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 Jul 11;12(7):1690.
doi: 10.3390/diagnostics12071690.

Exploiting the Dixon Method for a Robust Breast and Fibro-Glandular Tissue Segmentation in Breast MRI

Riccardo Samperna  1   2 , Nikita Moriakov  1   3 , Nico Karssemeijer  1   4 , Jonas Teuwen  1   3 , Ritse M Mann  1   2
Affiliations

Exploiting the Dixon Method for a Robust Breast and Fibro-Glandular Tissue Segmentation in Breast MRI

Riccardo Samperna et al. Diagnostics (Basel). .

Abstract

Automatic breast and fibro-glandular tissue (FGT) segmentation in breast MRI allows for the efficient and accurate calculation of breast density. The U-Net architecture, either 2D or 3D, has already been shown to be effective at addressing the segmentation problem in breast MRI. However, the lack of publicly available datasets for this task has forced several authors to rely on internal datasets composed of either acquisitions without fat suppression (WOFS) or with fat suppression (FS), limiting the generalization of the approach. To solve this problem, we propose a data-centric approach, efficiently using the data available. By collecting a dataset of T1-weighted breast MRI acquisitions acquired with the use of the Dixon method, we train a network on both T1 WOFS and FS acquisitions while utilizing the same ground truth segmentation. Using the "plug-and-play" framework nnUNet, we achieve, on our internal test set, a Dice Similarity Coefficient (DSC) of 0.96 and 0.91 for WOFS breast and FGT segmentation and 0.95 and 0.86 for FS breast and FGT segmentation, respectively. On an external, publicly available dataset, a panel of breast radiologists rated the quality of our automatic segmentation with an average of 3.73 on a four-point scale, with an average percentage agreement of 67.5%.

Keywords: MRI; breast; data-centric AI; deep learning; segmentation.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict 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
Examples of in-phase and reconstructed water Dixon acquisitions from our internal dataset used to mimic acquisitions without (WOFS) and with (FS) fat suppression. (a) In-phase Dixon acquisition used as WOFS image. (b) Reconstructed water Dixon acquisition used as FS image.
Figure 2
Figure 2
Example of manual annotation of fat tissue (green) and FGT (red) in WOFS image.
Figure 3
Figure 3
Screenshot of reader study set-up. The Grand Challenge platform allows the set-up of a web-based reader study with a fully functional medical imaging viewer. In this reader study, we showed participants the same WOFS and FS case side-by-side, and they were asked to answer the questions on the left side of the screen, which, in this case, were multiple choice questions.
Figure 4
Figure 4
Bland–Altman plot to compare the breast density (BD) calculated on ground truth manual annotation and BD calculated from breast and FGT segmentations generated by the network trained with WOFS + FS acquisitions. (a) Bland–Altman plot for WOFS test cases. (b) Bland–Altman plot for FS test cases.
Figure 5
Figure 5
Internal test set results (n = 9 patients, 18 acquisitions (9 WOFS, 9 FS)). Reader study confusion matrix comparing the ratings (1—Poor, 2—Fair, 3—Good, 4—Excellent) from the two readers.
Figure 6
Figure 6
External test set results (n = 30 patients, 60 acquisitions (30 WOFS, 30 FS)). Reader study confusion matrix comparing the ratings (1—Poor, 2—Fair, 3—Good, 4—Excellent) from the two readers.
Figure 7
Figure 7
Example slices of FGT segmentations from external test set acquisitions rated either poor or fair during the reader study assessment.
See this image and copyright information in PMC

References

    1. Mann R.M., Cho N., Moy L. Breast MRI: State of the Art. Radiology. 2019;292:520–536. doi: 10.1148/radiol.2019182947. - DOI - PubMed
    1. Bakker M.F., de Lange S.V., Pijnappel R.M., Mann R.M., Peeters P.H.M., Monninkhof E.M., Emaus M.J., Loo C.E., Bisschops R.H.C., Lobbes M.B.I., et al. Supplemental MRI Screening for Women with Extremely Dense Breast Tissue. N. Engl. J. Med. 2019;381:2091–2102. doi: 10.1056/NEJMoa1903986. - DOI - PubMed
    1. Mann R.M., Athanasiou A., Baltzer P.A.T., Camps-Herrero J., Clauser P., Fallenberg E.M., Forrai G., Fuchsjäger M.H., Helbich T.H., Killburn-Toppin F., et al. Breast cancer screening in women with extremely dense breasts recommendations of the European Society of Breast Imaging (EUSOBI) Eur. Radiol. 2022;32:4036–4045. doi: 10.1007/s00330-022-08617-6. - DOI - PMC - PubMed
    1. American College of Radiology . ACR BI-RADS Atlas: Breast Imaging Reporting and Data System. 5th ed. American College of Radiology; Reston, VA, USA: 2013.
    1. Redondo A., Comas M., Macià F., Ferrer F., Murta-Nascimento C., Maristany M.T., Molins E., Sala M., Castells X. Inter- and intraradiologist variability in the BI-RADS assessment and breast density categories for screening mammograms. Br. J. Radiol. 2012;85:1465–1470. doi: 10.1259/bjr/21256379. - DOI - PMC - PubMed

LinkOut - more resources