Skip to main content

Main menu

  • Home
  • Content
    • Current
    • Ahead of print
    • Past Issues
    • JNM Supplement
    • SNMMI Annual Meeting Abstracts
    • Continuing Education
    • JNM Podcasts
  • Subscriptions
    • Subscribers
    • Institutional and Non-member
    • Rates
    • Journal Claims
    • Corporate & Special Sales
  • Authors
    • Submit to JNM
    • Information for Authors
    • Assignment of Copyright
    • AQARA requirements
  • Info
    • Reviewers
    • Permissions
    • Advertisers
  • About
    • About Us
    • Editorial Board
    • Contact Information
  • More
    • Alerts
    • Feedback
    • Help
    • SNMMI Journals
  • SNMMI
    • JNM
    • JNMT
    • SNMMI Journals
    • SNMMI

User menu

  • Subscribe
  • My alerts
  • Log in
  • My Cart

Search

  • Advanced search
Journal of Nuclear Medicine
  • SNMMI
    • JNM
    • JNMT
    • SNMMI Journals
    • SNMMI
  • Subscribe
  • My alerts
  • Log in
  • My Cart
Journal of Nuclear Medicine

Advanced Search

  • Home
  • Content
    • Current
    • Ahead of print
    • Past Issues
    • JNM Supplement
    • SNMMI Annual Meeting Abstracts
    • Continuing Education
    • JNM Podcasts
  • Subscriptions
    • Subscribers
    • Institutional and Non-member
    • Rates
    • Journal Claims
    • Corporate & Special Sales
  • Authors
    • Submit to JNM
    • Information for Authors
    • Assignment of Copyright
    • AQARA requirements
  • Info
    • Reviewers
    • Permissions
    • Advertisers
  • About
    • About Us
    • Editorial Board
    • Contact Information
  • More
    • Alerts
    • Feedback
    • Help
    • SNMMI Journals
  • View or Listen to JNM Podcast
  • Visit JNM on Facebook
  • Join JNM on LinkedIn
  • Follow JNM on Twitter
  • Subscribe to our RSS feeds
Research ArticleClinical Investigation

Clinical Decision Support for Axillary Lymph Node Staging in Newly Diagnosed Breast Cancer Patients Based on 18F-FDG PET/MRI and Machine Learning

