Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2021 Aug 25;11(9):1542.
doi: 10.3390/diagnostics11091542.

Generating Virtual Short Tau Inversion Recovery (STIR) Images from T1- and T2-Weighted Images Using a Conditional Generative Adversarial Network in Spine Imaging

Johannes Haubold  1 , Aydin Demircioglu  1 , Jens Matthias Theysohn  1 , Axel Wetter  1 , Alexander Radbruch  2 , Nils Dörner  1 , Thomas Wilfried Schlosser  1 , Cornelius Deuschl  1 , Yan Li  1 , Kai Nassenstein  1 , Benedikt Michael Schaarschmidt  1 , Michael Forsting  1 , Lale Umutlu  1 , Felix Nensa  1   3
Affiliations

Generating Virtual Short Tau Inversion Recovery (STIR) Images from T1- and T2-Weighted Images Using a Conditional Generative Adversarial Network in Spine Imaging

Johannes Haubold et al. Diagnostics (Basel). .

Abstract

Short tau inversion recovery (STIR) sequences are frequently used in magnetic resonance imaging (MRI) of the spine. However, STIR sequences require a significant amount of scanning time. The purpose of the present study was to generate virtual STIR (vSTIR) images from non-contrast, non-fat-suppressed T1- and T2-weighted images using a conditional generative adversarial network (cGAN). The training dataset comprised 612 studies from 514 patients, and the validation dataset comprised 141 studies from 133 patients. For validation, 100 original STIR and respective vSTIR series were presented to six senior radiologists (blinded for the STIR type) in independent A/B-testing sessions. Additionally, for 141 real or vSTIR sequences, the testers were required to produce a structured report of 15 different findings. In the A/B-test, most testers could not reliably identify the real STIR (mean error of tester 1-6: 41%; 44%; 58%; 48%; 39%; 45%). In the evaluation of the structured reports, vSTIR was equivalent to real STIR in 13 of 15 categories. In the category of the number of STIR hyperintense vertebral bodies (p = 0.08) and in the diagnosis of bone metastases (p = 0.055), the vSTIR was only slightly insignificantly equivalent. By virtually generating STIR images of diagnostic quality from T1- and T2-weighted images using a cGAN, one can shorten examination times and increase throughput.

Keywords: computing; machine learning; magnetic resonance imaging; medical informatics; spine.

PubMed Disclaimer

Conflict of interest statement

The authors declare that there is no competing interest.

Figures

Figure 1
Figure 1
A/B-test to identify the real STIR sequence.
Figure 2
Figure 2
Structured reporting using our web tool developed in-house.
Figure 3
Figure 3
Examples of the validation cohort.
Figure 4
Figure 4
Diagram of the mean acquisition times with (left) and without STIR sequence.
Figure 5
Figure 5
Acquisition of the virtual STIR image from the merged T1 and T2 image compared to the real STIR sequence.
See this image and copyright information in PMC

References

    1. Yu L., Wang X., Lin X., Wang Y. The Use of Lumbar Spine Magnetic Resonance Imaging in Eastern China: Appropriateness and Related Factors. PLoS ONE. 2016;11:e0146369. doi: 10.1371/journal.pone.0146369. - DOI - PMC - PubMed
    1. Saadat S., Ghodsi S.M., Firouznia K., Etminan M., Goudarzi K., Naieni K.H. Overuse or Underuse of MRI Scanners in Private Radiology Centers in Tehran. Int. J. Technol. Assess. Health Care. 2008;24:277–281. doi: 10.1017/S0266462308080379. - DOI - PubMed
    1. Mahnken A.H., Wildberger J.E., Adam G., Stanzel S., Schmitz-Rode T., Günther R.W., Buecker A. Is There a Need for Contrast-Enhanced T1-Weighted MRI of the Spine after Inconspicuous Short Tau Inversion Recovery Imaging? Eur. Radiol. 2005;15:1387–1392. doi: 10.1007/s00330-005-2719-8. - DOI - PubMed
    1. Kumar Y., Hayashi D. Role of Magnetic Resonance Imaging in Acute Spinal Trauma: A Pictorial Review. BMC Musculoskelet. Disord. 2016;17:310. doi: 10.1186/s12891-016-1169-6. - DOI - PMC - PubMed
    1. Low R.N., Austin M.J., Ma J. Fast Spin-Echo Triple Echo Dixon: Initial Clinical Experience with a Novel Pulse Sequence for Simultaneous Fat-Suppressed and Nonfat-Suppressed T2-Weighted Spine Magnetic Resonance Imaging. J. Magn. Reson. Imaging JMRI. 2011;33:390–400. doi: 10.1002/jmri.22453. - DOI - PubMed

LinkOut - more resources