Hepatic vein and portal vein segmentation method and device

Abstract

The invention provides a hepatic vein and portal vein segmentation method and device. The method comprises the following steps: inputting an original medical image into a first segmentation model to obtain a liver mask; inputting the liver mask into a second segmentation model to obtain segmented image areas of six categories including a background, a hepatic vein blood vessel, a hepatic vein blood vessel outermost mask, a portal vein blood vessel outermost mask, a portal vein blood vessel and an intersection area of the hepatic vein and the portal vein blood vessel; and correcting the segmented image region based on the connectivity of the blood vessels to obtain two types of images including the hepatic vein blood vessel and the portal vein blood vessel. According to the method, six different types of segmented image regions are obtained, so that the main vein of the hepatic vein and the portal vein can be separated as much as possible; and by segmenting the outermost mask of the hepatic vein and the outermost mask of the portal vein, the noise interference influence caused by unclear boundary due to partial volume effect can be reduced, so that the segmentation precision of the hepatic vein and the portal vein is obviously improved.

Description

technical field [0001] The invention belongs to the technical field of medical imaging, and in particular relates to a method and device for segmenting a hepatic vein and a portal vein. Background technique [0002] In recent years, the number of patients with liver disease has been on the rise, seriously endangering human health. Since many liver diseases need to be treated by liver resection or ablation, in the early stage of surgical planning, doctors need to segment the liver according to the morphological trends of the hepatic veins and portal veins in medical images, in order to make the best possible use of the liver during surgery. Precise resection or elimination of the diseased area is possible, preserving more liver function for the patient. However, at the current stage of surgical planning, most of the medical image reading work is done manually by doctors, which poses a huge challenge to doctors' energy, experience, and patience. Therefore, accurate automatic...

AI Technical Summary

Problems solved by technology

This not only requires a huge amount of calculation, but these methods have not fully used (or even destroyed) the structural characteristics and prior information of the hepatic vein and portal vein itself.

Images