Skip to main content
Advertisement

Main menu

  • Home
  • Content
    • Current Issue
    • Accepted Manuscripts
    • Article Preview
    • Past Issue Archive
    • Video Articles
    • AJNR Case Collection
    • Case of the Week Archive
    • Case of the Month Archive
    • Classic Case Archive
  • Special Collections
    • AJNR Awards
    • Low-Field MRI
    • Alzheimer Disease
    • ASNR Foundation Special Collection
    • Photon-Counting CT
    • View All
  • Multimedia
    • AJNR Podcasts
    • AJNR SCANtastic
    • Trainee Corner
    • MRI Safety Corner
    • Imaging Protocols
  • For Authors
    • Submit a Manuscript
    • Submit a Video Article
    • Submit an eLetter to the Editor/Response
    • Manuscript Submission Guidelines
    • Statistical Tips
    • Fast Publishing of Accepted Manuscripts
    • Graphical Abstract Preparation
    • Imaging Protocol Submission
    • Author Policies
  • About Us
    • About AJNR
    • Editorial Board
    • Editorial Board Alumni
  • More
    • Become a Reviewer/Academy of Reviewers
    • Subscribers
    • Permissions
    • Alerts
    • Feedback
    • Advertisers
    • ASNR Home

User menu

  • Alerts
  • Log in

Search

  • Advanced search
American Journal of Neuroradiology
American Journal of Neuroradiology

American Journal of Neuroradiology

ASHNR American Society of Functional Neuroradiology ASHNR American Society of Pediatric Neuroradiology ASSR
  • Alerts
  • Log in

Advanced Search

  • Home
  • Content
    • Current Issue
    • Accepted Manuscripts
    • Article Preview
    • Past Issue Archive
    • Video Articles
    • AJNR Case Collection
    • Case of the Week Archive
    • Case of the Month Archive
    • Classic Case Archive
  • Special Collections
    • AJNR Awards
    • Low-Field MRI
    • Alzheimer Disease
    • ASNR Foundation Special Collection
    • Photon-Counting CT
    • View All
  • Multimedia
    • AJNR Podcasts
    • AJNR SCANtastic
    • Trainee Corner
    • MRI Safety Corner
    • Imaging Protocols
  • For Authors
    • Submit a Manuscript
    • Submit a Video Article
    • Submit an eLetter to the Editor/Response
    • Manuscript Submission Guidelines
    • Statistical Tips
    • Fast Publishing of Accepted Manuscripts
    • Graphical Abstract Preparation
    • Imaging Protocol Submission
    • Author Policies
  • About Us
    • About AJNR
    • Editorial Board
    • Editorial Board Alumni
  • More
    • Become a Reviewer/Academy of Reviewers
    • Subscribers
    • Permissions
    • Alerts
    • Feedback
    • Advertisers
    • ASNR Home
  • Follow AJNR on Twitter
  • Visit AJNR on Facebook
  • Follow AJNR on Instagram
  • Join AJNR on LinkedIn
  • RSS Feeds

AJNR Awards, New Junior Editors, and more. Read the latest AJNR updates

Research ArticleARTIFICIAL INTELLIGENCE

AI-Generated Synthetic STIR of the Lumbar Spine from T1 and T2 MRI Sequences Trained with Open-Source Algorithms

