Liver segmentation method and system

Abstract

The invention belongs to the technical field of preoperative planning. The invention discloses a liver segmentation method and system. The invention relates to the technical field of medical instruments, in particular to a liver segmentation method and system based on a multi-stage MRI image, and the method comprises the steps: employing an abdominal MRI portal vein sequence image and a liver contour image, carrying out the segmentation of an MRI image on the basis of an existing liver segmentation result, obtaining a segmentation result of a blood vessel in the liver, and carrying out the blood vessel refinement, and extracting a center line; performing topological analysis on the vascular structure to separate the hepatic vein from the portal vein; and classifying the portal vein to finally realize liver segmentation and reconstruct the three-dimensional shape of the liver segmentation. The liver can be completely automatically segmented based on the multi-stage MRI image, manual marking is not needed any more, manpower and material resources are saved, and the efficiency is improved.

Description

technical field [0001] The invention belongs to the technical field of preoperative planning, and in particular relates to a liver segmentation method and system based on multi-phase MRI images. Background technique [0002] With the development of imaging technology and computer technology, the emergence of 3D visualization system can quickly convert 2D images such as MRI and CT of liver anatomy into 3D visualization images. At the same time, the development of hepatobiliary surgery technology, especially the maturity of living donor liver transplantation technology, has further increased the requirements for segmental liver anatomy, and liver segmentation should be more individualized, digitalized and precise. [0003] The liver is the largest organ in the abdomen. Anatomical studies have shown that the liver is generally divided into eight liver segments. Each liver segment is responsible for an independent pipeline system and can be used as a surgical resection unit alon...

AI Technical Summary

Problems solved by technology

[0005] Nowadays, the segmentation of the liver mostly relies on interactive software, which requires doctors to manually mark the starting point of the hepatic vein and portal vein, which cannot be fully automated

[0006] Meinzer and Osorio performed liver segmentation according to the liver surface feature points, but this did not combine the internal anatomical structure of the liver, which would lead to a large difference between the segmentation results and the actual clinical results

The current general segmentation results are based on the vascular tree structure of the intrahepatic portal vein, and the use of interactive equipment to grade blood vessels limits the scope of application

Images