Abstract AIM:To evaluate the role of multi-detector row computed tomography(MDCT) angiography for assessing the therapeutic effects of percutaneous transhepatic variceal embolization(PTVE) for esophageal varices(EVs)....Abstract AIM:To evaluate the role of multi-detector row computed tomography(MDCT) angiography for assessing the therapeutic effects of percutaneous transhepatic variceal embolization(PTVE) for esophageal varices(EVs).METHODS:The subjects of this prospective study were 156 patients who underwent PTVE with cyanoacrylate for EVs.Patients were divided into three groups according to the filling range of cyanoacrylate in EVs and their feeding vessels:(1) group A,complete obliteration,with at least 3 cm of the lower EVs and peri-/EVs,as well as the adventitial plexus of the gastric cardia and fundus filled with cyanoacrylate;(2) group B,partial obliteration of varices surrounding the gastric cardia and fundus,with their feeding vessels being obliterated with cyanoacrylate,but without reaching lower EVs;and(3) group C,trunk obliteration,with the main branch of the left gastric vein being filled with cyanoacrylate,but without reaching varices surrounding the gastric cardia or fundus.We performed chart reviews and a prospective follow-up using MDCT images,angiography,and gastrointestinal endoscopy.RESULTS:The median follow-up period was 34 mo.The rate of eradication of varices for all patients was 56.4%(88/156) and the rate of relapse was 31.3%(41/131).The rates of variceal eradication at 1,3,and 5 years after PTVE were 90.2%,84.1% and 81.7%,respectively,for the complete group;61.2%,49% and 42.9%,respectively,for the partial group;with no varices disappearing in the trunk group.The relapsefree rates at 1,3 and 5 years after PTVE were 91.5%,86.6% and 81.7%,respectively,for the complete group;71.1%,55.6% and 51.1%,respectively,for the partial group;and all EVs recurred in the trunk group.Kaplan-Meier analysis showed P values of 0.000 and 0.000,and odds ratios of 3.824 and 3.603 for the rates of variceal eradication and relapse free rates,respectively.Cyanoacrylate in EVs disappeared with time,but those in the EVs and other feeding vessels remained permanently in the vessels without a decrease with time,which is important for the continued obliteration of the feeding vessels and prevention of EV relapse.CONCLUSION:MDCT provides excellent visualization of cyanoacrylate obliteration in EV and their feeding veins after PTVE.It confirms that PTVE is effective for treating EVs.展开更多
This paper describes a novel gait pattern recognition method based on Long Short-Term Memory(LSTM)and Convolutional Neural Network(CNN)for lower limb exoskeleton.The Inertial Measurement Unit(IMU)installed on the exos...This paper describes a novel gait pattern recognition method based on Long Short-Term Memory(LSTM)and Convolutional Neural Network(CNN)for lower limb exoskeleton.The Inertial Measurement Unit(IMU)installed on the exoskeleton to collect motion information,which is used for LSTM-CNN input.This article considers five common gait patterns,including walking,going up stairs,going down stairs,sitting down,and standing up.In the LSTM-CNN model,the LSTM layer is used to process temporal sequences and the CNN layer is used to extract features.To optimize the deep neural network structure proposed in this paper,some hyperparameter selection experiments were carried out.In addition,to verify the superiority of the proposed recognition method,the method is compared with several common methods such as LSTM,CNN and SVM.The results show that the average recognition accuracy can reach 97.78%,which has a good recognition eff ect.Finally,according to the experimental results of gait pattern switching,the proposed method can identify the switching gait pattern in time,which shows that it has good real-time performance.展开更多
文摘Abstract AIM:To evaluate the role of multi-detector row computed tomography(MDCT) angiography for assessing the therapeutic effects of percutaneous transhepatic variceal embolization(PTVE) for esophageal varices(EVs).METHODS:The subjects of this prospective study were 156 patients who underwent PTVE with cyanoacrylate for EVs.Patients were divided into three groups according to the filling range of cyanoacrylate in EVs and their feeding vessels:(1) group A,complete obliteration,with at least 3 cm of the lower EVs and peri-/EVs,as well as the adventitial plexus of the gastric cardia and fundus filled with cyanoacrylate;(2) group B,partial obliteration of varices surrounding the gastric cardia and fundus,with their feeding vessels being obliterated with cyanoacrylate,but without reaching lower EVs;and(3) group C,trunk obliteration,with the main branch of the left gastric vein being filled with cyanoacrylate,but without reaching varices surrounding the gastric cardia or fundus.We performed chart reviews and a prospective follow-up using MDCT images,angiography,and gastrointestinal endoscopy.RESULTS:The median follow-up period was 34 mo.The rate of eradication of varices for all patients was 56.4%(88/156) and the rate of relapse was 31.3%(41/131).The rates of variceal eradication at 1,3,and 5 years after PTVE were 90.2%,84.1% and 81.7%,respectively,for the complete group;61.2%,49% and 42.9%,respectively,for the partial group;with no varices disappearing in the trunk group.The relapsefree rates at 1,3 and 5 years after PTVE were 91.5%,86.6% and 81.7%,respectively,for the complete group;71.1%,55.6% and 51.1%,respectively,for the partial group;and all EVs recurred in the trunk group.Kaplan-Meier analysis showed P values of 0.000 and 0.000,and odds ratios of 3.824 and 3.603 for the rates of variceal eradication and relapse free rates,respectively.Cyanoacrylate in EVs disappeared with time,but those in the EVs and other feeding vessels remained permanently in the vessels without a decrease with time,which is important for the continued obliteration of the feeding vessels and prevention of EV relapse.CONCLUSION:MDCT provides excellent visualization of cyanoacrylate obliteration in EV and their feeding veins after PTVE.It confirms that PTVE is effective for treating EVs.
基金supported by the Pre-research project in the manned space field.Project Number 020202,China.
文摘This paper describes a novel gait pattern recognition method based on Long Short-Term Memory(LSTM)and Convolutional Neural Network(CNN)for lower limb exoskeleton.The Inertial Measurement Unit(IMU)installed on the exoskeleton to collect motion information,which is used for LSTM-CNN input.This article considers five common gait patterns,including walking,going up stairs,going down stairs,sitting down,and standing up.In the LSTM-CNN model,the LSTM layer is used to process temporal sequences and the CNN layer is used to extract features.To optimize the deep neural network structure proposed in this paper,some hyperparameter selection experiments were carried out.In addition,to verify the superiority of the proposed recognition method,the method is compared with several common methods such as LSTM,CNN and SVM.The results show that the average recognition accuracy can reach 97.78%,which has a good recognition eff ect.Finally,according to the experimental results of gait pattern switching,the proposed method can identify the switching gait pattern in time,which shows that it has good real-time performance.