Literature DB >> 29520831

A convolutional neural network to filter artifacts in spectroscopic MRI.

Saumya S Gurbani1,2,3, Eduard Schreibmann1,3, Andrew A Maudsley4, James Scott Cordova1,3, Brian J Soher5, Harish Poptani6, Gaurav Verma7, Peter B Barker8, Hyunsuk Shim1,2,3,9, Lee A D Cooper2,3,10.   

Abstract

PURPOSE: Proton MRSI is a noninvasive modality capable of generating volumetric maps of in vivo tissue metabolism without the need for ionizing radiation or injected contrast agent. Magnetic resonance spectroscopic imaging has been shown to be a viable imaging modality for studying several neuropathologies. However, a key hurdle in the routine clinical adoption of MRSI is the presence of spectral artifacts that can arise from a number of sources, possibly leading to false information.
METHODS: A deep learning model was developed that was capable of identifying and filtering out poor quality spectra. The core of the model used a tiled convolutional neural network that analyzed frequency-domain spectra to detect artifacts.
RESULTS: When compared with a panel of MRS experts, our convolutional neural network achieved high sensitivity and specificity with an area under the curve of 0.95. A visualization scheme was implemented to better understand how the convolutional neural network made its judgement on single-voxel or multivoxel MRSI, and the convolutional neural network was embedded into a pipeline capable of producing whole-brain spectroscopic MRI volumes in real time.
CONCLUSION: The fully automated method for assessment of spectral quality provides a valuable tool to support clinical MRSI or spectroscopic MRI studies for use in fields such as adaptive radiation therapy planning.
© 2018 International Society for Magnetic Resonance in Medicine.

Entities:  

Keywords:  MR spectroscopic imaging; deep learning; machine learning; spectroscopic MRI

Mesh:

Year:  2018        PMID: 29520831      PMCID: PMC6107370          DOI: 10.1002/mrm.27166

Source DB:  PubMed          Journal:  Magn Reson Med        ISSN: 0740-3194            Impact factor:   4.668


  21 in total

1.  High-grade gliomas and solitary metastases: differentiation by using perfusion and proton spectroscopic MR imaging.

Authors:  Meng Law; Soonmee Cha; Edmond A Knopp; Glyn Johnson; John Arnett; Andrew W Litt
Journal:  Radiology       Date:  2002-03       Impact factor: 11.105

Review 2.  Magnetic resonance spectroscopy of the brain: review of metabolites and clinical applications.

Authors:  D P Soares; M Law
Journal:  Clin Radiol       Date:  2008-08-30       Impact factor: 2.350

3.  Improving labeling efficiency in automatic quality control of MRSI data.

Authors:  Nuno Pedrosa de Barros; Richard McKinley; Roland Wiest; Johannes Slotboom
Journal:  Magn Reson Med       Date:  2017-02-07       Impact factor: 4.668

4.  A systematic study of the class imbalance problem in convolutional neural networks.

Authors:  Mateusz Buda; Atsuto Maki; Maciej A Mazurowski
Journal:  Neural Netw       Date:  2018-07-29

5.  Whole-brain spectroscopic MRI biomarkers identify infiltrating margins in glioblastoma patients.

Authors:  James S Cordova; Hui-Kuo G Shu; Zhongxing Liang; Saumya S Gurbani; Lee A D Cooper; Chad A Holder; Jeffrey J Olson; Brad Kairdolf; Eduard Schreibmann; Stewart G Neill; Constantinos G Hadjipanayis; Hyunsuk Shim
Journal:  Neuro Oncol       Date:  2016-03-15       Impact factor: 12.300

6.  Representation learning: a unified deep learning framework for automatic prostate MR segmentation.

Authors:  Shu Liao; Yaozong Gao; Aytekin Oto; Dinggang Shen
Journal:  Med Image Comput Comput Assist Interv       Date:  2013

7.  Identification of MRI and 1H MRSI parameters that may predict survival for patients with malignant gliomas.

Authors:  Xiaojuan Li; Hua Jin; Ying Lu; Joonmi Oh; Susan Chang; Sarah J Nelson
Journal:  NMR Biomed       Date:  2004-02       Impact factor: 4.044

8.  Mapping of brain metabolite distributions by volumetric proton MR spectroscopic imaging (MRSI).

Authors:  A A Maudsley; C Domenig; V Govind; A Darkazanli; C Studholme; K Arheart; C Bloomer
Journal:  Magn Reson Med       Date:  2009-03       Impact factor: 4.668

