Deep Learning for Fast and Spatially Constrained Tissue Quantification from Highly Accelerated Data in Magnetic Resonance Fingerprinting

Zhenghan Fang, Yong Chen, Mingxia Liu, Lei Xiang, Qian Zhang, Qian Wang, Weili Lin, Dinggang Shen

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

Magnetic resonance fingerprinting (MRF) is a quantitative imaging technique that can simultaneously measure multiple important tissue properties of human body. Although MRF has demonstrated improved scan efficiency as compared to conventional techniques, further acceleration is still desired for translation into routine clinical practice. The purpose of this paper is to accelerate MRF acquisition by developing a new tissue quantification method for MRF that allows accurate quantification with fewer sampling data. Most of the existing approaches use the MRF signal evolution at each individual pixel to estimate tissue properties, without considering the spatial association among neighboring pixels. In this paper, we propose a spatially constrained quantification method that uses the signals at multiple neighboring pixels to better estimate tissue properties at the central pixel. Specifically, we design a unique two-step deep learning model that learns the mapping from the observed signals to the desired properties for tissue quantification, i.e.: 1) with a feature extraction module for reducing the dimension of signals by extracting a low-dimensional feature vector from the high-dimensional signal evolution and 2) a spatially constrained quantification module for exploiting the spatial information from the extracted feature maps to generate the final tissue property map. A corresponding two-step training strategy is developed for network training. The proposed method is tested on highly undersampled MRF data acquired from human brains. Experimental results demonstrate that our method can achieve accurate quantification for T1 and T2 relaxation times by using only 1/4 time points of the original sequence (i.e., four times of acceleration for MRF acquisition).

Original languageEnglish
Article number8641364
Pages (from-to)2364-2374
Number of pages11
JournalIEEE Transactions on Medical Imaging
Volume38
Issue number10
DOIs
Publication statusPublished - 2019 Oct

Fingerprint

Magnetic resonance
Magnetic Resonance Spectroscopy
Learning
Tissue
Pixels
Deep learning
Human Body
Relaxation time
Feature extraction
Brain
Sampling
Efficiency
Imaging techniques

Keywords

  • Magnetic resonance fingerprinting
  • neural network
  • quantitative magnetic resonance imaging
  • tissue quantification

ASJC Scopus subject areas

  • Software
  • Radiological and Ultrasound Technology
  • Computer Science Applications
  • Electrical and Electronic Engineering

Cite this

Deep Learning for Fast and Spatially Constrained Tissue Quantification from Highly Accelerated Data in Magnetic Resonance Fingerprinting. / Fang, Zhenghan; Chen, Yong; Liu, Mingxia; Xiang, Lei; Zhang, Qian; Wang, Qian; Lin, Weili; Shen, Dinggang.

In: IEEE Transactions on Medical Imaging, Vol. 38, No. 10, 8641364, 10.2019, p. 2364-2374.

Research output: Contribution to journalArticle

Fang, Zhenghan ; Chen, Yong ; Liu, Mingxia ; Xiang, Lei ; Zhang, Qian ; Wang, Qian ; Lin, Weili ; Shen, Dinggang. / Deep Learning for Fast and Spatially Constrained Tissue Quantification from Highly Accelerated Data in Magnetic Resonance Fingerprinting. In: IEEE Transactions on Medical Imaging. 2019 ; Vol. 38, No. 10. pp. 2364-2374.
@article{0075992ff7524df8a3c03c34449ed3cd,
title = "Deep Learning for Fast and Spatially Constrained Tissue Quantification from Highly Accelerated Data in Magnetic Resonance Fingerprinting",
abstract = "Magnetic resonance fingerprinting (MRF) is a quantitative imaging technique that can simultaneously measure multiple important tissue properties of human body. Although MRF has demonstrated improved scan efficiency as compared to conventional techniques, further acceleration is still desired for translation into routine clinical practice. The purpose of this paper is to accelerate MRF acquisition by developing a new tissue quantification method for MRF that allows accurate quantification with fewer sampling data. Most of the existing approaches use the MRF signal evolution at each individual pixel to estimate tissue properties, without considering the spatial association among neighboring pixels. In this paper, we propose a spatially constrained quantification method that uses the signals at multiple neighboring pixels to better estimate tissue properties at the central pixel. Specifically, we design a unique two-step deep learning model that learns the mapping from the observed signals to the desired properties for tissue quantification, i.e.: 1) with a feature extraction module for reducing the dimension of signals by extracting a low-dimensional feature vector from the high-dimensional signal evolution and 2) a spatially constrained quantification module for exploiting the spatial information from the extracted feature maps to generate the final tissue property map. A corresponding two-step training strategy is developed for network training. The proposed method is tested on highly undersampled MRF data acquired from human brains. Experimental results demonstrate that our method can achieve accurate quantification for T1 and T2 relaxation times by using only 1/4 time points of the original sequence (i.e., four times of acceleration for MRF acquisition).",
keywords = "Magnetic resonance fingerprinting, neural network, quantitative magnetic resonance imaging, tissue quantification",
author = "Zhenghan Fang and Yong Chen and Mingxia Liu and Lei Xiang and Qian Zhang and Qian Wang and Weili Lin and Dinggang Shen",
year = "2019",
month = "10",
doi = "10.1109/TMI.2019.2899328",
language = "English",
volume = "38",
pages = "2364--2374",
journal = "IEEE Transactions on Medical Imaging",
issn = "0278-0062",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "10",

