Abstract #2195

Ablation Studies in 3D Encoder-Decoder Networks for Brain MRI-to-PET Cerebral Blood Flow Transformation

Ramy Hussein¹, Moss Zhao¹, Jia Guo², Kevin Chen¹, David Shin³, Michael Moseley¹, and Greg Zaharchuk¹

¹Radiology, Stanford University, Stanford, CA, United States, ²Bioengineering, University of California, Riverside, Riverside, CA, United States, ³Neuro MR, GE Healthcare, Menlo Park, CA, United States

In this study, we demonstrate that an optimized 3D encoder-decoder structured convolutional neural network with attention gates can effectively integrate brain structural MRI and ASL perfusion images to produce high-quality synthetic PET CBF maps without using radiotracers. We performed experiments to evaluate different loss functions and the role of the attention mechanism. Our results showed that attention-based 3D encoder-decoder network with custom loss function produces the superior PET CBF prediction results, achieving SSIM of 0.94, MSE of 0.00025, and PSNR of 38dB.

This abstract and the presentation materials are available to members only; a login is required.

Join Here