Deep learning approaches for detection and removal of ghosting artifacts in MR spectroscopy.

Kyathanahally, Sreenath Pruthviraj; Döring, André; Kreis, Roland (2018). Deep learning approaches for detection and removal of ghosting artifacts in MR spectroscopy. Magnetic resonance in medicine, 80(3), pp. 851-863. Wiley-Liss 10.1002/mrm.27096

[img]
Preview
Text
Kyathanahally_MRM_accepted.pdf - Accepted Version
Available under License Publisher holds Copyright.

Download (1MB) | Preview
[img] Text
Kyathanahally_et_al-2018-Magnetic_Resonance_in_Medicine.pdf - Published Version
Restricted to registered users only
Available under License Publisher holds Copyright.

Download (1MB) | Request a copy

PURPOSE To make use of deep learning (DL) methods to detect and remove ghosting artifacts in clinical magnetic resonance spectra of human brain. METHODS Deep learning algorithms, including fully connected neural networks, deep-convolutional neural networks, and stacked what-where auto encoders, were implemented to detect and correct MR spectra containing spurious echo ghost signals. The DL methods were trained on a huge database of simulated spectra with and without ghosting artifacts that represent complex variations of ghost-ridden spectra, transformed to time-frequency spectrograms. The trained model was tested on simulated and in vivo spectra. RESULTS The preliminary results for ghost detection are very promising, reaching almost 100% accuracy, and the DL ghost removal methods show potential in simulated and in vivo spectra, but need further refinement and quantitative testing. CONCLUSIONS Ghosting artifacts in spectroscopy are problematic, as they superimpose with metabolites and lead to inaccurate quantification. Detection and removal of ghosting artifacts using traditional machine learning approaches with feature extraction/selection is difficult, as ghosts appear at different frequencies. Here, we show that DL methods perform extremely well for ghost detection if the spectra are treated as images in the form of time-frequency representations. Further optimization for in vivo spectra will hopefully confirm their "ghostbusting" capacity. Magn Reson Med, 2018. © 2018 International Society for Magnetic Resonance in Medicine.

Item Type:

Journal Article (Original Article)

Division/Institute:

04 Faculty of Medicine > Department of Radiology, Neuroradiology and Nuclear Medicine (DRNN) > Institute of Diagnostic, Interventional and Paediatric Radiology > DCR Magnetic Resonance Spectroscopy and Methodology (AMSM)
04 Faculty of Medicine > Pre-clinic Human Medicine > BioMedical Research (DBMR)
04 Faculty of Medicine > Pre-clinic Human Medicine > BioMedical Research (DBMR) > Forschungsbereich Pavillon 52 > Abt. Magnetresonanz-Spektroskopie und Methodologie, AMSM
04 Faculty of Medicine > Faculty Institutions > Teaching Staff, Faculty of Medicine

Graduate School:

Graduate School for Cellular and Biomedical Sciences (GCB)

UniBE Contributor:

Kyathanahally, Sreenath Pruthviraj; Döring, André and Kreis, Roland

Subjects:

600 Technology > 610 Medicine & health

ISSN:

0740-3194

Publisher:

Wiley-Liss

Funders:

[4] Swiss National Science Foundation

Language:

English

Submitter:

Roland Kreis

Date Deposited:

16 Apr 2018 12:39

Last Modified:

24 Oct 2019 06:53

Publisher DOI:

10.1002/mrm.27096

PubMed ID:

29388313

Uncontrolled Keywords:

artifacts deep learning human brain machine learning magnetic resonance spectroscopy quality control time-frequency representation

BORIS DOI:

10.7892/boris.111229

URI:

https://boris.unibe.ch/id/eprint/111229

Actions (login required)

Edit item Edit item
Provide Feedback