Intracranial aneurysm risk prediction method and device based on artificial intelligence

Abstract

The invention provides an intracranial aneurysm risk prediction method and device based on artificial intelligence. The method comprises the steps of obtaining a to-be-predicted medical image, wherein the to-be-predicted medical image at least comprises graphic information of aneurysm; segmenting the to-be-predicted medical image based on a preset feature segmentation model to obtain an aneurysm three-dimensional image, wherein the aneurysm three-dimensional image comprises a pattern of the aneurysm; measuring the aneurysm pattern to obtain characteristic data of the aneurysm; inputting the characteristic data of the aneurysm and preset structured characteristic data into a preset rupture risk prediction model for prediction to obtain rupture risk data; and generating a medical diagnosis report based on the aneurysm three-dimensional image, the characteristic data of the aneurysm and the rupture risk data. According to the method, a deep learning technology is utilized in implementation, the trained learning model is used for performing aneurysm recognition and segmentation on the patient image and completing automatic measurement, the diagnosis time is greatly shortened, and the diagnosis accuracy is improved.

Description

technical field [0001] The invention relates to the technical field of medical aided diagnosis, in particular to an artificial intelligence-based intracranial aneurysm risk prediction method and related devices. Background technique [0002] With the continuous improvement of people's living standards, aneurysm has gradually become a major disease that threatens people's lives and health. Aneurysms are the cause of many serious diseases such as hypertension and coronary heart disease, and early detection and treatment are the best treatment options. [0003] At present, the traditional aneurysm diagnosis method needs to manually preprocess the patient's vascular images, and then perform disease diagnosis and risk prediction on the processed images based on manual experience. It is conceivable that this manual processing method takes a lot of time and energy, and cannot guarantee the accuracy of diagnosis and prediction, and is prone to many problems such as missed detection...

AI Technical Summary

Problems solved by technology

It is conceivable that this manual processing method takes a lot of time and energy, and cannot guarantee the accuracy of diagnosis and prediction, and is prone to many problems such as missed detection and low screening efficiency.

Images