Alice M.L. Santilli, Mark A. Fontana, Erwin E. Xia, Zenas Igbinoba, Ek Tsoon Tan, Darryl B. Sneag and J. Levi Chazen
American Journal of Neuroradiology February 2025, DOI: https://doi.org/10.3174/ajnr.A8512
Alice M.L. Santilli
aFrom the Orthopedic Data Innovation Lab (ODIL) (A.M.L.S., M.A.F.), Hospital for Special Surgery, New York, New York
  • Find this author on Google Scholar
  • Find this author on PubMed
  • Search for this author on this site
  • ORCID record for Alice M.L. Santilli
Mark A. Fontana
aFrom the Orthopedic Data Innovation Lab (ODIL) (A.M.L.S., M.A.F.), Hospital for Special Surgery, New York, New York
cDepartment of Population Health Sciences (M.A.F.), Weill Cornell Medicine, New York, New York
  • Find this author on Google Scholar
  • Find this author on PubMed
  • Search for this author on this site
  • ORCID record for Mark A. Fontana
Erwin E. Xia
bDepartment of Radiology and Imaging (E.E.X., Z.I., E.T.T., D.B.S., J.L.C.), Hospital for Special Surgery, New York, New York
  • Find this author on Google Scholar
  • Find this author on PubMed
  • Search for this author on this site
Zenas Igbinoba
bDepartment of Radiology and Imaging (E.E.X., Z.I., E.T.T., D.B.S., J.L.C.), Hospital for Special Surgery, New York, New York
  • Find this author on Google Scholar
  • Find this author on PubMed
  • Search for this author on this site
Ek Tsoon Tan
bDepartment of Radiology and Imaging (E.E.X., Z.I., E.T.T., D.B.S., J.L.C.), Hospital for Special Surgery, New York, New York
  • Find this author on Google Scholar
  • Find this author on PubMed
  • Search for this author on this site
  • ORCID record for Ek Tsoon Tan
Darryl B. Sneag
bDepartment of Radiology and Imaging (E.E.X., Z.I., E.T.T., D.B.S., J.L.C.), Hospital for Special Surgery, New York, New York
  • Find this author on Google Scholar
  • Find this author on PubMed
  • Search for this author on this site
  • ORCID record for Darryl B. Sneag
J. Levi Chazen
bDepartment of Radiology and Imaging (E.E.X., Z.I., E.T.T., D.B.S., J.L.C.), Hospital for Special Surgery, New York, New York
  • Find this author on Google Scholar
  • Find this author on PubMed
  • Search for this author on this site
  • ORCID record for J. Levi Chazen
  • Article
  • Figures & Data
  • Supplemental
  • Info & Metrics
  • Responses
  • References
  • PDF
Loading

Article Figures & Data

Figures

  • Tables
  • Figure
    • Download figure
    • Open in new tab
    • Download powerpoint
  • FIG 1.
    • Download figure
    • Open in new tab
    • Download powerpoint
    FIG 1.

    Overview of GAN for producing synthetic STIR volumes. Each patient’s 3 acquired MRI volumes (T1, T2, STIR) are utilized during training of a GAN. The 2 models, generator and discriminator, compete to improve their own performance by either generating (more realistic) synthetic STIR (sSTIR) images or discriminating between sSTIR and acquired STIR (aqSTIR).

  • FIG 2.
    • Download figure
    • Open in new tab
    • Download powerpoint
    FIG 2.

    Top, Example of an acquired STIR volume slice from 1 patient (blue) and the same patient’s equivalent synthetic volume slices generated from GANs with 4 different loss functions (yellow). Bottom, Three zoomed images that allow a comparison of the quality of the basi vertebral venous plexus between the acquired volume slice and 2 synthetic volume slices (SSIM+Sobel+MAE and Foreground-MAE).

  • FIG 3.
    • Download figure
    • Open in new tab
    • Download powerpoint
    FIG 3.

    A slice from a randomly selected volume from the test set, which was assigned a quality metric of 5/5 from the 3 reviewers. Left, Slice from the acquired STIR volume. Right, Same slice from the synthetic STIR volume.

  • FIG 4.
    • Download figure
    • Open in new tab
    • Download powerpoint
    FIG 4.

    Examples of a variety of imaging features. Each pair shows a sample sagittal slice from the acquired STIR volume with its corresponding model-generated synthetic STIR volume.

Tables

  • Figures
    • View popup
    Table 1:

    Patient cohort and imaging descriptionsa

    VariablesData Set
    TrainValidationTest
    Patients163384100
    Sex (% female)53%54%47%
    Age (mean ± SD)57.66 ± 17.755.05 ± 19.561.7 ± 17.8
    Volumes4899252300
    T1/T2 slices42,68821212702
    • aNumber of patients (including sex and age information), number of image volumes, and number of slices in each randomized data set.

