Pulmonary vessel segmentation method and device, storage medium and electronic equipment

Abstract

The invention provides a pulmonary vessel segmentation method and device, a storage medium and electronic equipment, and relates to the technical field of image processing. The pulmonary blood vessel segmentation method comprises the following steps: processing a to-be-segmented lung three-dimensional image, a first pulmonary blood vessel segmentation image corresponding to the to-be-segmented lung three-dimensional image and a mediastinal mask image corresponding to the first pulmonary blood vessel segmentation image by using a pulmonary blood vessel mediastinal optimization model; generating a first mediastinal vessel segmentation image, a first initial pixel fusion weight matrix corresponding to the first pulmonary vessel segmentation image, and a second initial pixel fusion weight matrix corresponding to the first mediastinal vessel segmentation image; and generating a second lung blood vessel segmentation image corresponding to the to-be-segmented lung three-dimensional image based on the first lung blood vessel segmentation image, the first mediastinal blood vessel segmentation image, the first initial pixel fusion weight matrix and the second initial pixel fusion weight matrix. According to the pulmonary blood vessel segmentation method, the segmentation result of the mediastinal septum is more accurate, so that a doctor can conveniently diagnose lung-related diseases of a patient.

Description

technical field [0001] The present application relates to the technical field of medical image processing, and in particular to a pulmonary vessel segmentation method, device, storage medium and electronic equipment. Background technique [0002] Medical image processing is an important technology that uses image vision processing methods to assist clinical diagnosis. Therefore, in recent years, medical image processing has gradually become a research hotspot. Medical image segmentation is a branch of medical image processing. It usually needs to segment a computerized tomography (CT) image of a certain part of the human body to better assist doctors in the diagnosis and treatment of diseases. [0003] Taking lung CT images as an example, the blood vessels in the lungs are dense and slender, and the lung CT images are usually relatively large. Generally, it is necessary to first slice the lung CT images to obtain multiple lung slices, and then use deep learning The model se...

AI Technical Summary

Problems solved by technology

However, the pulmonary vessel segmentation results obtained by the above method have obvious splicing marks at the mediastinum, resulting in an uneven final pulmonary vessel segmentation result, which affects doctors' diagnosis of lung-related diseases

Images