Tomohiro Ueda - Graduate School of Health Sciences, Kumamoto University, Japan
Kousuke Yamshita - Graduate School of Health Sciences, Kumamoto University, Japan
Retsu Kawazoe - Graduate School of Health Sciences, Kumamoto University, Japan
Yuta Sayawaki - Graduate School of Health Sciences, Kumamoto University, Japan
Yoshiki Morisawa - Graduate School of Health Sciences, Kumamoto University, Japan
Ryosuke Kamezaki - ۲Kumamoto University Hospital, Japan
Ryuji Ikeda - Department of Central Radiology Kumamoto University Hospital, Japan
Shinya Shiraishi - Department of Diagnostic Radiology, Faculty of Life Sciences,Kumamoto University, Japan
Yoshikazu Uchiyama - Department of Information and Communication Technology, Faculty of Engineering, University of Miyazaki, Japan
Shigeki Ito - Department of Medical Radiation Sciences, Faculty of Life Sciences, Kumamoto University, Japan

Objective(s): To develop the following three attenuation correction (AC) methods for brain ۱۸F-fluorodeoxyglucose-positron emission tomography (PET), using deep learning, and to ascertain their precision levels: (i) indirect method; (ii) direct method; and (iii) direct and high-resolution correction (direct+HRC) method.Methods: We included ۵۳ patients who underwent cranial magnetic resonance imaging (MRI) and computed tomography (CT) and ۲۷ patients who underwent cranial MRI, CT, and PET. After fusion of the magnetic resonance, CT, and PET images, resampling was performed to standardize the field of view and matrix size and prepare the data set. In the indirect method, synthetic CT (SCT) images were generated, whereas in the direct and direct+HRC methods, a U-net structure was used to generate AC images. In the indirect method, attenuation correction was performed using SCT images generated from MRI findings using U-net instead of CT images. In the direct and direct+HRC methods, AC images were generated directly from non-AC images using U-net, followed by image evaluation. The precision levels of AC images generated using the indirect and direct methods were compared based on the normalized mean squared error (NMSE) and structural similarity (SSIM).Results: Visual inspection revealed no difference between the AC images prepared using CT-based attenuation correction and those prepared using the three methods. The NMSE increased in the order indirect, direct, and direct+HRC methods, with values of ۰.۲۸۱×۱۰-۳, ۴.۶۲×۱۰-۳, and ۱۲.۷×۱۰-۳, respectively. Moreover, the SSIM of the direct+HRC method was ۰.۹۷۵.Conclusion: The direct+HRC method enables accurate attenuation without CT exposure and high-resolution correction without dedicated correction programs.

Brain PET, Attenuation Correction, high-resolution correction, DCNN