Method and device for extracting pulmonary embolism image, storage medium and electronic equipment

Abstract

The invention relates to a method and device for extracting a pulmonary embolism image, a storage medium and electronic equipment, and aims to accurately extract the pulmonary embolism image. The method comprises the steps of obtaining a 3D image of pulmonary artery CT angiography, and extracting a pulmonary artery blood vessel tree image in the 3D image; segmenting the pulmonary artery blood vessel tree image to obtain a first pulmonary artery blood vessel image corresponding to the pulmonary lobe and lung segment part and a second pulmonary artery blood vessel image corresponding to the pulmonary portal and lung medial septum part; performing connected component analysis on the first pulmonary artery blood vessel image and the second pulmonary artery blood vessel image to obtain a firstcandidate pulmonary embolism image set and a second candidate pulmonary embolism image set; and inputting the first image feature parameter of each first candidate pulmonary embolism image into a first classifier, and inputting the second image feature parameter of each second candidate pulmonary embolism image into a second classifier to obtain pulmonary embolism images screened by the first classifier and the second classifier respectively.

Description

technical field [0001] The present disclosure relates to the technical field of image processing, and in particular, to a method, device, storage medium and electronic equipment for extracting images of pulmonary embolism. Background technique [0002] Pulmonary embolism (PE for short) refers to the clinical pathophysiological syndrome of pulmonary circulation disorder caused by various emboli in the systemic circulation blocking the pulmonary artery and its branches. Patients with pulmonary embolism will suddenly experience unexplained collapse, pale complexion, cold sweat, dyspnea, chest pain, cough and other symptoms, as well as symptoms of cerebral hypoxia such as extreme anxiety, fatigue, nausea, convulsions, and coma. Pulmonary embolism is a common disease with high morbidity and mortality, and its incidence is second only to acute myocardial infarction and aortic dissection. However, due to the "atypical" nature of symptoms and signs of pulmonary embolism, it is easy...

AI Technical Summary

Problems solved by technology

However, this method requires a large amount of sample data of marked embolized areas, and the workload of manually marking embolized areas is huge

Moreover, it is difficult to collect a variety of CTPA image samples

Images