Janna Morawitz, Benjamin Sigl, Christian Rubbert, Nils-Martin Bruckmann, Frederic Dietzel, Lena J. Häberle, Saskia Ting, Svjetlana Mohrmann, Eugen Ruckhäberle, Ann-Kathrin Bittner, Oliver Hoffmann, Pascal Baltzer, Panagiotis Kapetas, Thomas Helbich, Paola Clauser, Wolfgang P. Fendler, Christoph Rischpler, Ken Herrmann, Benedikt M. Schaarschmidt, Andreas Stang, Lale Umutlu, Gerald Antoch, Julian Caspers and Julian Kirchner
Journal of Nuclear Medicine February 2023, 64 (2) 304-311; DOI: https://doi.org/10.2967/jnumed.122.264138
Janna Morawitz
1Department of Diagnostic and Interventional Radiology, Medical Faculty, University of Duesseldorf, Duesseldorf, Germany;
  • Find this author on Google Scholar
  • Find this author on PubMed
  • Search for this author on this site
Benjamin Sigl
2Department of Biomedical Imaging and Image-Guided Therapy, Division of General Radiology, Medical University of Vienna, Vienna, Austria;
  • Find this author on Google Scholar
  • Find this author on PubMed
  • Search for this author on this site
Christian Rubbert
1Department of Diagnostic and Interventional Radiology, Medical Faculty, University of Duesseldorf, Duesseldorf, Germany;
  • Find this author on Google Scholar
  • Find this author on PubMed
  • Search for this author on this site
Nils-Martin Bruckmann
1Department of Diagnostic and Interventional Radiology, Medical Faculty, University of Duesseldorf, Duesseldorf, Germany;
  • Find this author on Google Scholar
  • Find this author on PubMed
  • Search for this author on this site
Frederic Dietzel
1Department of Diagnostic and Interventional Radiology, Medical Faculty, University of Duesseldorf, Duesseldorf, Germany;
  • Find this author on Google Scholar
  • Find this author on PubMed
  • Search for this author on this site
Lena J. Häberle
3Institute of Pathology, Medical Faculty, Heinrich Heine University and University Hospital Duesseldorf, Duesseldorf, Germany;
  • Find this author on Google Scholar
  • Find this author on PubMed
  • Search for this author on this site
Saskia Ting
4Institute of Pathology, University Hospital Essen, West German Cancer Center, University of Duisburg–Essen and the German Cancer Consortium (DKTK), Essen, Germany;
  • Find this author on Google Scholar
  • Find this author on PubMed
  • Search for this author on this site
Svjetlana Mohrmann
5Department of Gynecology, University of Duesseldorf, Medical Faculty, Duesseldorf, Germany;
  • Find this author on Google Scholar
  • Find this author on PubMed
  • Search for this author on this site
Eugen Ruckhäberle
5Department of Gynecology, University of Duesseldorf, Medical Faculty, Duesseldorf, Germany;
  • Find this author on Google Scholar
  • Find this author on PubMed
  • Search for this author on this site
Ann-Kathrin Bittner
6Department of Gynecology and Obstetrics, University Hospital Essen, University of Duisburg–Essen, Essen, Germany;
  • Find this author on Google Scholar
  • Find this author on PubMed
  • Search for this author on this site
Oliver Hoffmann
6Department of Gynecology and Obstetrics, University Hospital Essen, University of Duisburg–Essen, Essen, Germany;
  • Find this author on Google Scholar
  • Find this author on PubMed
  • Search for this author on this site
Pascal Baltzer
2Department of Biomedical Imaging and Image-Guided Therapy, Division of General Radiology, Medical University of Vienna, Vienna, Austria;
  • Find this author on Google Scholar
  • Find this author on PubMed
  • Search for this author on this site
Panagiotis Kapetas
2Department of Biomedical Imaging and Image-Guided Therapy, Division of General Radiology, Medical University of Vienna, Vienna, Austria;
  • Find this author on Google Scholar
  • Find this author on PubMed
  • Search for this author on this site
Thomas Helbich
2Department of Biomedical Imaging and Image-Guided Therapy, Division of General Radiology, Medical University of Vienna, Vienna, Austria;
  • Find this author on Google Scholar
  • Find this author on PubMed
  • Search for this author on this site
Paola Clauser
2Department of Biomedical Imaging and Image-Guided Therapy, Division of General Radiology, Medical University of Vienna, Vienna, Austria;
  • Find this author on Google Scholar
  • Find this author on PubMed
  • Search for this author on this site
Wolfgang P. Fendler
7Department of Nuclear Medicine, University Hospital Essen, University of Duisburg–Essen and German Cancer Consortium (DKTK), Essen, Germany;
  • Find this author on Google Scholar
  • Find this author on PubMed
  • Search for this author on this site
Christoph Rischpler
7Department of Nuclear Medicine, University Hospital Essen, University of Duisburg–Essen and German Cancer Consortium (DKTK), Essen, Germany;
  • Find this author on Google Scholar
  • Find this author on PubMed
  • Search for this author on this site
Ken Herrmann
7Department of Nuclear Medicine, University Hospital Essen, University of Duisburg–Essen and German Cancer Consortium (DKTK), Essen, Germany;
  • Find this author on Google Scholar
  • Find this author on PubMed
  • Search for this author on this site
Benedikt M. Schaarschmidt
8Department of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital Essen, University of Duisburg–Essen, Essen, Germany; and
  • Find this author on Google Scholar
  • Find this author on PubMed
  • Search for this author on this site
Andreas Stang
9Institute of Medical Informatics, Biometry, and Epidemiology, Essen University Medical Center, Essen, Germany
  • Find this author on Google Scholar
  • Find this author on PubMed
  • Search for this author on this site
Lale Umutlu
8Department of Diagnostic and Interventional Radiology and Neuroradiology, University Hospital Essen, University of Duisburg–Essen, Essen, Germany; and
  • Find this author on Google Scholar
  • Find this author on PubMed
  • Search for this author on this site
Gerald Antoch
1Department of Diagnostic and Interventional Radiology, Medical Faculty, University of Duesseldorf, Duesseldorf, Germany;
  • Find this author on Google Scholar
  • Find this author on PubMed
  • Search for this author on this site
Julian Caspers
1Department of Diagnostic and Interventional Radiology, Medical Faculty, University of Duesseldorf, Duesseldorf, Germany;
  • Find this author on Google Scholar
  • Find this author on PubMed
  • Search for this author on this site
Julian Kirchner
1Department of Diagnostic and Interventional Radiology, Medical Faculty, University of Duesseldorf, Duesseldorf, Germany;
  • Find this author on Google Scholar
  • Find this author on PubMed
  • Search for this author on this site
  • Article
  • Figures & Data
  • Supplemental
  • Info & Metrics
  • PDF
Loading

