Search

Purpose: Deep learning is an emerging reconstruction method for positron emission tomography (PET), which can tackle complex PET corrections in an integrated procedure. This paper optimizes the direct PET reconstruction from sinogram on a long axial field of view (LAFOV) PET. Methods: This paper proposes a novel deep learning architecture to reduce the biases during direct reconstruction from sinograms to images. This architecture is based on an encoder-decoder network, where the perceptual loss is used with pre-trained convolutional layers. It is trained and tested on data of 80 patients acquired from recent Siemens Biograph Vision Quadra long axial FOV (LAFOV) PET/CT. The patients are randomly split into a training dataset of 60 patients, a validation dataset of 10 patients, and a test dataset of 10 patients. The 3D sinograms are converted into 2D sinogram slices and used as input to the network. In addition, the vendor reconstructed images are considered as ground truths. Finally, the proposed method is compared with DeepPET, a benchmark deep learning method for PET reconstruction. Results: Compared with DeepPET, the proposed network significantly reduces the root-mean-squared error (NRMSE) from 0.63 to 0.6 (p < 0.01) and increases the structural similarity index (SSIM) and peak signal-to-noise ratio (PSNR) from 0.93 to 0.95 (p < 0.01) and from 82.02 to 82.36 (p < 0.01), respectively. The reconstruction time is approximately 10 s per patient, which is shortened by 23 times compared with the conventional method. The errors of mean standardized uptake values (SUVmean) for lesions between ground truth and the predicted result are reduced from 33.5 to 18.7% (p = 0.03). In addition, the error of max SUV is reduced from 32.7 to 21.8% (p = 0.02). Conclusion: The results demonstrate the feasibility of using deep learning to reconstruct images with acceptable image quality and short reconstruction time. It is shown that the proposed method can improve the quality of deep learning-based reconstructed images without additional CT images for attenuation and scattering corrections. This study demonstrated the feasibility of deep learning to rapidly reconstruct images without additional CT images for complex corrections from actual clinical measurements on LAFOV PET. Despite improving the current development, AI-based reconstruction does not work appropriately for untrained scenarios due to limited extrapolation capability and cannot completely replace conventional reconstruction currently. [ABSTRACT FROM AUTHOR]

We propose a novel method to analyze a set of poses of 3D models that are represented with triangle meshes and unregistered. Different shapes of poses are transformed from the 3D spatial domain to a geometry spectrum domain that is defined by Laplace-Beltrami operator. During this space-spectrum transform, all near-isometric deformations, mesh triangulations and Euclidean transformations are filtered away. The different spatial poses from a 3D model are represented with near-isometric deformations; therefore, they have similar behaviors in the spectral domain. Semantic parts of that model are then determined based on the computed geometric properties of all the mapped vertices in the geometry spectrum domain. Semantic skeleton can be automatically built with joints detected as well. The Laplace-Beltrami operator is proved to be invariant to isometric deformations and Euclidean transformations such as translation and rotation. It also can be invariant to scaling with normalization. The discrete implementation also makes the Laplace-Beltrami operator straightforward to be applied on triangle meshes despite triangulations. Our method turns a rather difficult spatial problem into a spectral problem that is much easier to solve. The applications show that our 3D pose analysis method leads to a registration-free pose analysis and a high-level semantic part understanding of 3D shapes. [ABSTRACT FROM AUTHOR]

Purpose: To obtain the optimal simultaneous-multislice (SMS)—accelerated diffusion-weighted imaging (DWI) of the liver at 3.0 T MRI by systematically estimating the repeatability of apparent diffusion coefficient (ADC), signal-to-noise ratio (SNR) and image quality of different breathing schemes in comparison to standard DWI (STD) and other SMS sequences. Methods: In this institutional review board-approved prospective study, hepatic DWIs (b = 50, 300, 600 s/mm2) were performed in 23 volunteers on 3.0 T MRI using SMS and STD with breath-hold (BH-SMS, BH-STD), free-breathing (FB-SMS, FB-STD) and respiratory-triggered (RT-SMS, RT-STD). Reduction of scan time with SMS-acceleration was calculated. ADC and SNR were measured in nine anatomic locations and image quality was assessed on all SMS and STD sequences. An optimal SMS-DWI was decided by systematically comparing the ADC repeatability, SNR and image quality among above DWIs. Results: SMS-DWI reduced scan time significantly by comparison with corresponding STD-DWI (27 vs. 42 s for BH, 54 vs. 78 s for FB and 42 vs. 97 s for RT). In all DWIs, BH-SMS had the greatest intraobserver agreement (intraclass correlation coefficient (ICC): 0.920–0.944) and good interobserver agreement (ICC: 0.831–0.886) for ADC measurements, and had the best ADC repeatability (mean ADC absolute differences: 0.046–0.058 × 10−3mm2/s, limits of agreement (LOA): 0.010–0.013 × 10−3mm2/s) in nine locations. BH-SMS had the highest SNR in three representative sections except for RT-STD. There were no significant differences in image quality between BH-SMS and other DWI sequences (median BH-SMS: 4.75, other DWI: 4.5–5.0; P > 0.0.5). Conclusion: BH-SMS provides considerable scan time reduction with good image quality, sufficient SNR and highest ADC repeatability on 3.0 T MRI, which is thus recommended as the optimal hepatic DWI sequence for those subjects with adequate breath-holding capability. [ABSTRACT FROM AUTHOR]

Aerosol-cloud-radiation interactions represent one of the largest uncertainties in the current climate assessment. Much of the complexity arises from the non-monotonic responses of clouds, precipitation and radiative fluxes to aerosol perturbations under various meteorological conditions. In this study, an aerosol-aware WRF model is used to investigate the microphysical and radiative effects of aerosols in three weather systems during the March 2000 Cloud Intensive Observational Period campaign at the US Southern Great Plains. Three simulated cloud ensembles include a low-pressure deep convective cloud system, a collection of less-precipitating stratus and shallow cumulus, and a cold frontal passage. The WRF simulations are evaluated by several ground-based measurements. The microphysical properties of cloud hydrometeors, such as their mass and number concentrations, generally show monotonic trends as a function of cloud condensation nuclei concentrations. Aerosol radiative effects do not influence the trends of cloud microphysics, except for the stratus and shallow cumulus cases where aerosol semi-direct effects are identified. The precipitation changes by aerosols vary with the cloud types and their evolving stages, with a prominent aerosol invigoration effect and associated enhanced precipitation from the convective sources. The simulated aerosol direct effect suppresses precipitation in all three cases but does not overturn the aerosol indirect effect. Cloud fraction exhibits much smaller sensitivity (typically less than 2%) to aerosol perturbations, and the responses vary with aerosol concentrations and cloud regimes. The surface shortwave radiation shows a monotonic decrease by increasing aerosols, while the magnitude of the decrease depends on the cloud type. [ABSTRACT FROM AUTHOR]