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
. 2024 Oct 14;16(20):3480.
doi: 10.3390/cancers16203480.

Development of an MRI Radiomic Machine-Learning Model to Predict Triple-Negative Breast Cancer Based on Fibroglandular Tissue of the Contralateral Unaffected Breast in Breast Cancer Patients

Roberto Lo Gullo  1   2 , Rosa Elena Ochoa-Albiztegui  2 , Jayasree Chakraborty  3 , Sunitha B Thakur  2   4 , Mark Robson  5 , Maxine S Jochelson  2 , Keitha Varela  6 , Daphne Resch  7 , Sarah Eskreis-Winkler  2 , Katja Pinker  1   2
Affiliations

Development of an MRI Radiomic Machine-Learning Model to Predict Triple-Negative Breast Cancer Based on Fibroglandular Tissue of the Contralateral Unaffected Breast in Breast Cancer Patients

Roberto Lo Gullo et al. Cancers (Basel). .

Abstract

Aim: The purpose of this study was to develop a radiomic-based machine-learning model to predict triple-negative breast cancer (TNBC) based on the contralateral unaffected breast's fibroglandular tissue (FGT) in breast cancer patients.

Materials and methods: This study retrospectively included 541 patients (mean age, 51 years; range, 26-82) who underwent a screening breast MRI between November 2016 and September 2018 and who were subsequently diagnosed with biopsy-confirmed, treatment-naïve breast cancer. Patients were divided into training (n = 250) and validation (n = 291) sets. In the training set, 132 radiomic features were extracted using the open-source CERR platform. Following feature selection, the final prediction model was created, based on a support vector machine with a polynomial kernel of order 2.

Results: In the validation set, the final prediction model, which included four radiomic features, achieved an F1 score of 0.66, an area under the curve of 0.71, a sensitivity of 54% [47-60%], a specificity of 74% [65-84%], a positive predictive value of 84% [78-90%], and a negative predictive value of 39% [31-47%].

Conclusions: TNBC can be predicted based on radiomic features extracted from the FGT of the contralateral unaffected breast of patients, suggesting the potential for risk prediction specific to TNBC.

Keywords: breast cancer; fibroglandular tissue; radiomics; triple-negative breast cancer.

PubMed Disclaimer

Conflict of interest statement

Maxine Jochelson declares a paid lecture to GE Healthcare (ended). Katja Pinker declares being part of speakers bureaus for the European Society of Breast Imaging (EUSOBI) (active), Bayer (ended), Siemens Healthineers (ended), DKD 2019 (ended), Olea Medical (ended), and Roche (ended); consulting for Genentech, Merantix Healthcare, AURA Health Technologies. Guerbet, and Bayer. The remaining authors declare no conflicts of interest. The funders had no role in the design of the study; in the collection, analyses, or interpretation of data; in the writing of the manuscript; or in the decision to publish the results.

Figures

Figure 1
Figure 1
An example of fibroglandular tissue segmentation from the contralateral healthy breast on post-contrast T1-weighted imaging. Interspersed as well as surrounding subcutaneous adipose tissue were excluded from the segmentation.
Figure 2
Figure 2
Example of a post-contrast axial T1-weighted image depicting an irregular lesion in the mid-inner quadrant of the left breast, which was correctly predicted by our radiomic machine-learning model as triple-negative breast cancer (TNBC), and an example of a post-contrast axial T1-weighted image depicting an irregular lesion in the lower-inner quadrant of the right, which was correctly predicted by our radiomic machine-learning model as luminal B cancer (ER-positive, PR-negative, and HER2-positive breast cancer). The fibroglandular tissue of the contralateral breast was segmented as in Figure 1.
Figure 3
Figure 3
A comparison of the receiver operating characteristic (ROC) curves of the radiomic machine-learning model to predict the development of triple-negative breast cancer in the training set vs. the validation set. The true-positive rate (sensitivity) on the y-axis is plotted against the false-positive rate (100-specificity) on the x-axis.
See this image and copyright information in PMC

References

    1. American College of Radiology ACR Practice Parameter for the Performance of Contrast-Enhanced Magnetic Resonance Imaging (MRI) of the Breast. Revised 2023 (Resolution 8) [(accessed on 21 February 2024)]. Available online: https://www.acr.org/-/media/ACR/Files/Practice-Parameters/mr-contrast-br....
    1. Wernli K.J., DeMartini W.B., Ichikawa L., Lehman C.D., Onega T., Kerlikowske K., Henderson L.M., Geller B.M., Hofmann M., Yankaskas B.C. Patterns of breast magnetic resonance imaging use in community practice. JAMA Intern. Med. 2014;174:125–132. doi: 10.1001/jamainternmed.2013.11963. - DOI - PMC - PubMed
    1. Ozanne E.M., Drohan B., Bosinoff P., Semine A., Jellinek M., Cronin C., Millham F., Dowd D., Rourke T., Block C., et al. Which risk model to use? Clinical implications of the ACS MRI screening guidelines. Cancer Epidemiol. Biomarkers Prev. 2013;22:146–149. doi: 10.1158/1055-9965.EPI-12-0570. - DOI - PubMed
    1. Yang X.R., Chang-Claude J., Goode E.L., Couch F.J., Nevanlinna H., Milne R.L., Gaudet M., Schmidt M.K., Broeks A., Cox A., et al. Associations of breast cancer risk factors with tumor subtypes: A pooled analysis from the Breast Cancer Association Consortium studies. J. Natl. Cancer Inst. 2011;103:250–263. doi: 10.1093/jnci/djq526. - DOI - PMC - PubMed
    1. Surveillance, Epidemiology, and End Results (SEER) Program, National Cancer Institute, DCCPS Cancer Stat Facts: Female Breast Cancer Subtypes. [(accessed on 21 February 2024)]; Available online: https://seer.cancer.gov/statfacts/html/breast-subtypes.html.

LinkOut - more resources