    • View popup
    Table 2:

    Summary statistics of radiologists’ assessments of acquired and synthetic volumesa

      Acquired STIR VolumesSynthetic STIR Volumes
    R1R2R3R1R2R3
    Quality (1–5)Average3.923.383.533.833.013.31
    SD0.841.170.791.181.271.08
    Median434434
    Min-max1–51–51–51–51–51–5
    Motion artifact (0–3)Average0.690.741.20.681.141.4
    SD0.810.880.6530.891.040.8
    Median10.51011
    Min-max0–30–30–30–30–30–3
    Acquired vs synthetic (1–5)Average4.163.853.481.111.111.63
    SD0.731.141.050.340.340.89
    Median443111
    Min-max2–51–51–51–41–31–5
    Fat suppression Y/NYes %100%93%100%98%81%96%
    • ↵a Summary statistics of radiologists’ assessments of acquired and synthetic STIR volumes from test set of 100 patients. Three radiologists (R1, R2, R3) each reviewed in a blinded fashion 1 synthetic STIR volume and 1 acquired STIR volume from 100 patients and evaluated each volume’s quality (1 = Unacceptable, 2 = Poor, 3 = Acceptable, 4 = Good, 5 = Excellent), degree of motion artifacts (0 = absent, 1 = mild, 2 = moderate, 3 = severe), whether they believed the volume to be acquired or synthetic (1 = definitely synthetic, 2 = probably synthetic, 3 = unsure, 4 = probably acquired, 5 = definitively acquired) and whether the fat suppression is homogeneous (Y/N) in the volume.

    • View popup
    Table 3:

    Radiologist-assessed occurrence of pathologies present in acquired and synthetic volumesa

    PathologiesAcquired STIRSynthetic STIR
    2/3 Reviewers3/3 Reviewers2/3 Reviewers3/3 Reviewers
    Bone marrow lesion3%2%2%2%
    Spinal cord signal change0%0%0%0%
    Paraspinous muscle edema24%9%9%3%
    Facet arthritis with synovitis13%2%4%1%
    Fracture with edema2%1%0%0%
    Modic type 1 change41%21%19%4%
    Synovial cyst0%0%0%0%
    None25%9%50%21%
    • ↵a Percentage of acquired and synthetic volumes in the test set (n = 100) with each pathology (or none) as determined by the 3 radiologists during the blinded review. Rows detail pathologies available to the 3 radiologist reviewers (including none). Columns detail the percentage of the 100 patients in the test set with each pathology according to 2/3 reviewers or 3/3 reviewers.

    • View popup
    Table 4:

    Majority-rule pathology predictive performancea

    PathologiesPPVSensitivityNPVSpecificity
    Ratio%Ratio%Ratio%Ratio%
    Bone marrow lesion2/2100%2/366.6%97/9898.9%97/97100%
    Spinal cord signal change0/0–0/0–100/100100%100/100100%
    Paraspinous muscle edema9/9100%9/2437.5%76/9183.5%76/76100%
    Facet arthritis with synovitis3/475%3/1323%86/9689.5%86/8798.8%
    Fracture with edema0/0–0/20%98/10098%98/98100%
    Modic type 1 change18/1994.7%18/4143.9%58/8171.6%58/5998.3%
    Synovial cyst0/0–0/0–100/100100%100/100100%
    None30/5060%30/3488.2%46/5092%46/6669.6%
    • ↵a Predictive performance statistics of pathologies from synthetic STIR volumes versus acquired STIR volumes in the test set of 100 patients. Three radiologists each reviewed in a blinded fashion the synthetic and acquired STIR volumes and evaluated the pathologies present in each of them. The rows detail the pathologies available to the 3 radiologist reviewers (including none). Their evaluations of the presence of pathologies were aggregated by using majority-rule; a pathology was considered present in each acquired STIR volume if 2 or 3 reviewers identified it as present, and similarly for each synthetic volume. The columns detail predictive performance metrics (numerator, denominator, and percentage), comparing the prediction (from sSTIR) to the ground truth (from aqSTIR) for each pathology. 95% confidence intervals for the percentage values are available in Supplemental Data.

PreviousNext
Back to top
Advertisement
Print
Download PDF
Email Article

Thank you for your interest in spreading the word on American Journal of Neuroradiology.

NOTE: We only request your email address so that the person you are recommending the page to knows that you wanted them to see it, and that it is not junk mail. We do not capture any email address.

