Simultaneous Attenuation Correction and Reconstruction of PET Images Using Deep Convolutional Encoder Decoder Networks from Emission Data

Aim: Quantitative positron emission tomography (PET) image reconstruction is challenging due to the attenuation correction needed during the reconstruction process. In this study, we propose and investigate methods that perform attenuation correction and reconstruction of PET images via deep convolutional encoder-decoder networks, without using anatomical information for attenuation correction.

Methods: Brain PET images from 120 patients were included in our study. Patient data were divided into training, test, and external validation sets with 80, 20 and 20 patients, respectively. We proposed and investigated 3 main methods. First, we directly mapped the non-attenuation-corrected sinogram to original reconstructed image. The second method consisted of two convolutional encoder and decoder networks where the first part tries to reconstruct non-attention-corrected images and the second network tries to perform attenuation correction of the generated image in the image space. Third method’s architecture consists of two convolutional encoder and decoder networks for end-to-end learning: the first part tries to correct attenuation in sinogram space from non-attenuated corrected sinogram passed as input through the encoder, and the decoder tries to reconstruct the attenuation-corrected sinogram. This latter second part mapped the sinogram to the pixel-wise continuously-valued measured attenuation-corrected PET images as obtained from reference CT images. Quality of the synthesized images were quantitatively assessed by mean squared error (MSE), peak signal-to-noise ratio (PSNR), and structural Similarity index metrics (SSIM). Image quantification was assessed using SUV bias map and joint histogram of pixel-wise SUV correlation between generated images and reference (attenuated corrected by CT, and reconstruction with iterative reconstruction).

Results: With respect to reference PET images, MSE, PSNR and SSIM values were 0.0023±0.0011, 26.85±2.44, 0.85±0.09 and 0.0029±0.0011, 25.66±2.07, 0.82±0.01 and 0.0020±0.0013, 28.45±1.03 ,0.87±0.01 for the first, second and third methods, respectively. Relative error (%) of SUV was -34.12±6.01, 36.12±7.03 and 18.12±8.12 for the first, second and third method respectively. Pixel wise SUV correlation (Pearson correlation, R²) between generated images and reference was 0.71± 0.01, 0.69± 0.05 and 0.81± 0.09 for the first, second and third method, respectively.

Conclusions: In this present study, we developed new approaches to attenuation correction and reconstruction of PET images from emission data without using anatomical information for attenuation correction. The highest performance was obtained by the deep neural network architecture that consisted of two convolutional encoder and decoder networks where first part performed attenuation correction in sinogram space and the second network reconstructed the image. The present study showed that attenuation correction and reconstruction of PET images using deep convolutional encoder-decoder networks from emission data is a promising technique for PET images.

• Download figure
• Open in new tab
• Download powerpoint