Attenuation correction using deep Learning and integrated UTE/multi-echo Dixon sequence: evaluation in amyloid and tau PET imaging

Abstract

Purpose: PET measures of amyloid and tau pathologies are powerful biomarkers for the diagnosis and monitoring of Alzheimer’s disease (AD). Because cortical regions are close to bone, quantitation accuracy of amyloid and tau PET imaging can be significantly influenced by errors of attenuation correction (AC). This work presents an MR-based AC method that combines deep learning with a novel ultrashort time-to-echo (UTE)/Multi-Echo Dixon (mUTE) sequence for amyloid and tau imaging. Methods: Thirty-five subjects that underwent both 11C-PiB and 18F-MK6240 scans were included in this study. The proposed method was compared with Dixon-based atlas method as well as other magnetization-prepared rapid acquisition with gradient echo (MPRAGE)- or Dixon- based deep learning methods. The Dice coefficient and validation loss of the generated pseudo-CT images were used for comparison. PET error images regarding standardized uptake value ratio (SUVR) were quantified through regional and surface analysis to evaluate the final AC accuracy. Results: The Dice coefficients of the deep learning methods based on MPRAGE, Dixon and mUTE images were 0.84 (0.91), 0.84 (0.92), and 0.87 (0.94) for the whole-brain (above-eye) bone regions, respectively, higher than the atlas method of 0.52 (0.64). The regional SUVR error for the atlas method was around 6%, higher than the regional SUV error. The regional SUV and SUVR errors for all deep learning methods were below 2%, with mUTE-based deep learning method performing the best. As for the surface analysis, the atlas method showed the largest error (> 10%) near vertices inside superior frontal, lateral occipital, superior parietal and inferior temporal cortices. The mUTE-based deep learning method resulted in the least number of regions with error higher than 1%, with the largest error (> 5%) showing up near the inferior temporal and medial orbitofrontal cortices. Conclusion: Deep learning with mUTE can generate accurate AC for amyloid and tau imaging in PET/MR.

Deep learning based synthetic‐CT generation in radiotherapy and PET: A review

“…Results showed that DL prediction reduced the root mean squared error (RMSE) in corrected PET SUV by a factor of 4 for bone lesions and 1.5 for soft tissue lesions. Following this first work, other authors showed the improvement of DL‐based AC over the traditional atlas‐based MRAC proposed by the vendors, 70,139–144 also comparing several network configurations 145,146 …”

“…GANs were the most popular architecture, but we cannot conclude that it is the best network scheme for sCT. Indeed, some studies compared U-net or other CNN vs GAN finding GAN performing statistically better 85,139 ; others found similar results 145,146 or even worse performances 76,144 . We can speculate that, as demonstrated by 113 , a vital role is played by the loss function, which, despite being the effective driver for network learning, has been investigated less than the network architecture, as highlighted for image restoration 190 Focusing on the body sites, we observed that most of the investigations were conducted in the brain, H&N and pelvic regions.…”

“…Results showed that DL prediction reduced the RMSE in corrected PET SUV by a factor of 4 for bone lesions and 1.5 for soft tissue lesions. Following this first work, other authors showed the improvement of DL-based AC over the traditional atlasbased MRAC proposed by the vendors 70,139,140,141,142,143,144 , also comparing several network configurations145,146 . Torrado et al142 pre-trained their U-net on 19 healthy brains acquired with T 1 GRE MRI and, subsequently, they trained the network using Dixon images of colorectal and prostate cancer patients.…”

Assessment of vertebral fractures and edema of the thoracolumbar spine based on water‐fat and susceptibility‐weighted images derived from a single ultra‐short echo time scan

“…23,24 Beyond that, the water-and fat-separated images were used to suppress long T 2 components which proves itself beneficial in pseudo-CT imaging or in the context of PET attenuation map generation. [22][23][24][25][26][27][28] However, also typical UTE-Dixon imaging requires the acquisition of multiple echoes which prolong the repetition time (TR) and conventional Dixon does not consider the short T * 2 decay of water signal. 29 Single-echo Dixon (sTE-Dixon) methods rely on a single complex TE image to decompose fat and water components directly from the complex MR signal.…”

The promise of artificial intelligence and deep learning in PET and SPECT imaging

“…Roccia et al used a DL algorithm to predict the arterial input function for quantification of the regional cerebral metabolic rate from dynamic 18 F-FDG PET scans [111]. Park et al developed an automated pipeline for glomerular filtration rate (GFR) quantification of 99m Tc-DTPA from SPECT/CT scans using a 3D U-Net model through kidney segmentation [112].…”