BACKGROUND Angiomyolipomas(AMLs),belonging to the family of mesenchymal tumors,are considered benign lesions that occur mostly in the kidney or as a part of tuberous sclerosis.Epithelioid AML(EAML)is a rare type of AM...BACKGROUND Angiomyolipomas(AMLs),belonging to the family of mesenchymal tumors,are considered benign lesions that occur mostly in the kidney or as a part of tuberous sclerosis.Epithelioid AML(EAML)is a rare type of AML that appears to have malignant potential.Extrarenal AMLs usually occur in the liver according to the retrieved literature reports.There have been only two previous reports of monofocal primary AML of the pancreas;however,no cases of primary monotypic EAML of the pancreas have been reported.CASE SUMMARY An asymptomatic 59-year-old woman incidentally revealed a tumor during abdominal ultrasound examination.Routine blood tests and physical examination were within normal limits.Abdominal ultrasound revealed a 1.9-cm hypoechogenic mass in the tail of the pancreas,clearly visualized by endoscopic ultrasound.However,contrast-enhanced abdominal computed tomography scans did not demonstrate the lesion.A subsequent gadolinium-enhanced magnetic resonance imaging scan showed that the lesion had some characteristic manifestations.The lesion was initially thought to be a neuroendocrine tumor(asymptomatic PanNET).After surgical resection,histopathology and immunohistochemistry confirmed the diagnosis of EAML.At the 6-mo follow-up,no recurrence,spread,or metastasis was identified on computed tomography or magnetic resonance imaging.CONCLUSION The preoperative diagnosis of pancreatic AML is extremely difficult.Imaging techniques are essential for providing valuable morphological features for differential diagnosis.展开更多
Aspect category detection is one challenging subtask of aspect based sentiment analysis, which categorizes a review sentence into a set of predefined aspect categories. Most existing methods regard the aspect category...Aspect category detection is one challenging subtask of aspect based sentiment analysis, which categorizes a review sentence into a set of predefined aspect categories. Most existing methods regard the aspect category detection as a flat classification problem. However, aspect categories are inter-related, and they are usually organized with a hierarchical tree structure. To leverage the structure information, this paper proposes a hierarchical multi-label classification model to detect aspect categories and uses a graph enhanced transformer network to integrate label dependency information into prediction features. Experiments have been conducted on four widely-used benchmark datasets, showing that the proposed model outperforms all strong baselines.展开更多
文摘BACKGROUND Angiomyolipomas(AMLs),belonging to the family of mesenchymal tumors,are considered benign lesions that occur mostly in the kidney or as a part of tuberous sclerosis.Epithelioid AML(EAML)is a rare type of AML that appears to have malignant potential.Extrarenal AMLs usually occur in the liver according to the retrieved literature reports.There have been only two previous reports of monofocal primary AML of the pancreas;however,no cases of primary monotypic EAML of the pancreas have been reported.CASE SUMMARY An asymptomatic 59-year-old woman incidentally revealed a tumor during abdominal ultrasound examination.Routine blood tests and physical examination were within normal limits.Abdominal ultrasound revealed a 1.9-cm hypoechogenic mass in the tail of the pancreas,clearly visualized by endoscopic ultrasound.However,contrast-enhanced abdominal computed tomography scans did not demonstrate the lesion.A subsequent gadolinium-enhanced magnetic resonance imaging scan showed that the lesion had some characteristic manifestations.The lesion was initially thought to be a neuroendocrine tumor(asymptomatic PanNET).After surgical resection,histopathology and immunohistochemistry confirmed the diagnosis of EAML.At the 6-mo follow-up,no recurrence,spread,or metastasis was identified on computed tomography or magnetic resonance imaging.CONCLUSION The preoperative diagnosis of pancreatic AML is extremely difficult.Imaging techniques are essential for providing valuable morphological features for differential diagnosis.
基金supported by the National Natural Science Foundation of China under Grant No.62036001.
文摘Aspect category detection is one challenging subtask of aspect based sentiment analysis, which categorizes a review sentence into a set of predefined aspect categories. Most existing methods regard the aspect category detection as a flat classification problem. However, aspect categories are inter-related, and they are usually organized with a hierarchical tree structure. To leverage the structure information, this paper proposes a hierarchical multi-label classification model to detect aspect categories and uses a graph enhanced transformer network to integrate label dependency information into prediction features. Experiments have been conducted on four widely-used benchmark datasets, showing that the proposed model outperforms all strong baselines.
