A patent foramen ovale detection method, system, terminal and storage medium

Abstract

The present application relates to a patent foramen ovale detection method, system, terminal and storage medium. Including: left atrium ROI segmentation for each frame of image data in the dynamic image data of the apical four-chamber view; wherein, the dynamic image data of the apical four-chamber view includes TTE image data and cTTE within a set number of cardiac cycles Image data; calculate the gray level of the left atrium ROI of each frame of image in the TTE image data, and filter out the minimum gray level distribution interval of the TTE image data, and filter out the corresponding Interval cTTE images; microbubble detection and feature extraction are performed on the screened cTTE images, and input into the trained prediction model, and the detection result of the closed state of the foramen ovale is output through the prediction model. The application realizes the non-invasive PFO detection, the operation is simple and the accuracy is high, and the detection rate and detection efficiency are improved.

Description

technical field [0001] The application belongs to the technical field of medical ultrasound imaging, and in particular relates to a method, system, terminal and storage medium for detecting a patent foramen ovale. Background technique [0002] The foramen ovale is an embryonic defect (hole) in the atrial septum in the center of the heart. During fetal growth and development, the foramen ovale acts as an important life channel, which allows oxygenated blood to flow from the right atrium to the left atrium. In 75% of newborns, as the lungs develop and the resistance of the lungs decreases, there is a consequent increase in the pressure in the heart from the left to the right atrium, causing the opening to close automatically and the foramen ovale to functionally close . However, patent foramen ovale (PFO) still exists in 15%-35% of the adult population. According to statistics, PFO is the most common congenital heart abnormality among adults. The correct judgment of whethe...

AI Technical Summary

Problems solved by technology

[0007] 1. TEE is a semi-invasive detection method that cannot avoid risks. It is difficult to operate and requires high experience of clinicians. In China, this detection method is not popular, and only large hospitals usually carry out this detection; cTCD passed Cerebral blood circulation detection of contrast agent microbubbles from PFO can only infer the source of microbubbles indirectly, and cannot directly prove the existence of PFO; TTE is non-invasive and easy to operate, but its detection rate and sensitivity are low; cTTE as a A new type of detection method, which is non-invasive and can provide more detailed information on shunting from right to left in the heart, but is easily affected by noise, motion artifacts, and lung gas, with poor sensitivity and high specificity

[0008] 2. The existing clinical inquiry methods involve limited experimental groups and the conclusions are not universal, and their effects need to be further confirmed

[0009] 3. At present, there is no artificial intelligence method to effectively evaluate whether the foramen ovale is closed

Images