Article Figures & Data

Figures

  • Tables
  • Additional Files
  • Figure
    • Download figure
    • Open in new tab
    • Download powerpoint
  • FIGURE 1.
    • Download figure
    • Open in new tab
    • Download powerpoint
    FIGURE 1.

    Flowchart of included and excluded participants. G3 = grade 3; Her2neu = human epidermal growth factor receptor type 2.

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

    Examples of morphologic and metabolic features for assessment of axillary lymph nodes in axial T1-weighted, volume-interpolated breath-hold examination, fat-saturated, contrast-enhanced images. Enlarged lymph node has short-axis diameter of 31 mm. Lymph node with increased 18F-FDG uptake has SUVmax of 13.1.

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

    ROC AUC for random forest model performance on testing data and for prediction of lymph node status by radiologists on MRI and PET/MRI. LN = lymph node.

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

    Importance of different morphologic and metabolic features of lymph nodes.

  • FIGURE 5.
    • Download figure
    • Open in new tab
    • Download powerpoint
    FIGURE 5.

    Precision and recall scores as function of decision threshold on internal validation sample. x represents threshold values, and y is score of precision or recall. Adjusted decision threshold for optimized sensitivity is indicated by dashed line.

  • FIGURE 6.
    • Download figure
    • Open in new tab
    • Download powerpoint
    FIGURE 6.

    (A) Decision tree for predicting lymph node status in MRI and PET/MRI. (B) ROC AUC for size and for SUVmax ratio of lymph node to mediastinal blood pool for prediction of lymph node status. Ao = aorta; LN = lymph node.

Tables

  • Figures
  • Additional Files
    • View popup
    TABLE 1.

    Participant Demographics and Tumor Characteristics

    ParameterTraining sampleTesting sampleP
    Total participants25548
    Mean age (±SD)51.2 ± 11.9 y52.2 ± 12.2 y0.689
    Lymph node status (reference standard)
     Negative154 (60.4%)26 (54.2%)0.420
     Positive101 (39.6%)22 (45.8%)
    Menopause status
     Premenopausal111 (43.5%)18 (37.5%)0.737
     Perimenopausal25 (9.8%)5 (10.4%)
     Postmenopausal119 (46.7%)25 (52.1%)
    Ki-67
     Positive > 14%226 (88.6%)41 (85.4%)0.528
     Negative < 14%29 (11.4%)7 (14.6%)
    Progesterone status
     Positive169 (66.3%)29 (60.4%)0.433
     Negative86 (33.7%)19 (39.6%)
    Estrogen status
     Positive187 (73.3%)28 (58.3%)<0.01
     Negative68 (26.7%)20 (41.7%)
    HER2neu expression
     097 (38.0%)23 (47.9%)0.479
     1+73 (28.6%)14 (29.2%)
     2+34 (13.3%)5 (10.4%)
     3+51 (20.0%)6 (12.5%)
    Tumor grade
     110 (3.9%)4 (8.3%)0.025
     2137 (53.7%)16 (33.3%)
     3108 (42.4%)28 (58.3%)
    Histology
     No special type222 (87.1%)42 (87.5%)< 0.01
     Lobular invasive25 (9.8%)0 (0%)
     Other8 (3.1%)6 (12.5%)
    • HER2neu = human epidermal growth factor receptor type 2.

