Method for constructing prediction model of multifunctional veins based on brain nuclear magnetic resonance image

Abstract

The invention discloses a method for constructing a prediction model of multifunctional veins based on a brain nuclear magnetic resonance image. The image is divided through an area increasing method, an edge vein characteristic parameter of ROIs is extracted through a Contourlet conversion method, a multifunctional data base is established, and the prediction model is established through various data mining methods including the gaussian process, a support vector machine, random forest, Lasso regression and a semi-supervised support vector machine, wherein the ROIs comprise a sea horse area and an entorhinal cortex layer area.

Description

Technical field: [0001] The invention belongs to the field of medical technology, and in particular relates to a method for establishing a prediction model based on multi-dimensional texture extraction of nuclear magnetic resonance images. Background technique: [0002] Identifying the nature of ROIs (including entorhinal cortex, hippocampus) in MRI images is of great significance in aiding the diagnosis of early Alzheimer's disease (AD). However, MRI imaging technology can only use hippocampal atrophy as one of the indicators to distinguish patients from normal people. Doctors' interpretation of MRI images is easily influenced by subjective individuals, lacks consistency, and is difficult to accurately evaluate the severity of symptoms in dementia patients. [0003] 1. Existing image processing technology; [0004] Contourlet transformation [0005] Contourlet transform inherits the anisotropic scale relationship of Curvelet transform, and in a certain sense it is another...

AI Technical Summary

Problems solved by technology

Although this is a biased estimate to reduce the variance of the predicted value, the prediction accuracy of the model will be improved accordingly and the resulting model is easier to explain

Images