arrow
返回

Diffusion tensor estimation with transformer neural networks

delete2022-08-01
delete15
delete
OA
AI
D
Davood Karimi *
A
Ali Gholipour
DOI:10.1016/j.artmed.2022.102330delete
delete原文链接
delete分享
delete收藏
查看原文
摘要

摘要

En 中文
Diffusion tensor imaging (DTI) is a widely used method for studying brain white matter development and degeneration. However, standard DTI estimation methods depend on a large number of high-quality measure-ments. This would require long scan times and can be particularly difficult to achieve with certain patient populations such as neonates. Here, we propose a method that can accurately estimate the diffusion tensor from only six diffusion-weighted measurements. Our method achieves this by learning to exploit the relationships between the diffusion signals and tensors in neighboring voxels. Our model is based on transformer networks, which represent the state of the art in modeling the relationship between signals in a sequence. In particular, our model consists of two such networks. The first network estimates the diffusion tensor based on the diffusion signals in a neighborhood of voxels. The second network provides more accurate tensor estimations by learning the relationships between the diffusion signals as well as the tensors estimated by the first network in neigh-boring voxels. Our experiments with three datasets show that our proposed method achieves highly accurate estimations of the diffusion tensor and is significantly superior to three competing methods. Estimations pro-duced by our method with six diffusion-weighted measurements are comparable with those of standard esti-mation methods with 30-88 diffusion-weighted measurements. Hence, our method promises shorter scan times and more reliable assessment of brain white matter, particularly in non-cooperative patients such as neonates and infants.
Keyword:
Diffusion MRI
Diffusion tensor imaging
Deep learning
Transformer networks
AI总结

AI总结

对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

Artificial Intelligence in Medicine 封面图
Artificial Intelligence in Medicine
IF:
6.2
论文数:
2.5K
被引数:
7.8K

机构

H
Harvard University
学者数:
26.5W
论文数: 22.0W
被引数: 28.7W
引用论文

引用论文

Open-Ended Questions
err2020-06-22
err0
PREAI
errSubhadra Dutta; Eric M. O’Rourke
err分享
err收藏
CARTILAGINOUS TUMORS OF THE BASE OF SKULL
err1969-02-01
err0
PREAI
errHIDEYO MINAGI; THOMAS H. NEWTON
err分享
err收藏
Optimal acquisition orders of diffusion-weighted MRI measurements
err2007-04-24
err113
errOAAI
errCook, Philip A.; Symms, Mark; Boulby, Philip A.; Alexander, Daniel C.
err分享
err收藏
学者 查看更多内容