Shihan Qiu1,2, Yuhua Chen1,2, Sen Ma1, Zhaoyang Fan1,2, Anthony G. Christodoulou1,2, Yibin Xie1, and Debiao Li1,2
1Biomedical Imaging Research Institute, Cedars-Sinai Medical Center, Los Angeles, CA, United States, 2Department of Bioengineering, UCLA, Los Angeles, CA, United States
1Biomedical Imaging Research Institute, Cedars-Sinai Medical Center, Los Angeles, CA, United States, 2Department of Bioengineering, UCLA, Los Angeles, CA, United States
Combined training of two neural networks with additional cycle consistency loss allows bidirectional translation between contrast-weighted images and quantitative maps. It generates high-quality weighted images and quantitative maps simultaneously.
Figure 1. Network design. (a) The proposed combined training of two synthetic networks using cycle consistency loss. (b) Separate training of the networks without cycle consistency loss.
Figure 3. A sample case of synthetic quantitative maps from a patient with multiple sclerosis using CNN with or without cycle loss. (a) T1 map, (b) T2 map, (c) proton density map. The black arrows show a lesion.
