Abstract #5661

Direct Pseudo-CT Image Synthesis Using Deep Learning for Pelvis PET/MR Attenuation Correction

Andrew Palmera Leynes¹, Jaewon Yang², Dattesh D Shanbhag³, Sandeep S Kaushik³, Florian Wiesinger⁴, Youngho Seo², Thomas Armstrong Hope², and Peder Larson¹

¹Radiology and Biomedical Imaging, University of California San Francisco, San Francisco, CA, United States, ²University of California San Francisco, San Francisco, CA, United States, ³GE Global Research, Bangalore, India, ⁴GE Global Research, Munich, Germany

A deep learning model with fully-convolutional networks was used to directly synthesize pseudo-CT images from MR images. The pseudo-CT images were used for MR-based attenuation correction (MRAC) of PET reconstruction in PET/MRI. The effects of the MRAC on high-uptake volumes are evaluated quantitatively. We demonstrate that the deep learning-based MRAC significantly improves PET uptake quantification.

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

Join Here