3D T2-Weighted Rectal Cancer Imaging using a 3D Fast Spin Echo Sequence with Deep Learning Reconstruction
Sarah Palmquist1, Usama Salem1, Nir Stanietzky1, Jia Sun2, Xinzeng Wang3, Ersin Bayram3, Ken-Pin Hwang4, Jong Bum Son4, Peng Wei2, Randy Ernst1, Harmeet Kaur1, and Jingfei Ma4
1Abdominal Imaging, M.D. Anderson Cancer Center, Houston, TX, United States, 2Biostatistics, M.D. Anderson Cancer Center, Houston, TX, United States, 3GE Healthcare, Houston, TX, United States, 4Imaging Physics, M.D. Anderson Cancer Center, Houston, TX, United States
Multiplanar high resolution T2-weighted (T2W) imaging with a 2D fast spin echo (FSE) sequence is currently an essential component of rectal cancer MRI. In this work, we performed T2W imaging of rectal cancer with a 3D FSE sequence and evaluated the quality and potential clinical value of the images after applying a postprocessing deep learning reconstruction (DLR) algorithm. We found that DLR images are non-inferior to conventional images and there are fair-moderate inter-reader agreements in a large majority of the categories evaluated for image quality and clinical usefulness.
This abstract and the presentation materials are available to members only;
a login is required.