Quad-Contrast Imaging: Simultaneous Acquisition of Four Contrast-Weighted Images (PD-Weighted, T2-Weighted, PD-FLAIR and T2-FLAIR Images) With Synthetic T1-Weighted Image, T1- and T2-Maps

被引:4
作者
Ji, Sooyeon [1 ]
Jeong, Jinhee [2 ]
Oh, Se-Hong [3 ]
Nam, Yoonho [3 ]
Choi, Seung Hong [4 ]
Shin, Hyeong-Geol [1 ]
Shin, Dongmyung [1 ]
Jung, Woojin [1 ,5 ]
Lee, Jongho [1 ]
机构
[1] Seoul Natl Univ, Dept Elect & Comp Engn, Seoul 08826, South Korea
[2] Samsung Res, Seoul 06765, South Korea
[3] Hankuk Univ Foreign Studies, Dept Biomed Engn, Yongin 17035, South Korea
[4] Seoul Natl Univ Hosp, Dept Radiol, Seoul 03080, South Korea
[5] AIRS Med, Seoul 08788, South Korea
基金
新加坡国家研究基金会;
关键词
Imaging; Image reconstruction; Magnetic resonance imaging; Radio frequency; Timing; Specific absorption rate; Encoding; fast imaging; deep learning; multi-contrast imaging; CONVOLUTIONAL NEURAL-NETWORKS; MRI; BRAIN; RECONSTRUCTION; SEGMENTATION;
D O I
10.1109/TMI.2021.3093617
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Magnetic resonance imaging (MRI) can provide multiple contrast-weighted images using different pulse sequences and protocols. However, a long acquisition time of the images is a major challenge. To address this limitation, a new pulse sequence referred to as quad-contrast imaging is presented. The quad-contrast sequence enables the simultaneous acquisition of four contrast-weighted images (proton density (PD)-weighted, T-2-weighted, PD-fluid attenuated inversion recovery (FLAIR), and T-2-FLAIR), and the synthesis of T-1-weighted images and T-1- and T-2-maps in a single scan. The scan time is less than 6 min and is further reduced to 2 min 50 s using a deep learning-based parallel imaging reconstruction. The natively acquired quad contrasts demonstrate high quality images, comparable to those from the conventional scans. The deep learning-based reconstruction successfully reconstructed highly accelerated data (acceleration factor 6), reporting smaller normalized root mean squared errors (NRMSEs) and higher structural similarities (SSIMs) than those from conventional generalized autocalibrating partially parallel acquisitions (GRAPPA)-reconstruction (mean NRMSE of 4.36% vs. 10.54% and mean SSIM of 0.990 vs. 0.953). In particular, the FLAIR contrast is natively acquired and does not suffer from lesion-like artifacts at the boundary of tissue and cerebrospinal fluid, differentiating the proposed method from synthetic imaging methods. The quad-contrast imaging method may have the potentials to be used in a clinical routine as a rapid diagnostic tool.
引用
收藏
页码:3617 / 3626
页数:10
相关论文
共 50 条
  • [21] Evaluation of multimodal segmentation based on 3D T1-, T2-and FLAIR-weighted images - the difficulty of choosing
    Lindig, Tobias
    Kotikalapudi, Raviteja
    Schweikardt, Daniel
    Martin, Pascal
    Bender, Friedemann
    Klose, Uwe
    Ernemann, Ulrike
    Focke, Niels K.
    Bender, Benjamin
    NEUROIMAGE, 2018, 170 : 210 - 221
  • [22] The use of combined T2-weighted and FLAIR synthetic magnetic resonance images to improve white matter region contrast: a feasibility study
    Fujiwara, Yasuhiro
    Inoue, Yumi
    Kanamoto, Masayuki
    Ishida, Shota
    Adachi, Toshiki
    Kimura, Hirohiko
    RADIOLOGICAL PHYSICS AND TECHNOLOGY, 2019, 12 (01) : 118 - 125
  • [23] T2ρ-weighted contrast in MR images of the human brain
    Wheaton, AJ
    Borthakur, A
    Corbo, MT
    Moonis, G
    Melhem, E
    Reddy, R
    MAGNETIC RESONANCE IN MEDICINE, 2004, 52 (06) : 1223 - 1227
  • [24] Neurite density explains cortical T1-weighted/T2-weighted ratio in multiple sclerosis
    Preziosa, Paolo
    Bouman, Piet M.
    Kiljan, Svenja
    Steenwijk, Martijn D.
    Meani, Alessandro
    Pouwels, Petra J.
    Rocca, Maria A.
    Filippi, Massimo
    Geurts, Jeroen J. G.
    Jonkman, Laura E.
    JOURNAL OF NEUROLOGY NEUROSURGERY AND PSYCHIATRY, 2021, 92 (07) : 790 - 792
  • [25] Altered Intracortical T1-Weighted/T2-Weighted Ratio Signal in Huntington's Disease
    Rowley, Christopher D.
    Tabrizi, Sarah J.
    Scahill, Rachael, I
    Leavitt, Blair R.
    Roos, Raymund A. C.
    Durr, Alexandra
    Bock, Nicholas A.
    FRONTIERS IN NEUROSCIENCE, 2018, 12
  • [26] Robust texture features for response monitoring of glioblastoma multiforme on T1-weighted and T2-FLAIR MR images: A preliminary investigation in terms of identification and segmentation
    Assefa, Dawit
    Keller, Harald
    Menard, Cynthia
    Laperriere, Normand
    Ferrari, Ricardo J.
    Yeung, Ivan
    MEDICAL PHYSICS, 2010, 37 (04) : 1722 - 1736
  • [27] Elucidating the aberrant brain regions in bipolar disorder using T1-weighted/T2-weighted magnetic resonance ratio images
    Ishida, Takuya
    Donishi, Tomohiro
    Iwatani, Jun
    Yamada, Shinichi
    Takahashi, Shun
    Ukai, Satoshi
    Shinosaki, Kazuhiro
    Terada, Masaki
    Kaneoke, Yoshiki
    PSYCHIATRY RESEARCH-NEUROIMAGING, 2017, 263 : 76 - 84
  • [28] SIGNAL, CONTRAST, AND RESOLUTION IN OPTIMIZED PD-WEIGTED AND T2-WEIGHTED TURBO SE IMAGES OF THE KNEE
    FELLNER, C
    GEISSLER, A
    HELD, P
    STROTZER, M
    TREIBEL, W
    FELLNER, F
    JOURNAL OF COMPUTER ASSISTED TOMOGRAPHY, 1995, 19 (01) : 96 - 105
  • [29] The Image Evaluation of Iterative Motion Correction Reconstruction Algorithm PROPELLER T2-Weighted Imaging Compared with MultiVane T2-Weighted Imaging
    Lee, Suk-Jun
    Yu, Seung-Man
    JOURNAL OF THE KOREAN PHYSICAL SOCIETY, 2017, 71 (04) : 238 - 243
  • [30] Contrast Enhancement of the Normal Infundibular Recess Using Heavily T2-weighted 3D FLAIR
    Osawa, Iichiro
    Kozawa, Eito
    Yamamoto, Yuya
    Tanaka, Sayuri
    Shiratori, Taira
    Kaizu, Akane
    Inoue, Kaiji
    Niitsu, Mamoru
    MAGNETIC RESONANCE IN MEDICAL SCIENCES, 2022, 21 (03) : 469 - 476