Automatic lung organ model leaf division method and system based on CT image

Abstract

The invention discloses a lung organ model automatic leaf division method based on a CT image. The lung organ model automatic leaf division method comprises the following steps: importing original data ImageData of a chest sequence CT image; extracting a lung parenchyma region by adopting a threshold segmentation algorithm to obtain a binary image of the lung parenchyma, recording the binary image as MASK1, and performing three-dimensional reconstruction on the detected and segmented lung parenchyma region; calculating the maximum bounding box of the pulmonary parenchyma according to whether the outermost boundary of the binary image of the pulmonary parenchyma has a binary point, performing enhancement calculation on the sheet structure to obtain enhanced image data MASK2, further processing to obtain a binary image MASK3, and extracting a set of all points of the left and right binary data as a left lung point cloud S1 and a right lung point cloud S2; performing left lung cutting segmentation by taking the left lung point cloud S1 as input data; and taking the right lung point cloud S2 as input data to sequentially carry out right lung first-stage cutting and right lung second-stage cutting. The method can reduce the interference of the non-lung region on the extraction of the lung gap point cloud, can improve the operation efficiency, does not need manual intervention, and can significantly reduce the workload.

Description

technical field The invention relates to a medical 3D image visualization processing method, in particular to a method and system for automatic lobulation of a lung organ model based on CT images. Background technique At present, lung cancer has become the number one cancer with the highest fatality rate in the world, and the most effective way to improve the survival rate of lung cancer is early detection, early diagnosis and early treatment. The lungs have lobes: two on the left and three on the right, for a total of five lobes. The lobulation of the lung is distinguished according to the direction of the pulmonary blood vessels, and the lobulation of the lung is of great guiding significance for the diagnosis and treatment of lung cancer. . With the development of artificial intelligence technology, existing lung segmentation methods rely on a large number of manually delineated gold standards as training data, please refer to the following existing literature: [000...

AI Technical Summary

Problems solved by technology

The disadvantage of this type of method is that training data requires a lot of manpower and material resources, and there is a correlation between the performance of the model and the amount of data used for model training; at the same time, the trained model needs to be equipped with high-configuration computer hardware to run; furthermore, the training Later model revisions and iterations are costly

In addition, the traditional lung lobulation method needs to obtain the bronchial model first, and then extract the centerline. These two operations require a lot of pre-work, requiring a large workload and manpower input

Images