9.  Predicting clinical outcomes from large scale cancer genomic profiles with deep survival models.

Authors:  Safoora Yousefi; Fatemeh Amrollahi; Mohamed Amgad; Chengliang Dong; Joshua E Lewis; Congzheng Song; David A Gutman; Sameer H Halani; Jose Enrique Velazquez Vega; Daniel J Brat; Lee A D Cooper
Journal:  Sci Rep       Date:  2017-09-15       Impact factor: 4.379

10.  Multiproject-multicenter evaluation of automatic brain tumor classification by magnetic resonance spectroscopy.

Authors:  Juan M García-Gómez; Jan Luts; Margarida Julià-Sapé; Patrick Krooshof; Salvador Tortajada; Javier Vicente Robledo; Willem Melssen; Elies Fuster-García; Iván Olier; Geert Postma; Daniel Monleón; Angel Moreno-Torres; Jesús Pujol; Ana-Paula Candiota; M Carmen Martínez-Bisbal; Johan Suykens; Lutgarde Buydens; Bernardo Celda; Sabine Van Huffel; Carles Arús; Montserrat Robles
Journal:  MAGMA       Date:  2008-11-07       Impact factor: 2.310

View more
  16 in total

1.  In vivo magnetic resonance imaging and spectroscopy. Technological advances and opportunities for applications continue to abound.

Authors:  Peter van Zijl; Linda Knutsson
Journal:  J Magn Reson       Date:  2019-07-09       Impact factor: 2.229

2.  Incorporation of a spectral model in a convolutional neural network for accelerated spectral fitting.

Authors:  Saumya S Gurbani; Sulaiman Sheriff; Andrew A Maudsley; Hyunsuk Shim; Lee A D Cooper
Journal:  Magn Reson Med       Date:  2019-01-21       Impact factor: 4.668

3.  Suppression of artifact-generating echoes in cine DENSE using deep learning.

Authors:  Mohamad Abdi; Xue Feng; Changyu Sun; Kenneth C Bilchick; Craig H Meyer; Frederick H Epstein
Journal:  Magn Reson Med       Date:  2021-05-22       Impact factor: 3.737

Review 4.  Hyperpolarized MRI, functional MRI, MR spectroscopy and CEST to provide metabolic information in vivo.

Authors:  Peter C M van Zijl; Kevin Brindle; Hanzhang Lu; Peter B Barker; Richard Edden; Nirbhay Yadav; Linda Knutsson
Journal:  Curr Opin Chem Biol       Date:  2021-07-20       Impact factor: 8.972

5.  The Brain Imaging Collaboration Suite (BrICS): A Cloud Platform for Integrating Whole-Brain Spectroscopic MRI into the Radiation Therapy Planning Workflow.

Authors:  Saumya Gurbani; Brent Weinberg; Lee Cooper; Eric Mellon; Eduard Schreibmann; Sulaiman Sheriff; Andrew Maudsley; Mohammed Goryawala; Hui-Kuo Shu; Hyunsuk Shim
Journal:  Tomography       Date:  2019-03

Review 6.  Applications of Deep Learning to Neuro-Imaging Techniques.

Authors:  Guangming Zhu; Bin Jiang; Liz Tong; Yuan Xie; Greg Zaharchuk; Max Wintermark
Journal:  Front Neurol       Date:  2019-08-14       Impact factor: 4.003

Review 7.  Deep Learning: A Review for the Radiation Oncologist.

Authors:  Luca Boldrini; Jean-Emmanuel Bibault; Carlotta Masciocchi; Yanting Shen; Martin-Immanuel Bittner
Journal:  Front Oncol       Date:  2019-10-01       Impact factor: 6.244

8.  Multiparametric deep learning tissue signatures for a radiological biomarker of breast cancer: Preliminary results.

Authors:  Vishwa S Parekh; Katarzyna J Macura; Susan C Harvey; Ihab R Kamel; Riham Ei-Khouli; David A Bluemke; Michael A Jacobs
Journal:  Med Phys       Date:  2019-11-22       Impact factor: 4.071

9.  Frequency and phase correction of J-difference edited MR spectra using deep learning.

Authors:  Sofie Tapper; Mark Mikkelsen; Blake E Dewey; Helge J Zöllner; Steve C N Hui; Georg Oeltzschner; Richard A E Edden
Journal:  Magn Reson Med       Date:  2020-11-18       Impact factor: 4.668

10.  Advanced magnetic resonance spectroscopic neuroimaging: Experts' consensus recommendations.

Authors:  Andrew A Maudsley; Ovidiu C Andronesi; Peter B Barker; Alberto Bizzi; Wolfgang Bogner; Anke Henning; Sarah J Nelson; Stefan Posse; Dikoma C Shungu; Brian J Soher
Journal:  NMR Biomed       Date:  2020-04-29       Impact factor: 4.044

View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.