SuperDTI: Superfast Deep-learned Diffusion Tensor Imaging

Hongyu Li; Zifei Liang; Chaoyi Zhang; Ruiying Liu; Jing Li; Weihong Zhang; Dong Liang; Bowen Shen; Peizhou Huang; Sunil K Gaire; Xiaoliang Zhang; Yulin Ge; Jiangyang Zhang; Leslie Ying

SuperDTI: Superfast Deep-learned Diffusion Tensor Imaging

Hongyu Li
, Zifei Liang
, Chaoyi Zhang
, Ruiying Liu
, Jing Li
, Weihong Zhang
, Dong Liang
, Bowen Shen
, Peizhou Huang
, Sunil K Gaire
, Xiaoliang Zhang
, Yulin Ge
, Jiangyang Zhang
, Leslie Ying

Electrical and Computer Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

The main factor that prevents diffusion tensor imaging (DTI) from being incorporated in clinical routines is its long acquisition time of a large number of diffusion-weighted images (DWIs) required for reliable tensor estimation. This abstract presents SuperDTI to learn the nonlinear relationship between DWIs (reduced in q-space and k-space) and the corresponding tensor-derived quantitative maps as well as fiber tractography. Experimental results show that the proposed method can generate fractional anisotropy and mean diffusivity maps, as well as fiber tractography, from as few as six undersampled raw DWIs with quality comparable to results from 90 DWIs using conventional tensor fitting.

Original language	English
Title of host publication	Unknown book
State	Published - 2021

Cite this

@inproceedings{dd07474cea794ebab1866d7982909eb2,

title = "SuperDTI: Superfast Deep-learned Diffusion Tensor Imaging",

abstract = "The main factor that prevents diffusion tensor imaging (DTI) from being incorporated in clinical routines is its long acquisition time of a large number of diffusion-weighted images (DWIs) required for reliable tensor estimation. This abstract presents SuperDTI to learn the nonlinear relationship between DWIs (reduced in q-space and k-space) and the corresponding tensor-derived quantitative maps as well as fiber tractography. Experimental results show that the proposed method can generate fractional anisotropy and mean diffusivity maps, as well as fiber tractography, from as few as six undersampled raw DWIs with quality comparable to results from 90 DWIs using conventional tensor fitting.",

author = "Hongyu Li and Zifei Liang and Chaoyi Zhang and Ruiying Liu and Jing Li and Weihong Zhang and Dong Liang and Bowen Shen and Peizhou Huang and Gaire, \{Sunil K\} and Xiaoliang Zhang and Yulin Ge and Jiangyang Zhang and Leslie Ying",

year = "2021",

language = "English",

booktitle = "Unknown book",

}

TY - GEN

T1 - SuperDTI: Superfast Deep-learned Diffusion Tensor Imaging

AU - Li, Hongyu

AU - Liang, Zifei

AU - Zhang, Chaoyi

AU - Liu, Ruiying

AU - Li, Jing

AU - Zhang, Weihong

AU - Liang, Dong

AU - Shen, Bowen

AU - Huang, Peizhou

AU - Gaire, Sunil K

AU - Zhang, Xiaoliang

AU - Ge, Yulin

AU - Zhang, Jiangyang

AU - Ying, Leslie

PY - 2021

Y1 - 2021

N2 - The main factor that prevents diffusion tensor imaging (DTI) from being incorporated in clinical routines is its long acquisition time of a large number of diffusion-weighted images (DWIs) required for reliable tensor estimation. This abstract presents SuperDTI to learn the nonlinear relationship between DWIs (reduced in q-space and k-space) and the corresponding tensor-derived quantitative maps as well as fiber tractography. Experimental results show that the proposed method can generate fractional anisotropy and mean diffusivity maps, as well as fiber tractography, from as few as six undersampled raw DWIs with quality comparable to results from 90 DWIs using conventional tensor fitting.

AB - The main factor that prevents diffusion tensor imaging (DTI) from being incorporated in clinical routines is its long acquisition time of a large number of diffusion-weighted images (DWIs) required for reliable tensor estimation. This abstract presents SuperDTI to learn the nonlinear relationship between DWIs (reduced in q-space and k-space) and the corresponding tensor-derived quantitative maps as well as fiber tractography. Experimental results show that the proposed method can generate fractional anisotropy and mean diffusivity maps, as well as fiber tractography, from as few as six undersampled raw DWIs with quality comparable to results from 90 DWIs using conventional tensor fitting.

M3 - Conference contribution

BT - Unknown book

ER -

SuperDTI: Superfast Deep-learned Diffusion Tensor Imaging

Abstract

Fingerprint

Cite this