Intracranial aneurysm recognition and detection method and device, computer equipment and storage medium

Abstract

The invention relates to an intracranial aneurysm recognition and detection method and device, computer equipment and a storage medium. The method comprises the steps that positive and negative sample image blocks of an original intracranial image are acquired, and the positive and negative sample image blocks are three-dimensional image blocks; the positive sample image block and the negative sample image block are processed through a three-dimensional semantic segmentation model, corresponding detection results are output, the three-dimensional semantic segmentation model is constructed through a Transformer module, an encoder and a decoder on the basis of a convolutional neural network, the processing process of the three-dimensional semantic segmentation model is divided into multiple stages according to the specifications of the positive sample image block and the negative sample image block, the encoder and the decoder are coupled and connected through a first type of paths in the same stage, and the first type of paths are a plurality of paths corresponding to a single-dimensional vector of a three-dimensional image block. According to the method, feature extraction can be better carried out on the positive and negative sample image blocks, the detection rate of the micro aneurysm is improved, the coherence between original intracranial images is kept, and the continuity between layers is improved.

Description

technical field [0001] The present application relates to the intersecting fields of the medical field and image processing, and in particular relates to a method, device, computer equipment and storage medium for identifying and detecting intracranial aneurysms. Background technique [0002] Intracranial aneurysm is one of the most common cerebrovascular diseases. Although intracranial aneurysm includes the word "tumor", it is not a tumor, but a local intracranial artery wall damage caused by factors such as congenital abnormalities or acquired injuries; in the combined effects of hemodynamics and other factors Next, the abnormal swelling formed by gradual expansion is a kind of cerebrovascular disease. The incidence of intracranial aneurysm in the population is about 2% to 7%, and it can occur in any age group, and the peak age of onset is 40 to 60 years old. [0003] Subarachnoid hemorrhage (SAH) caused by ruptured intracranial aneurysm has extremely high morbidity and ...

AI Technical Summary

Problems solved by technology

[0008] In the above-mentioned existing technical solutions, although some researches have been done on the detection of intracranial aneurysms based on deep learning, there are generally the following technical problems: First, the area occupied by aneurysms on the entire CTA image is very small, and the actual detection The ratio between the background area and the aneurysm target area is seriously unbalanced, which leads to a low detection rate of some small or tiny aneurysms; second, the long-term dependence of the current classic 3D UNet network structure design on CTA imaging aneurysms The capture effect is not good, and the continuity between layers needs to be further improved

Images