Ultrasonic image quantitative evaluation method

Abstract

The invention relates to an ultrasonic image quantitative evaluation method, which comprises the following steps of: 1, preprocessing an obtained lung ultrasonic image; 2, carrying out image segmentation on the lung ultrasonic image; 3, carrying out quantitative analysis index extraction on the lung ultrasonic image; and 4, carrying out multi-parameter conjoint analysis on the lung ultrasonic image. According to the method, parameters related to the pleura line, the B line and the real lung change are extracted by adopting a method for carrying out quantitative analysis on the ultrasonic image, then a multi-parameter conjoint analysis method is utilized, all quantitative analysis indexes are comprehensively utilized, and finally a lung lesion degree classification result is obtained. Therefore, a non-invasive / quantitative lung ultrasound image quantitative evaluation method is provided for clinic, and the method can be better applied to rapid lesion screening, grading diagnosis and illness follow-up visit of a large range of people and critically ill bedside monitoring.

Description

technical field [0001] The invention relates to a method for quantitatively evaluating ultrasonic images, in particular to a method for quantitatively evaluating ultrasonic images for evaluating lung lesions. Background technique [0002] During the diagnosis and treatment of lung diseases, timely and accurate assessment of the degree of lung disease is extremely important. Clinically, computed tomography (chest computer tomography, CT) is commonly used in lung imaging, but its application in routine screening is limited due to the ionizing radiation of CT. In addition, the difficulty in transporting critically ill patients and increasing the risk of infection also limit its application in intensive care. [0003] Ultrasound diagnosis has the advantages of non-invasive, ionizing radiation-free, real-time, and cost-effective, and can be used as a fast and convenient clinical screening tool and bedside detection tool. At present, in clinical practice related to intensive car...

AI Technical Summary

Problems solved by technology

However, such methods still rely on the subjective judgment of doctors and operators.

In addition, some artificial intelligence-based evaluation methods have been proven to have great application potential and have shown good evaluation results, but the disadvantages of such evaluation methods are that they require a large number of labeled samples (difficult to obtain clinically), and can be interpreted Poor sex

Images