Method and device for detecting thin cap fibroplaque based on intracranial artery image

Abstract

The invention discloses a thin fibrous cap plaque detection method and device based on an intracranial artery image. The method comprises the following steps: acquiring an intracranial artery OCT image; segmenting a fiber region from the intracranial artery OCT image through the trained fiber segmentation model; determining the inner wall of the lumen according to the fiber area; intercepting the intracranial artery OCT image according to the inner wall of the lumen and a preset distance to obtain an intercepted intracranial artery OCT image; segmenting a lipid region from the intercepted intracranial artery OCT image through a trained lipid segmentation model; and determining a thin cap fibroplaque detection result according to the segmented image. According to the method, the characteristic difference between fibers and lipids is fully considered, two-section segmentation is adopted, namely, the fiber region is segmented through the trained fiber segmentation model, and then the lipid region is segmented through the trained lipid segmentation model, so that the model segmentation performance is improved, the segmentation process is more accurate and controllable, and the segmentation efficiency is improved. And the accuracy of the detection result of the thin fiber cap plaque is improved.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a method and a device for detecting thin fiber cap plaques based on intracranial arterial images. Background technique [0002] Thin-Cap Fibroatheroma (TCFA) is one of the characteristics of vulnerable plaques. Since such lesions have extremely high requirements for the thickness of the fibrous cap, no related reports have been reported in intracranial arteries. With the gradual application of optical coherence tomography (OCT) to intracranial arteries, people have a detectable method for intracranial arterial TCFA. [0003] Existing technologies focus on the intelligent interpretation of cardiovascular OCT images, and there is little work to explore and study intracranial arterial OCT. At present, no studies have clearly pointed out that the image interpretation and pathological treatment of cardiovascular OCT are completely applicable to intracranial arteries, and there is ...

AI Technical Summary

Problems solved by technology

Plaque boundaries in OCT images are usually not obvious. Relying on existing segmentation techniques, it is difficult to achieve accurate segmentation with small errors. Larger segmentation errors are unavoidable and will interfere with subsequent tasks.

On the other hand, due to the limited resolution of OCT images, segmentation errors cause huge interference to TCFA detection

Images