Hideaki Kutsuna1, Hideki Ota2,3, Yoshimori Kassai4, Hidenori Takeshima5, Tatsuo Nagasaka6, Takashi Nishina7, Yoshiaki Morita3, and Kei Takase3,8
1MRI Systems Development Department, Canon Medical Systems Corporation, Kanagawa, Japan, 2Department of Advanced MRI Collaboration Research, Tohoku University Graduate School of Medicine, Miyagi, Japan, 3Department of Diagnostic Radiology, Tohoku University Hospital, Miyagi, Japan, 4CT-MR Solution Planning Department, Canon Medical Systems Corporation, Tochigi, Japan, 5Advanced Technology Research Department, Research and Development Center, Canon Medical Systems Corporation, Kanagawa, Japan, 6Department of Radiological Technology, Tohoku University Hospital, Miyagi, Japan, 7MRI Sales Department, Canon Medical Systems Corporation, Miyagi, Japan, 8Department of Diagnostic Radiology, Tohoku University Graduate School of Medicine, Miyagi, Japan
The purpose is to provide improved time
intensity curves (TICs) of dynamic contrast enhanced MRI. In this work, a
method based on convolutional neural network (CNN) was compared with a
conventional method based on compressed sensing (CS). While both of the methods
used radial sampling for free-breathing acquisitions, reconstruction strategies
were different.
The experimental results showed that, in
comparison with the images reconstructed with CS, the images reconstructed with
CNN exhibited higher temporal resolution in the TICs without losing spatial
detail.
