CT image lung lobe method and system

Abstract

The invention discloses a CT image lung lobe method and system, and belongs to the technical field of medical image processing and artificial intelligence. The method comprises the following steps: marking a lung contour and a lung lobe area in CT horizontal scanning image data; according to the CT horizontal scanning image data and the lung contour data, performing training learning by using a first neural network to obtain a lung contour segmentation model; extracting the lung contour according to the lung contour segmentation model, and performing training learning on the lung contour dataand the lung lobe area by using a second neural network to obtain a lung partial lobe segmentation model; and according to the CT horizontal scanning image data and the lung part leaf segmentation model, segmenting lung part leaves, and performing three-dimensional display. The system comprises a labeling module, a first training module, a second training module and a segmentation display module.According to the CT image lung lobe method and system, the processing efficiency of CT image data is improved, the lung area and the lung part leaves can be quickly segmented, and the segmented lung part leaves are displayed in a three-dimensional mode.

Description

technical field [0001] The invention relates to the technical fields of medical image processing and artificial intelligence, in particular to a CT image lung lobulation method and system. Background technique [0002] The human lungs are located in the thoracic cavity, suspended on both sides of the mediastinum by the lung roots and pulmonary ligaments. All organs of the human body cannot work without oxygen, and the lungs are the only organ that transports oxygen and discharges carbon dioxide. Through breathing, the alveoli will be in contact with the atmosphere at any time and perform gas exchange, inhaling oxygen and exhaling carbon dioxide. The human body has two lungs, one on the left and one on the left, and the surface of the lungs is covered with the pleura and the visceral layer of the septum. The left lung is long and narrow, and is divided into upper and lower lobes by oblique fissures; the right lung is wide and short, and is divided into upper, middle, and low...

AI Technical Summary

Problems solved by technology

[0005] In order to solve the existing problems of manually distinguishing lung lobes, such as long time-consuming, differences in lobulation results, and difficulty in recording and displaying, the present invention provides a method for lung lobes in CT images, including:

Images