Enter multiple addresses on separate lines or separate them with commas.
AI-Generated Synthetic STIR of the Lumbar Spine from T1 and T2 MRI Sequences Trained with Open-Source Algorithms
(Your Name) has sent you a message from American Journal of Neuroradiology
(Your Name) thought you would like to see the American Journal of Neuroradiology web site.
CAPTCHA
This question is for testing whether or not you are a human visitor and to prevent automated spam submissions.
Cite this article
Alice M.L. Santilli, Mark A. Fontana, Erwin E. Xia, Zenas Igbinoba, Ek Tsoon Tan, Darryl B. Sneag, J. Levi Chazen
AI-Generated Synthetic STIR of the Lumbar Spine from T1 and T2 MRI Sequences Trained with Open-Source Algorithms
American Journal of Neuroradiology Feb 2025, DOI: 10.3174/ajnr.A8512

Citation Manager Formats

  • BibTeX
  • Bookends
  • EasyBib
  • EndNote (tagged)
  • EndNote 8 (xml)
  • Medlars
  • Mendeley
  • Papers
  • RefWorks Tagged
  • Ref Manager
  • RIS
  • Zotero
0 Responses
Respond to this article
Share
Bookmark this article
AI-Synthesized Lumbar Spine STIR from T1 and T2
Alice M.L. Santilli, Mark A. Fontana, Erwin E. Xia, Zenas Igbinoba, Ek Tsoon Tan, Darryl B. Sneag, J. Levi Chazen
American Journal of Neuroradiology Feb 2025, DOI: 10.3174/ajnr.A8512
del.icio.us logo Twitter logo Facebook logo Mendeley logo
  • Tweet Widget
  • Facebook Like
  • Google Plus One
Purchase

Jump to section

  • Article
    • Graphical Abstract
    • Abstract
    • ABBREVIATIONS:
    • MATERIALS AND METHODS
    • RESULTS
    • DISCUSSION
    • CONCLUSIONS
    • Acknowledgment
    • Footnotes
    • References
  • Figures & Data
  • Supplemental
  • Info & Metrics
  • Responses
  • References
  • PDF

Related Articles

  • PubMed
  • Google Scholar

Cited By...

  • No citing articles found.
  • Crossref
  • Google Scholar

This article has not yet been cited by articles in journals that are participating in Crossref Cited-by Linking.

More in this TOC Section

  • Improving Hematoma Expansion Prediction Robustness
  • DIRDL for Inflammatory Myelopathies
  • AI-Enhanced Photon-Counting CT of Temporal Bone
Show more Artificial Intelligence

Similar Articles

Advertisement

Indexed Content

  • Current Issue
  • Accepted Manuscripts
  • Article Preview
  • Past Issues
  • Editorials
  • Editor's Choice
  • Fellows' Journal Club
  • Letters to the Editor
  • Video Articles

Cases

  • Case Collection
  • Archive - Case of the Week
  • Archive - Case of the Month
  • Archive - Classic Case

More from AJNR

  • Trainee Corner
  • Imaging Protocols
  • MRI Safety Corner
  • Book Reviews

Multimedia

  • AJNR Podcasts
  • AJNR Scantastics

Resources

  • Turnaround Time
  • Submit a Manuscript
  • Submit a Video Article
  • Submit an eLetter to the Editor/Response
  • Manuscript Submission Guidelines
  • Statistical Tips
  • Fast Publishing of Accepted Manuscripts
  • Graphical Abstract Preparation
  • Imaging Protocol Submission
  • Evidence-Based Medicine Level Guide
  • Publishing Checklists
  • Author Policies
  • Become a Reviewer/Academy of Reviewers
  • News and Updates

About Us

  • About AJNR
  • Editorial Board
  • Editorial Board Alumni
  • Alerts
  • Permissions
  • Not an AJNR Subscriber? Join Now
  • Advertise with Us
  • Librarian Resources
  • Feedback
  • Terms and Conditions
  • AJNR Editorial Board Alumni

American Society of Neuroradiology

  • Not an ASNR Member? Join Now

© 2025 by the American Society of Neuroradiology All rights, including for text and data mining, AI training, and similar technologies, are reserved.
Print ISSN: 0195-6108 Online ISSN: 1936-959X

Powered by HighWire