AIM: To assess the role of echo-Doppler ultrasonography in postprandial hyperemia in cirrhotic patients by comparing the results with the hepatic vein catheterization technique.METHODS: Patients with cirrhosis, admitt...AIM: To assess the role of echo-Doppler ultrasonography in postprandial hyperemia in cirrhotic patients by comparing the results with the hepatic vein catheterization technique.METHODS: Patients with cirrhosis, admitted to the portal hemodynamic laboratory were included into the study. After an overnight fast, echo-Doppler ultrasonography (basal and 30 min after a standard meal) and hemodynamic studies by hepatic vein catheterization (basal, 15 min and 30 min after a standard meal) were performed. Ensure Plus (Abbot Laboratories, North Chicago, IL) was used as the standard liquid meal. Correlation analysis of the echo-Doppler and hepatic vein catheterization measurements were done for the basal and postprandial periods.RESULTS: Eleven patients with cirrhosis (5 Child A, 4 Child B, 2 Child C) were enrolled into the study. After the standard meal, 8 of the 11 patients showed postprandial hyperemia with increase in portal blood flow, portal blood velocity and hepatic venous pressure gradient. Hepatic venous pressure gradient in the postprandial period correlated positively with postprandial portal blood velocity (r = 0.8, P < 0.05) and correlated inversely with postprandial superior mesenteric artery pulsatility index (r = -1, P < 0.01).CONCLUSION: Postprandial hyperemia can be efficiently measured by echo-Doppler ultrasonography and the results are comparable to those obtained with the hemodynamic studies.展开更多
To achieve automatic,fast and accurate severity classification of bulbar conjunctival hyperemia severity,we proposed a novel prior knowledge-based framework called mask distillation network(MDN).The proposed MDN consi...To achieve automatic,fast and accurate severity classification of bulbar conjunctival hyperemia severity,we proposed a novel prior knowledge-based framework called mask distillation network(MDN).The proposed MDN consists of a segmentation network and a classification network with teacher-student branches.The segmentation network is used to generate a bulbar conjunctival mask and the classification network divides the severity of bulbar conjunctival hyperemia into four grades.In the classification network,we feed the original image and the image with the bulbar conjunctival mask into the student and teacher branches respectively,and an attention consistency loss and a classification consistency loss are used to keep a similar learning mode for these two branches.This design of“different input but same output”,named mask distillation(MD),aims to introduce the regional prior knowledge that“bulbar conjunctival hyperemia severity classification is only related to the bulbar conjunctiva region”.Extensive experiments on 5117 anterior segment images have proven the effectiveness of mask distillation technology:1)The accuracy of the MDN student branch is 3.5%higher than that of a single optimal baseline network and 2%higher than that of the baseline network combination.2)In the test phase,only the student branch is needed,and no additional segmentation network is required.The framework only takes 0.003 s to classify a single image,achieving the fastest speed in all the methods we compared.3)Compared with a single baseline network,the attention of both teacher and student branches in the MDN has been intuitively improved.展开更多
文摘AIM: To assess the role of echo-Doppler ultrasonography in postprandial hyperemia in cirrhotic patients by comparing the results with the hepatic vein catheterization technique.METHODS: Patients with cirrhosis, admitted to the portal hemodynamic laboratory were included into the study. After an overnight fast, echo-Doppler ultrasonography (basal and 30 min after a standard meal) and hemodynamic studies by hepatic vein catheterization (basal, 15 min and 30 min after a standard meal) were performed. Ensure Plus (Abbot Laboratories, North Chicago, IL) was used as the standard liquid meal. Correlation analysis of the echo-Doppler and hepatic vein catheterization measurements were done for the basal and postprandial periods.RESULTS: Eleven patients with cirrhosis (5 Child A, 4 Child B, 2 Child C) were enrolled into the study. After the standard meal, 8 of the 11 patients showed postprandial hyperemia with increase in portal blood flow, portal blood velocity and hepatic venous pressure gradient. Hepatic venous pressure gradient in the postprandial period correlated positively with postprandial portal blood velocity (r = 0.8, P < 0.05) and correlated inversely with postprandial superior mesenteric artery pulsatility index (r = -1, P < 0.01).CONCLUSION: Postprandial hyperemia can be efficiently measured by echo-Doppler ultrasonography and the results are comparable to those obtained with the hemodynamic studies.
基金This work was supported in part by National Natural Science Foundation of China(Nos.62172223 and 61671242)the Fundamental Research Funds for the Central Universities(No.30921013105).
文摘To achieve automatic,fast and accurate severity classification of bulbar conjunctival hyperemia severity,we proposed a novel prior knowledge-based framework called mask distillation network(MDN).The proposed MDN consists of a segmentation network and a classification network with teacher-student branches.The segmentation network is used to generate a bulbar conjunctival mask and the classification network divides the severity of bulbar conjunctival hyperemia into four grades.In the classification network,we feed the original image and the image with the bulbar conjunctival mask into the student and teacher branches respectively,and an attention consistency loss and a classification consistency loss are used to keep a similar learning mode for these two branches.This design of“different input but same output”,named mask distillation(MD),aims to introduce the regional prior knowledge that“bulbar conjunctival hyperemia severity classification is only related to the bulbar conjunctiva region”.Extensive experiments on 5117 anterior segment images have proven the effectiveness of mask distillation technology:1)The accuracy of the MDN student branch is 3.5%higher than that of a single optimal baseline network and 2%higher than that of the baseline network combination.2)In the test phase,only the student branch is needed,and no additional segmentation network is required.The framework only takes 0.003 s to classify a single image,achieving the fastest speed in all the methods we compared.3)Compared with a single baseline network,the attention of both teacher and student branches in the MDN has been intuitively improved.