    • Data are number and percentage, except for age.

    • View popup
    TABLE 2.

    Diagnostic Performance of MRI and PET/MRI in Assessment of Lymph Node Status of Radiologists and Random Forest Classifier Within Testing Sample

    AssessorMRIPET/MRI
    Radiologists
     Sensitivity84.6 (65.1–95.6)92.3 (74.9–99.1)
     Specificity90.9 (70.8–98.9)86.4 (65.1–97.1)
     PPV91.7 (74.4–97.7)88.9 (73.5–96.8)
     NPV83.3 (66.8–92.6)90.5 (71.3–97.3)
     Accuracy87.5 (74.8–95.3)89.6 (77.3–96.5)
    Random forest algorithm
     Sensitivity88.5 (69.9–97.6)88.5 (69.9–97.6) (reader 1), 88.5 (69.9–97.6) (reader 2)
     Specificity86.4 (65.1–97.1)86.4 (65.1–97.1) (reader 1), 81.8 (59.7–94.8) (reader 2)
     PPV88.5 (72.6–95.7)88.5 (72.6–95.7) (reader 1), 85.2 (70.1–93.4) (reader 2)
     NPV86.4 (68.3–94.9)86.4 (68.3–94.9) (reader 1), 85.7 (67.0–94.7) (reader 2)
     Accuracy87.5 (74.8–96.3)87.5 (74.8–96.3) (reader 1), 85.4 (72.2–93.9) (reader 2)
    • Data are percentages, with 95% CIs in parentheses.

    • View popup
    TABLE 3.

    Confusion Matrix for Adjusted Threshold

    ActualPredicted
    NegativePositive
    Negative157
    Positive125
    • View popup
    TABLE 4.

    Performance Metrics for Adjusted Threshold

    MetricData
    Sensitivity96.2% (80.4%–99.9%)
    Specificity68.2% (45.1%–86.1%)
    PPV78.1% (65.9%–86.9%)
    NPV93.8% (68.2%–99.1%)
    Accuracy83.3% (69.8%–92.5%)
    • Data in parentheses are ranges.

    • View popup
    TABLE 5.

    Confusion Matrices for Decision Trees

    ActualPredicted
    MRIPET/MRI
    NegativePositiveNegativePositive
    Negative202211
    Positive323422
    • View popup
    TABLE 6.

    Performance Metrics for Decision Trees

    MetricData
    MRI
     Sensitivity88.5% (69.9%–97.6%)
     Specificity90.9% (70.8%–98.9%)
     PPV92.0% (75.3%–97.8%)
     NPV87.0% (69.5%–95.1%)
     Accuracy89.6% (77.3%–96.5%)
    PET/MRI
     Sensitivity84.6% (65.1%–95.6%)
     Specificity95.5% (77.2%–99.9%)
     PPV95.7% (76.3%–99.3%)
     NPV84.0% (68.0–92.9. %)
     Accuracy89.6% (77.3%–96.5%)
    • Data in parentheses are ranges.

Additional Files

  • Figures
  • Tables
  • Supplemental Data

    Files in this Data Supplement:

    • Supplemental Data
PreviousNext
Back to top

In this issue

Journal of Nuclear Medicine: 64 (2)
Journal of Nuclear Medicine
Vol. 64, Issue 2
February 1, 2023
  • Table of Contents
  • Table of Contents (PDF)
  • About the Cover
  • Index by author
  • Complete Issue (PDF)
Print
Download PDF
Article Alerts
Sign In to Email Alerts with your Email Address
Email Article

Thank you for your interest in spreading the word on Journal of Nuclear Medicine.

