卷积神经网络探索孕中晚期胎儿大脑发育模式研究进展

Research progresses of convolutional neural network for exploring fetal brain development patterns during the second and third trimester of pregnancy

MRI具有多参数、多序列,较高空间及组织分辨率等优势,已逐渐成为重要的产前影像学检查方法之一,可用于评估孕中晚期胎儿大脑发育;但受胎动等不可控因素影响,胎儿MR图像质量难以令人满意。卷积神经网络(CNN)是目前最常用于医学领域图像分割的深度学习算法,能够提升图像分辨率,已成功用于成人各系统,在胎儿领域尚处于起步阶段。本文就基于CNN探索孕中晚期胎儿大脑发育模式进展进行综述。

Due to the advantages of multiple parameters,multiple sequences and high spatial and tissue resolution,MRI has gradually become one of the important imaging methods for prenatal examination,having been used to evaluate fetal brain development during the second and third trimester of pregnancy.However,fetal MR images are affected by uncontrollable factors such as fetal movement,and the image quality is not satisfied.Currently,convolutional neural network(CNN)is the most commonly used deep learning algorithm for image segmentation in the medical field,which can improve image resolution and has been successfully applied to various systems of adults,but is still in the initial state in fetuses.The research progresses of exploring fetal brain development patterns based on CNN were reviewed in this paper.