A method, device, equipment and storage medium for segmental positioning of pulmonary vessels

Abstract

The present application provides a method, device, device, and storage medium for segmental positioning of pulmonary vessels. The method includes: from the acquired three-dimensional image of the lung, segment and extract the largest circumscribed cubic region of the three-dimensional image where the target pulmonary vessel is located as the first Input data; input the first input data into the trained pulmonary vessel segmentation model to obtain the first segmentation result, the second segmentation result and the initial positioning result of the target pulmonary vessel; use the first segmentation As a result and the second segmentation result, determine a location candidate region corresponding to each vessel branch of the target pulmonary vessel; for each vessel branch of the target pulmonary vessel, use the location candidate region corresponding to the vessel branch , correcting the starting point coordinates corresponding to the blood vessel branch in the initial positioning result to obtain the final positioning result of the target pulmonary vessel. Through the above method, the segmental positioning of the target pulmonary blood vessel can be performed, and the accuracy of the segmental positioning result can be improved.

Description

technical field [0001] The present application relates to the technical field of data processing, and in particular, to a method, device, device and storage medium for segmental positioning of pulmonary vessels. Background technique [0002] Pulmonary blood vessels are an important part of the pulmonary circulatory system. Pulmonary blood vessels can be divided into pulmonary arteries and pulmonary veins. Pulmonary blood vessels run in the lung segment and are distributed in a tree structure. Since the pulmonary vessels are distributed in a tree structure, the pulmonary vessels can be segmented according to the main trunk and vascular branches. Specifically, for the pulmonary artery, the pulmonary artery can be divided into one main trunk and 18 vascular branches; for the pulmonary vein, the pulmonary vein includes: the intrasegmental vein and the intersegmental vein, because the intersegmental vein is located between different pulmonary segments, Therefore, intersegmental ...

AI Technical Summary

Problems solved by technology

In this way, on the one hand, the recognition accuracy of the pulmonary vessel centerline in the segmentation task is relatively high, and the number of classification tasks in the classification task is also high, resulting in a large amount of data processing, which easily leads to a decrease in the accuracy of the obtained segmentation results; on the other hand, On the one hand, on the basis that the accuracy of the segmentation results cannot be guaranteed, the manual positioning method requires manual marking by the staff, and the accuracy of the positioning results obtained by it is greatly affected by artificial factors. Therefore, the lung The accuracy of blood vessel segmentation positioning results is low

Images