{"id":"W2517954747","doi":"10.1007/978-3-319-46976-8_19","title":"The Importance of Skip Connections in Biomedical Image Segmentation","year":2016,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":991,"is_retracted":false,"has_abstract":false,"ca_institutions":"Centre Hospitalier de l’Université de Montréal; Université de Montréal; Polytechnique Montréal","funders":"Mitacs","keywords":"Computer science; Upsampling; Path (computing); Residual; Segmentation; Artificial intelligence; Image (mathematics); Image segmentation; Pattern recognition (psychology); Computer vision; Algorithm; Computer network","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001344767,0.0009021251,0.000644048,0.001075967,0.000560939,0.001269415,0.0009904173,0.001554223,0.003218825],"category_scores_gemma":[0.005611337,0.0005196923,0.0004236064,0.0009135685,0.0007773953,0.00294734,0.001132439,0.0009949773,0.0007546142],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004282076,"about_ca_system_score_gemma":0.0006099822,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002097022,"about_ca_topic_score_gemma":0.004339977,"domain_scores_codex":[0.9997109,0.00007042226,0.00002099748,0.00007845344,0.00008600417,0.00003321792],"domain_scores_gemma":[0.9972163,0.001801059,0.0001845786,0.0002873641,0.0003804452,0.0001302104],"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":[0.001002446,0.0001298021,0.003761028,0.0007637562,0.0001850001,0.0007185334,0.0001919784,0.1464326,0.08024046,0.05413978,0.008543812,0.7038909],"study_design_scores_gemma":[0.00001888555,0.0001219264,0.004035433,0.00007241581,0.0001124315,0.0004101759,0.00003840642,0.8977801,0.02059706,0.07411439,0.002678356,0.00002035121],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1037755,0.007110326,0.8756208,0.001005813,0.0002577635,0.00005446156,0.0004339027,0.001343795,0.01039757],"genre_scores_gemma":[0.7443134,0.006529288,0.2304818,0.000361359,0.0005973386,0.00006726188,0.001262112,0.0006826624,0.01570485],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003218825,"threshold_uncertainty_score":0.01076806,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01373374754625272,"score_gpt":0.2756294804930322,"score_spread":0.2618957329467795,"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."}}