A method for noninvasive assessment of hepatic venous pressure gradient

Abstract

The invention discloses a non-invasive evaluation method of hepatic venous pressure gradient based on multimodal images and empirical knowledge, which utilizes a convolutional neural network to perform feature extraction on multimodal medical images and obtains an estimated value of HVPG based on the multimodal images. , using the deep neural network to perform regression analysis on the HVPG-related empirical knowledge parameters and obtain the HVPG estimated value based on the empirical knowledge. For the estimated value of HVPG, the optimization algorithm is used to jointly train the aforementioned convolutional neural network and deep neural network. After the training is completed, it can be used to accurately predict HVPG, and obtain the quantitative estimated value of HVPG based on multimodal images and empirical knowledge. . The present invention takes into account the complementary information of medical images of multiple modalities, and at the same time utilizes corresponding experience knowledge to supplement features, which is more in line with medical pertinence.

Description

technical field [0001] The invention relates to the technical field of medical images, in particular to a non-invasive evaluation method of hepatic venous pressure gradient based on multimodal images and empirical knowledge. Background technique [0002] Portal hypertension is one of the most common serious complications of liver cirrhosis. The risk of esophagogastric variceal bleeding increases with increased portal pressure, as well as the incidence of Hepatocellular Carcinoma (HCC), liver failure after HCC resection, and associated mortality. . Therefore, accurate quantification and dynamic monitoring of portal hypertension are of great significance to the research on the pathogenesis, diagnosis and treatment of portal hypertension. [0003] The currently recognized "gold standard" for assessing portal pressure is the hepatic venous pressure gradient (HVPG). This technique inserts a wedge-shaped catheter or balloon into the hepatic vein by puncture, and measures the hep...

AI Technical Summary

Problems solved by technology

[0005] 1) Due to the complex changes in liver and spleen morphology, hardness, and hemodynamics secondary to portal hypertension, traditional imaging methods are mostly qualitative diagnoses, which are greatly influenced by subjective experience and lack more accurate quantitative assessment;

[0006] 2) Images of different modalities usually reflect different pathological features, while traditional imaging methods mostly study from the perspective of single-modal imaging technology, and cannot achieve comprehensive multi-dimensional evaluation

Images