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.
Clinical Decision Support for Axillary Lymph Node Staging in Newly Diagnosed Breast Cancer Patients Based on 18F-FDG PET/MRI and Machine Learning
(Your Name) has sent you a message from Journal of Nuclear Medicine
(Your Name) thought you would like to see the Journal of Nuclear Medicine web site.
Citation Tools
Clinical Decision Support for Axillary Lymph Node Staging in Newly Diagnosed Breast Cancer Patients Based on 18F-FDG PET/MRI and Machine Learning
Janna Morawitz, Benjamin Sigl, Christian Rubbert, Nils-Martin Bruckmann, Frederic Dietzel, Lena J. Häberle, Saskia Ting, Svjetlana Mohrmann, Eugen Ruckhäberle, Ann-Kathrin Bittner, Oliver Hoffmann, Pascal Baltzer, Panagiotis Kapetas, Thomas Helbich, Paola Clauser, Wolfgang P. Fendler, Christoph Rischpler, Ken Herrmann, Benedikt M. Schaarschmidt, Andreas Stang, Lale Umutlu, Gerald Antoch, Julian Caspers, Julian Kirchner
Journal of Nuclear Medicine Feb 2023, 64 (2) 304-311; DOI: 10.2967/jnumed.122.264138

Citation Manager Formats

  • BibTeX
  • Bookends
  • EasyBib
  • EndNote (tagged)
  • EndNote 8 (xml)
  • Medlars
  • Mendeley
  • Papers
  • RefWorks Tagged
  • Ref Manager
  • RIS
  • Zotero
Share
Clinical Decision Support for Axillary Lymph Node Staging in Newly Diagnosed Breast Cancer Patients Based on 18F-FDG PET/MRI and Machine Learning
Janna Morawitz, Benjamin Sigl, Christian Rubbert, Nils-Martin Bruckmann, Frederic Dietzel, Lena J. Häberle, Saskia Ting, Svjetlana Mohrmann, Eugen Ruckhäberle, Ann-Kathrin Bittner, Oliver Hoffmann, Pascal Baltzer, Panagiotis Kapetas, Thomas Helbich, Paola Clauser, Wolfgang P. Fendler, Christoph Rischpler, Ken Herrmann, Benedikt M. Schaarschmidt, Andreas Stang, Lale Umutlu, Gerald Antoch, Julian Caspers, Julian Kirchner
Journal of Nuclear Medicine Feb 2023, 64 (2) 304-311; DOI: 10.2967/jnumed.122.264138
Twitter logo Facebook logo LinkedIn logo Mendeley logo
  • Tweet Widget
  • Facebook Like
  • Google Plus One
Bookmark this article

Jump to section

  • Article
    • Visual Abstract
    • Abstract
    • MATERIALS AND METHODS
    • RESULTS
    • DISCUSSION
    • CONCLUSION
    • DISCLOSURE
    • Footnotes
    • REFERENCES
  • Figures & Data
  • Supplemental
  • Info & Metrics
  • PDF

Related Articles

  • PubMed
  • Google Scholar

Cited By...

  • No citing articles found.
  • Google Scholar

More in this TOC Section

  • First-in-Human Study of 18F-Labeled PET Tracer for Glutamate AMPA Receptor [18F]K-40: A Derivative of [11C]K-2
  • Detection of HER2-Low Lesions Using HER2-Targeted PET Imaging in Patients with Metastatic Breast Cancer: A Paired HER2 PET and Tumor Biopsy Analysis
  • [11C]Carfentanil PET Whole-Body Imaging of μ-Opioid Receptors: A First in-Human Study
Show more Clinical Investigation

Similar Articles

Keywords

  • breast cancer
  • lymph node metastases
  • machine learning
  • PET/MRI
SNMMI

© 2025 SNMMI

Powered by HighWire