Feasibility of direct brain 18F-fluorodeoxyglucose-positron emission tomography attenuation and high-resolution correction methods using deep learning.

Abstract

Objectives: To develop the following three attenuation correction (AC) methods for brain ¹⁸F-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 53 patients who underwent cranial magnetic resonance imaging (MRI) and computed tomography (CT) and 27 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 0.281×10^-3, 4.62×10^-3, and 12.7×10^-3, respectively. Moreover, the SSIM of the direct+HRC method was 0.975.

Conclusion: The direct+HRC method enables accurate attenuation without CT exposure and high-resolution correction without dedicated correction programs.