{"id":"W4224862961","doi":"10.1038/s41598-022-10429-z","title":"Clinical target segmentation using a novel deep neural network: double attention Res-U-Net","year":2022,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Jaccard index; Segmentation; Computer science; Artificial intelligence; Sørensen–Dice coefficient; Pattern recognition (psychology); Dropout (neural networks); Dice; Noise (video); Image segmentation; Artificial neural network; Encoder; Encoding (memory); Image (mathematics); Machine learning; 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":["sts"],"consensus_categories":[],"category_scores_codex":[0.002719458,0.0001723564,0.000214206,0.0001352414,0.001920237,0.000416822,0.0006560014,0.00004317314,0.00008839857],"category_scores_gemma":[0.0000279058,0.0001844648,0.0001634071,0.001930949,0.0001620513,0.0008167935,0.0009842672,0.0003330181,0.00001148371],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001611403,"about_ca_system_score_gemma":0.0001183436,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001474286,"about_ca_topic_score_gemma":0.000009329045,"domain_scores_codex":[0.9960538,0.0001513167,0.000969884,0.001381136,0.0008895301,0.0005543709],"domain_scores_gemma":[0.9973617,0.00007402304,0.0007721675,0.00148061,0.0001431022,0.0001683517],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000219658,0.0002575355,0.01543114,0.000006835157,0.0000198579,0.0001403147,0.0001468172,0.9458497,0.016659,0.003344155,0.008623809,0.00949887],"study_design_scores_gemma":[0.0004620647,0.00005911864,0.002608258,0.000006650985,0.00001835172,0.0007770159,0.00004466118,0.9375091,0.0002962579,0.01879494,0.03909348,0.0003301502],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2048771,0.0001387222,0.7795404,0.0003652259,0.01381406,0.0007174825,0.000002108193,0.0002715146,0.0002733694],"genre_scores_gemma":[0.7142438,0.000001799669,0.2838544,0.0002646207,0.0003587927,0.0001711735,0.0001440818,0.00002455085,0.0009367712],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5093667,"threshold_uncertainty_score":0.9993791,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06503603948376563,"score_gpt":0.3438051097556136,"score_spread":0.278769070271848,"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."}}