}

TY - JOUR

T1 - Deep Learning for Fast and Spatially Constrained Tissue Quantification from Highly Accelerated Data in Magnetic Resonance Fingerprinting

AU - Fang, Zhenghan

AU - Chen, Yong

AU - Liu, Mingxia

AU - Xiang, Lei

AU - Zhang, Qian

AU - Wang, Qian

AU - Lin, Weili

AU - Shen, Dinggang

PY - 2019/10

Y1 - 2019/10

N2 - Magnetic resonance fingerprinting (MRF) is a quantitative imaging technique that can simultaneously measure multiple important tissue properties of human body. Although MRF has demonstrated improved scan efficiency as compared to conventional techniques, further acceleration is still desired for translation into routine clinical practice. The purpose of this paper is to accelerate MRF acquisition by developing a new tissue quantification method for MRF that allows accurate quantification with fewer sampling data. Most of the existing approaches use the MRF signal evolution at each individual pixel to estimate tissue properties, without considering the spatial association among neighboring pixels. In this paper, we propose a spatially constrained quantification method that uses the signals at multiple neighboring pixels to better estimate tissue properties at the central pixel. Specifically, we design a unique two-step deep learning model that learns the mapping from the observed signals to the desired properties for tissue quantification, i.e.: 1) with a feature extraction module for reducing the dimension of signals by extracting a low-dimensional feature vector from the high-dimensional signal evolution and 2) a spatially constrained quantification module for exploiting the spatial information from the extracted feature maps to generate the final tissue property map. A corresponding two-step training strategy is developed for network training. The proposed method is tested on highly undersampled MRF data acquired from human brains. Experimental results demonstrate that our method can achieve accurate quantification for T1 and T2 relaxation times by using only 1/4 time points of the original sequence (i.e., four times of acceleration for MRF acquisition).

AB - Magnetic resonance fingerprinting (MRF) is a quantitative imaging technique that can simultaneously measure multiple important tissue properties of human body. Although MRF has demonstrated improved scan efficiency as compared to conventional techniques, further acceleration is still desired for translation into routine clinical practice. The purpose of this paper is to accelerate MRF acquisition by developing a new tissue quantification method for MRF that allows accurate quantification with fewer sampling data. Most of the existing approaches use the MRF signal evolution at each individual pixel to estimate tissue properties, without considering the spatial association among neighboring pixels. In this paper, we propose a spatially constrained quantification method that uses the signals at multiple neighboring pixels to better estimate tissue properties at the central pixel. Specifically, we design a unique two-step deep learning model that learns the mapping from the observed signals to the desired properties for tissue quantification, i.e.: 1) with a feature extraction module for reducing the dimension of signals by extracting a low-dimensional feature vector from the high-dimensional signal evolution and 2) a spatially constrained quantification module for exploiting the spatial information from the extracted feature maps to generate the final tissue property map. A corresponding two-step training strategy is developed for network training. The proposed method is tested on highly undersampled MRF data acquired from human brains. Experimental results demonstrate that our method can achieve accurate quantification for T1 and T2 relaxation times by using only 1/4 time points of the original sequence (i.e., four times of acceleration for MRF acquisition).

KW - Magnetic resonance fingerprinting

KW - neural network

KW - quantitative magnetic resonance imaging

KW - tissue quantification

UR - http://www.scopus.com/inward/record.url?scp=85070316452&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85070316452&partnerID=8YFLogxK

U2 - 10.1109/TMI.2019.2899328

DO - 10.1109/TMI.2019.2899328

M3 - Article

C2 - 30762540

AN - SCOPUS:85070316452

VL - 38

SP - 2364

EP - 2374

JO - IEEE Transactions on Medical Imaging

JF - IEEE Transactions on Medical Imaging

SN - 0278-0062

IS - 10

M1 - 8641364

ER -