Estimation of fatty acid composition in mammary adipose tissue using deep neural network with unsupervised training
Magnetic Resonance in Medicine · 2025
DOI: 10.1002/mrm.30401 ↗At a glance
Journal article in Magnetic Resonance in Medicine, 2025. Written by Suneeta Chaudhary and 12 co-authors. Institution: Department of Radiology, Weill Cornell Medical College, New York, New York, USA. Major MEDLINE topics: Fatty Acids, Adipose Tissue, Magnetic Resonance Imaging, Breast. Cited 2 times so far (Crossref); 44 references. The full text is freely available in PubMed Central. Funded by: NCI NIH HHS, National Cancer Institute.
Abstract (original language)
Purpose
To develop a deep learning–based method for robust and rapid estimation of the fatty acid composition (FAC) in mammary adipose tissue.
Methods
A physics‐based unsupervised deep learning network for estimation of fatty acid composition‐network (FAC‐Net) is proposed to estimate the number of double bonds and number of methylene‐interrupted double bonds from multi‐echo bipolar gradient‐echo data, which are subsequently converted to saturated, mono‐unsaturated, and poly‐unsaturated fatty acids. The loss function was based on a 10 fat peak signal model. The proposed network was tested with a phantom containing eight oils with different FAC and on post‐menopausal women scanned using a whole‐body 3T MRI system between February 2022 and January 2024. The post‐menopausal women included a control group ( n = 8) with average risk for breast cancer and a cancer group ( n = 7) with biopsy‐proven breast cancer.
Results
The FAC values of eight oils in the phantom showed strong correlations between the measured and reference values (R 2 > 0.9 except chain length). The FAC values measured from scan and rescan data of the control group showed no significant difference between the two scans. The FAC measurements of the cancer group conducted before contrast and after contrast showed a significant difference in saturated fatty acid and mono‐unsaturated fatty acid. The cancer group has higher saturated fatty acid than the control group, although not statistically significant.
Conclusion
The results in this study suggest that the proposed FAC‐Net can be used to measure the FAC of mammary adipose tissue from gradient‐echo MRI data of the breast.
Subjects
MeSH terms (MEDLINE)
Author keywords
Substances
Authors and institutions
- Department of Radiology, Weill Cornell Medical College, New York, New York, USA.
- MR Application Predevelopment, Siemens Healthineers AG, Forchheim, Germany.
- Department of Radiology, New York University School of Medicine, New York, New York, USA.
ORCID profiles: Suneeta Chaudhary, Sungheon Gene Kim
Funding
- NCI NIH HHS
- National Cancer Institute
Cite
APA
Chaudhary, S., Lane, E. G., Levy, A., McGrath, A., Mema, E., Reichmann, M., Dodelzon, K., Simon, K., Chang, E., Nickel, M. D., Moy, L., Drotman, M., & Kim, S. G. (2025). Estimation of fatty acid composition in mammary adipose tissue using deep neural network with unsupervised training. Magnetic Resonance in Medicine. https://doi.org/10.1002/mrm.30401
Vancouver
Chaudhary S, Lane EG, Levy A, McGrath A, Mema E, Reichmann M, et al. Estimation of fatty acid composition in mammary adipose tissue using deep neural network with unsupervised training. Magnetic Resonance in Medicine. 2025. doi:10.1002/mrm.30401
BibTeX
@article{Chaudhary2025,
author = {Chaudhary, Suneeta and Lane, Elizabeth G and Levy, Allison and McGrath, Anika and Mema, Eralda and Reichmann, Melissa and Dodelzon, Katerina and Simon, Katherine and Chang, Eileen and Nickel, Marcel Dominik and Moy, Linda and Drotman, Michele and Kim, Sungheon Gene},
title = {Estimation of fatty acid composition in mammary adipose tissue using deep neural network with unsupervised training},
journal = {Magnetic Resonance in Medicine},
year = {2025},
doi = {10.1002/mrm.30401}
}
EUVIMED