Brain aneurysm three-dimensional detection segmentation method based on deep convolutional neural network

Abstract

The invention provides a cerebral aneurysm three-dimensional detection segmentation method based on a deep convolutional neural network. The method comprises the following steps: obtaining three-dimensional medical image data to be segmented; the method comprises the following steps: initializing prediction of three-dimensional medical image data, and generating a seed point as an initial tested area; outwards expanding a region from the tested region to obtain an expanded region; inputting the expansion area into the trained flow network model, predicting the expansion area, and merging the predicted expansion area into the tested area; iterative prediction is carried out on the three-dimensional medical image data until the tested area completely covers the three-dimensional medical image data, prediction is completed, and a prediction result of the three-dimensional medical image data is obtained; and obtaining a segmentation result of the three-dimensional medical image data according to the prediction result of the three-dimensional medical image data. The thought of iterative prediction in the flow network model is introduced, and the parameter quantity of the model is reduced while the three-dimensional structure information of the sample is maintained, so that the model is more accurate and convenient.

Description

technical field [0001] The present application relates to the field of computer multimedia technology, in particular to a method and device for three-dimensional detection and segmentation of cerebral aneurysms based on deep convolutional neural networks. Background technique [0002] With the continuous development of medical image detection technologies such as CT and MRI (Magnetic Resonance Imaging, Magnetic Resonance Imaging), it has greatly assisted doctors in the clinical diagnosis and pathological research of many diseases, especially for epilepsy and stroke. The emergence of brain imaging technology provides a very effective technical aid for the diagnosis and research of diseases such as brain aneurysms and cerebral aneurysms. However, with the continuous development and maturity of imaging technology, the traditional method of relying on expert identification can no longer meet the increasing number of medical images and diagnosis needs. Therefore, the use of artif...

AI Technical Summary

Problems solved by technology

[0005] Therefore, the first purpose of this application is to propose a three-dimensional detection and segmentation method for cerebral aneurysms based on deep convolutional neural networks, which solves the problem that the existing image segmentation methods are difficult to achieve in the task of detecting lesions such as cerebral aneurysms. For the problem of fine 3D segmentation, by introducing the idea of ​​iterative prediction in the flow network model, the number of parameters of the model is reduced while maintaining the 3D structure information of the image, making the model more accurate and convenient, so as to realize the 3D accuracy of cerebral aneurysm lesions Locating and Segmenting

Images