspective (graphical); Market segmentation; Feature extraction; Set (abstract data type); 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001517621,0.0001593422,0.0003622756,0.00009130186,0.0006771373,0.00004747959,0.000113963,0.0001097688,0.0003616115],"category_scores_gemma":[0.0002340171,0.0001310194,0.0001105877,0.0002220968,0.0002751253,0.00005322658,0.00004609886,0.0006814454,0.000001929091],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006104117,"about_ca_system_score_gemma":0.000296743,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000133289,"about_ca_topic_score_gemma":3.633797e-7,"domain_scores_codex":[0.9977127,0.0001505593,0.0004097344,0.0003852363,0.0009115256,0.0004302467],"domain_scores_gemma":[0.9989906,0.000221029,0.0001156181,0.00007420325,0.00005795928,0.0005405804],"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":[0.001371267,0.0007958951,0.01032137,0.0004579603,0.0001626074,0.00009958562,0.0002364248,0.0001612788,0.02803183,0.0001087892,0.006382081,0.9518709],"study_design_scores_gemma":[0.01281193,0.000831097,0.003710405,0.0001643504,0.0001623785,0.0003109126,0.00009141998,0.9432808,0.00002175814,0.0007617578,0.03764166,0.0002115375],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04646381,0.001713261,0.933408,0.01736172,0.0002944813,0.0005857481,0.00002144685,0.0001146329,0.00003694555],"genre_scores_gemma":[0.9756253,0.00001658574,0.01654277,0.005968632,0.001113197,0.0002910454,0.0001800062,0.00002966827,0.0002328345],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9516594,"threshold_uncertainty_score":0.5342817,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008804817647696066,"score_gpt":0.2851654570378857,"score_spread":0.2763606393901896,"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."}}