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
. 2022 Jan;10(2):35.
doi: 10.21037/atm-21-4056.

Detecting brain lesions in suspected acute ischemic stroke with CT-based synthetic MRI using generative adversarial networks

Na Hu #  1   2 , Tianwei Zhang #  3 , Yifan Wu  4 , Biqiu Tang  2 , Minlong Li  2   5 , Bin Song  1 , Qiyong Gong  2 , Min Wu  2 , Shi Gu  3 , Su Lui  2
Affiliations

Detecting brain lesions in suspected acute ischemic stroke with CT-based synthetic MRI using generative adversarial networks

Na Hu et al. Ann Transl Med. 2022 Jan.

Abstract

Background: Difficulties in detecting brain lesions in acute ischemic stroke (AIS) have convinced researchers to use computed tomography (CT) to scan for and magnetic resonance imaging (MRI) to search for these lesions. This work aimed to develop a generative adversarial network (GAN) model for CT-to-MR image synthesis and evaluate reader performance with synthetic MRI (syn-MRI) in detecting brain lesions in suspected patients.

Methods: Patients with primarily suspected AIS were randomly assigned to the training (n=140) or testing (n=53) set. Emergency CT and follow-up MR images in the training set were used to develop a GAN model to generate syn-MR images from the CT data in the testing set. The standard reference was the manual segmentations of follow-up MR images. Image similarity was evaluated between syn-MRI and the ground truth using a 4-grade visual rating scale, the peak signal-to-noise ratio (PSNR), and the structural similarity index measure (SSIM). Reader performance with syn-MRI and CT was evaluated and compared on a per-patient (patient detection) and per-lesion (lesion detection) basis. Paired t-tests or Wilcoxon signed-rank tests were used to compare reader performance in lesion detection between the syn-MRI and CT data.

Results: Grade 2-4 brain lesions were observed on syn-MRI in 92.5% (49/53) of the patients, while the remaining syn-MRI data showed no lesions compared to the ground truth. The GAN model exhibited a weak PSNR of 24.30 dB but a favorable SSIM of 0.857. Compared with CT, syn-MRI led to an increase in the overall sensitivity from 38% (57/150) to 82% (123/150) in patient detection and from 4% (68/1,620) to 16% (262/1,620) in lesion detection (R=0.32, corrected P<0.001), but the specificity in patient detection decreased from 67% (6/9) to 33% (3/9). An additional 75% (70/93) of patients and 15% (77/517) of lesions missed on CT were detected on syn-MRI.

Conclusions: The GAN model holds potential for generating synthetic MR images from noncontrast CT data and thus could help sensitively detect individuals among patients with suspected AIS. However, the image similarity performance of the model needs to be improved, and further expert discrimination is strongly recommended.

Keywords: Acute ischemic stroke (AIS); CT-to-MR image synthesis; generative adversarial network (GAN); imaging diagnosis.

PubMed Disclaimer

Conflict of interest statement

Conflicts of Interest: All authors have completed the ICMJE uniform disclosure form (available at https://atm.amegroups.com/article/view/10.21037/atm-21-4056/coif). NH, TZ, SG, and SL report two related patents pending (Chinese patent number 202010522445.1; PCT number PCT/CN2020/118667). NH reports that this work was supported by National Natural Science Foundation of China (grant number 82102000) and Sichuan Science and Technology Program (grant number 2019YJ0155). BS reports that this work was supported by National Key Research and Development Program of China (grant number 2018YFC0116400). SG reports that this work was supported by National Natural Science Foundation of China (grant number 61876032). SL reports that this work was supported by National Natural Science Foundation of China (grant number 81671664) and 1·3·5 Project for Disciplines of Excellence, West China Hospital, Sichuan University (grant number ZYJC18020). The other authors have no conflicts of interest to declare.

Figures

Figure 1
Figure 1
Flowchart of patient inclusion and exclusion. CT, computed tomography; FLAIR, fluid-attenuated inversion recovery.
Figure 2
Figure 2
Training and testing of the generative adversarial network model. CT, computed tomography; FLAIR, fluid-attenuated inversion recovery; 3D, three-dimensional; MRI, magnetic resonance imaging.
Figure 3
Figure 3
Examples of Grade 1 similarity between synthetic MRI and ground-truth FLAIR imaging. (A) An 80-year-old female with an acute medium-sized infarction in the right frontal lobe (onset-to-CT time, 2 hours; CT-to-MRI time, 2 days). (B) A 76-year-old male with an acute large-scale infarction in the right middle cerebral artery territory (onset-to-CT time, 2 hours; CT-to-MRI time, 2 days). Head CT (left) and synthetic MRI (middle) of both patients fail to show any definite infarcts, but FLAIR (right) confirms the acute lesions as hyperintensities. MRI, magnetic resonance imaging; FLAIR, fluid-attenuated inversion recovery; CT, computed tomography.
Figure 4
Figure 4
Examples of patient detection using synthetic MRI versus CT. (A) A 72-year-old man with a small acute infarct in the right insula. Head CT (left) fails to show any abnormal parenchymal hypodensities. In contrast, synthetic MRI (middle) shows regional hyperintensity in the right insula, consistent with FLAIR (right). (B) A 48-year-old woman with bilateral infarcts of different phases, an acute lesion in the left basal ganglia and a chronic lesion (lacune) in the right corona radiata. Head CT (left) shows the chronic but not the acute lesion, while synthetic MRI (middle) shows both, which are confirmed on FLAIR (right). MRI, magnetic resonance imaging; CT, computed tomography; FLAIR, fluid-attenuated inversion recovery.
Figure 5
Figure 5
Overall reader performance in lesion detection. The overall sensitivity (P<0.001), positive predictive value (P=0.002), and F measure (P=0.007) were significantly improved when using synthetic MRI versus CT. *, P<0.05; **, P<0.01. MRI, magnetic resonance imaging; CT, computed tomography.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

References

    1. Powers WJ, Rabinstein AA, Ackerson T, et al. Guidelines for the early management of patients with acute ischemic stroke: 2019 update to the 2018 guidelines for the early management of acute ischemic stroke: A guideline for healthcare professionals from the American Heart Association/American Stroke Association. Stroke 2019;50:e344-418. Erratum in: Stroke 2019;50:e440-1. 10.1161/STR.0000000000000211 - DOI - PubMed
    1. von Kummer R, Dzialowski I. Imaging of cerebral ischemic edema and neuronal death. Neuroradiology 2017;59:545-53. 10.1007/s00234-017-1847-6 - DOI - PubMed
    1. Allen LM, Hasso AN, Handwerker J, et al. Sequence-specific MR imaging findings that are useful in dating ischemic stroke. Radiographics 2012;32:1285-97; discussion 1297-9. 10.1148/rg.325115760 - DOI - PubMed
    1. Sauser K, Levine DA, Nickles AV, et al. Hospital variation in thrombolysis times among patients with acute ischemic stroke: The contributions of door-to-imaging time and imaging-to-needle time. JAMA Neurol 2014;71:1155-61. 10.1001/jamaneurol.2014.1528 - DOI - PubMed
    1. Berlyand Y, Raja AS, Dorner SC, et al. How artificial intelligence could transform emergency department operations. Am J Emerg Med 2018;36:1515-7. 10.1016/j.ajem.2018.01.017 - DOI - PubMed