Fetal brain age estimation and anomaly detection method and device based on deep learning

Abstract

The invention discloses a fetal brain age estimation and anomaly detection method and device based on deep learning. The brain age estimation and anomaly detection method comprises the following steps: firstly, establishing a data set of T2 weighted magnetic resonance images of the brain of a normal fetus by utilizing T2 weighted images in the uterus of a pregnant woman, which are collected clinically and conventionally; secondly, segmenting the brain of the fetus from the uterus by using a U-shaped network, predicting the brain age of the fetus by using a deep residual network based on an attention mechanism, and generating the uncertainty of the brain age and the credibility of the estimation of the brain age of the fetus; and finally, constructing a classifier according to the difference, uncertainty, credibility and other indexes of the actual fetal age and the predicted brain age, and judging whether the brain development of the fetus is abnormal or not. According to the method, the brain age of the fetus can be estimated at the same time, indexes such as uncertainty and estimation credibility are generated to be used for detecting the fetus with abnormal brain development, and the method and device have high accuracy and precision and high clinical application prospect and value.

Description

technical field [0001] This application relates to the field of brain magnetic resonance image processing, especially the application of deep learning and brain segmentation and brain age estimation. Background technique [0002] Brain age based on magnetic resonance neuroimaging is widely used to describe the development process of the normal brain, and the degree of deviation from the normal brain development track can be used as a sign and indicator to measure brain abnormalities. Research in the past decade has shown that the difference between predicted brain age and actual biological age (predicted age difference, PAD) can measure the abnormal development of the brain in premature children, the degree of brain atrophy in patients with Alzheimer's disease and traumatic brain injury, and schizophrenia The degree of accelerated aging of the patient. Fetal brain imaging has gradually become an important tool for assessing normal early brain development, however, brain age...

AI Technical Summary

Problems solved by technology

However, the use of PAD as a single indicator in the brain age model to detect brain abnormalities has obvious shortcomings. On the one hand, PAD is a regression residual, and the change of the model will directly affect the size of PAD, resulting in inconsistent calculation results of different models; on the other hand, The brain age prediction model is basically based on the data of the normal population, while the abnormally developed brain contains characteristics that are not in the normal development of the brain, which makes it difficult to detect using a single indicator of PAD and reduces the explainability of the PAD mechanism

Images