Endoscopic ultrasonography (EUS) was introduced 25 years ago aiming at better visualization of the pancreas compared to transabdominal ultrasonography. This update discusses the current evidence in 2010 concerning the...Endoscopic ultrasonography (EUS) was introduced 25 years ago aiming at better visualization of the pancreas compared to transabdominal ultrasonography. This update discusses the current evidence in 2010 concerning the role of EUS in the clinical management of patients with pancreatic disease. Major indications of EUS are:(1) Detection of common bile duct stones (e.g. in acute pancreatitis); (2) Detection of small exo-and endocrine pancreatic tumours; and (3) Performance of fine needle aspiration in pancreatic masses depending on therapeutic consequences. EUS seems to be less useful in cases of chronic pancreatitis and cystic pan-creatic lesions. Moreover the constant improvement of computed tomography has limited the role of EUS in pancreatic cancer staging. On the other hand,new therapeutic options are available due to EUS,such as pancreatic cyst drainage and celiac plexus neurolysis,offering a new field in which new techniques may arise. So the main goal of this review is to determine the exact role of EUS in a number of pancreatic and biliary diseases.展开更多
Knowledge distillation has demonstrated considerable success in scenarios involving multi-class single-label learning.However,its direct application to multi-label learning proves challenging due to complex correlatio...Knowledge distillation has demonstrated considerable success in scenarios involving multi-class single-label learning.However,its direct application to multi-label learning proves challenging due to complex correlations in multi-label structures,causing student models to overlook more finely structured semantic relations present in the teacher model.In this paper,we present a solution called multi-label prototype-aware structured contrastive distillation,comprising two modules:Prototype-aware Contrastive Representation Distillation(PCRD)and prototype-aware cross-image structure distillation.The PCRD module maximizes the mutual information of prototype-aware representation between the student and teacher,ensuring semantic representation structure consistency to improve the compactness of intra-class and dispersion of inter-class representations.In the PCSD module,we introduce sample-to-sample and sample-to-prototype structured contrastive distillation to model prototype-aware cross-image structure consistency,guiding the student model to maintain a coherent label semantic structure with the teacher across multiple instances.To enhance prototype guidance stability,we introduce batch-wise dynamic prototype correction for updating class prototypes.Experimental results on three public benchmark datasets validate the effectiveness of our proposed method,demonstrating its superiority over state-of-the-art methods.展开更多
文摘Endoscopic ultrasonography (EUS) was introduced 25 years ago aiming at better visualization of the pancreas compared to transabdominal ultrasonography. This update discusses the current evidence in 2010 concerning the role of EUS in the clinical management of patients with pancreatic disease. Major indications of EUS are:(1) Detection of common bile duct stones (e.g. in acute pancreatitis); (2) Detection of small exo-and endocrine pancreatic tumours; and (3) Performance of fine needle aspiration in pancreatic masses depending on therapeutic consequences. EUS seems to be less useful in cases of chronic pancreatitis and cystic pan-creatic lesions. Moreover the constant improvement of computed tomography has limited the role of EUS in pancreatic cancer staging. On the other hand,new therapeutic options are available due to EUS,such as pancreatic cyst drainage and celiac plexus neurolysis,offering a new field in which new techniques may arise. So the main goal of this review is to determine the exact role of EUS in a number of pancreatic and biliary diseases.
基金supported by the National Natural Science Foundation of China(No.62466061)the Yunnan Fundamental Research Projects(No.202401AU070052)+1 种基金the Yunnan Provincial Department of Education Science Research Fund,China(Nos.2023J0209 and 2024Y161)the Natural Science Doctoral Research Start-Up Fund of Yunnan Normal University(No.2022ZB015).
文摘Knowledge distillation has demonstrated considerable success in scenarios involving multi-class single-label learning.However,its direct application to multi-label learning proves challenging due to complex correlations in multi-label structures,causing student models to overlook more finely structured semantic relations present in the teacher model.In this paper,we present a solution called multi-label prototype-aware structured contrastive distillation,comprising two modules:Prototype-aware Contrastive Representation Distillation(PCRD)and prototype-aware cross-image structure distillation.The PCRD module maximizes the mutual information of prototype-aware representation between the student and teacher,ensuring semantic representation structure consistency to improve the compactness of intra-class and dispersion of inter-class representations.In the PCSD module,we introduce sample-to-sample and sample-to-prototype structured contrastive distillation to model prototype-aware cross-image structure consistency,guiding the student model to maintain a coherent label semantic structure with the teacher across multiple instances.To enhance prototype guidance stability,we introduce batch-wise dynamic prototype correction for updating class prototypes.Experimental results on three public benchmark datasets validate the effectiveness of our proposed method,demonstrating its superiority over state-of-the-art methods.
