Super-Resolution 1H Magnetic Resonance Spectroscopic Imaging Utilizing Deep Learning

Zohaib Iqbal, Dan Nguyen, Gilbert Hangel, Stanislav Motyka, Wolfgang Bogner, Steve Jiang

Research output: Contribution to journalArticle

Abstract

Magnetic resonance spectroscopic imaging (SI) is a unique imaging technique that provides biochemical information from in vivo tissues. The 1H spectra acquired from several spatial regions are quantified to yield metabolite concentrations reflective of tissue metabolism. However, since these metabolites are found in tissues at very low concentrations, SI is often acquired with limited spatial resolution. In this work, we test the hypothesis that deep learning is able to upscale low resolution SI, together with the T1-weighted (T1w) image, to reconstruct high resolution SI. We report on a novel densely connected UNet (D-UNet) architecture capable of producing super-resolution spectroscopic images. The inputs for the D-UNet are the T1w image and the low resolution SI image while the output is the high resolution SI. The results of the D-UNet are compared both qualitatively and quantitatively to simulated and in vivo high resolution SI. It is found that this deep learning approach can produce high quality spectroscopic images and reconstruct entire 1H spectra from low resolution acquisitions, which can greatly advance the current SI workflow.

Original languageEnglish (US)
Article number1010
JournalFrontiers in Oncology
Volume9
DOIs
StatePublished - Oct 9 2019

Fingerprint

Magnetic Resonance Imaging
Learning
Workflow

Keywords

  • artificial intelligence
  • deep learning (DL)
  • magnetic resonance spectroscopic imaging (SI)
  • magnetic resonance spectroscopy (H MRS)
  • super-resolution

ASJC Scopus subject areas

  • Oncology
  • Cancer Research

Cite this

Super-Resolution 1H Magnetic Resonance Spectroscopic Imaging Utilizing Deep Learning. / Iqbal, Zohaib; Nguyen, Dan; Hangel, Gilbert; Motyka, Stanislav; Bogner, Wolfgang; Jiang, Steve.

In: Frontiers in Oncology, Vol. 9, 1010, 09.10.2019.

Research output: Contribution to journalArticle

Iqbal, Zohaib ; Nguyen, Dan ; Hangel, Gilbert ; Motyka, Stanislav ; Bogner, Wolfgang ; Jiang, Steve. / Super-Resolution 1H Magnetic Resonance Spectroscopic Imaging Utilizing Deep Learning. In: Frontiers in Oncology. 2019 ; Vol. 9.
@article{e1098092b47b47a38f544aefde610d08,
title = "Super-Resolution 1H Magnetic Resonance Spectroscopic Imaging Utilizing Deep Learning",
abstract = "Magnetic resonance spectroscopic imaging (SI) is a unique imaging technique that provides biochemical information from in vivo tissues. The 1H spectra acquired from several spatial regions are quantified to yield metabolite concentrations reflective of tissue metabolism. However, since these metabolites are found in tissues at very low concentrations, SI is often acquired with limited spatial resolution. In this work, we test the hypothesis that deep learning is able to upscale low resolution SI, together with the T1-weighted (T1w) image, to reconstruct high resolution SI. We report on a novel densely connected UNet (D-UNet) architecture capable of producing super-resolution spectroscopic images. The inputs for the D-UNet are the T1w image and the low resolution SI image while the output is the high resolution SI. The results of the D-UNet are compared both qualitatively and quantitatively to simulated and in vivo high resolution SI. It is found that this deep learning approach can produce high quality spectroscopic images and reconstruct entire 1H spectra from low resolution acquisitions, which can greatly advance the current SI workflow.",
keywords = "artificial intelligence, deep learning (DL), magnetic resonance spectroscopic imaging (SI), magnetic resonance spectroscopy (H MRS), super-resolution",
author = "Zohaib Iqbal and Dan Nguyen and Gilbert Hangel and Stanislav Motyka and Wolfgang Bogner and Steve Jiang",
year = "2019",
month = "10",
day = "9",
doi = "10.3389/fonc.2019.01010",
language = "English (US)",
volume = "9",
journal = "Frontiers in Oncology",
issn = "2234-943X",
publisher = "Frontiers Media S. A.",

}

TY - JOUR

T1 - Super-Resolution 1H Magnetic Resonance Spectroscopic Imaging Utilizing Deep Learning

AU - Iqbal, Zohaib

AU - Nguyen, Dan

AU - Hangel, Gilbert

AU - Motyka, Stanislav

AU - Bogner, Wolfgang

AU - Jiang, Steve

PY - 2019/10/9

Y1 - 2019/10/9

N2 - Magnetic resonance spectroscopic imaging (SI) is a unique imaging technique that provides biochemical information from in vivo tissues. The 1H spectra acquired from several spatial regions are quantified to yield metabolite concentrations reflective of tissue metabolism. However, since these metabolites are found in tissues at very low concentrations, SI is often acquired with limited spatial resolution. In this work, we test the hypothesis that deep learning is able to upscale low resolution SI, together with the T1-weighted (T1w) image, to reconstruct high resolution SI. We report on a novel densely connected UNet (D-UNet) architecture capable of producing super-resolution spectroscopic images. The inputs for the D-UNet are the T1w image and the low resolution SI image while the output is the high resolution SI. The results of the D-UNet are compared both qualitatively and quantitatively to simulated and in vivo high resolution SI. It is found that this deep learning approach can produce high quality spectroscopic images and reconstruct entire 1H spectra from low resolution acquisitions, which can greatly advance the current SI workflow.

AB - Magnetic resonance spectroscopic imaging (SI) is a unique imaging technique that provides biochemical information from in vivo tissues. The 1H spectra acquired from several spatial regions are quantified to yield metabolite concentrations reflective of tissue metabolism. However, since these metabolites are found in tissues at very low concentrations, SI is often acquired with limited spatial resolution. In this work, we test the hypothesis that deep learning is able to upscale low resolution SI, together with the T1-weighted (T1w) image, to reconstruct high resolution SI. We report on a novel densely connected UNet (D-UNet) architecture capable of producing super-resolution spectroscopic images. The inputs for the D-UNet are the T1w image and the low resolution SI image while the output is the high resolution SI. The results of the D-UNet are compared both qualitatively and quantitatively to simulated and in vivo high resolution SI. It is found that this deep learning approach can produce high quality spectroscopic images and reconstruct entire 1H spectra from low resolution acquisitions, which can greatly advance the current SI workflow.

KW - artificial intelligence

KW - deep learning (DL)

KW - magnetic resonance spectroscopic imaging (SI)

KW - magnetic resonance spectroscopy (H MRS)

KW - super-resolution

UR - http://www.scopus.com/inward/record.url?scp=85074168396&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85074168396&partnerID=8YFLogxK

U2 - 10.3389/fonc.2019.01010

DO - 10.3389/fonc.2019.01010

M3 - Article

C2 - 31649879

AN - SCOPUS:85074168396

VL - 9

JO - Frontiers in Oncology

JF - Frontiers in Oncology

SN - 2234-943X

M1 - 1010

ER -