Estimation of fatty acid composition in mammary adipose tissue using deep neural network with unsupervised training

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 (R² > 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.