GPU-Based Fast Iterative Reconstruction of Fully 3-D PET Sinograms

Reconstruction of multi-animal PET acquisitions with anisotropically variant PSF

Among other factors such as random, attenuation and scatter corrections, uniform spatial resolution is key to performing accurate quantitative studies in Positron emission tomography (PET). Particularly in preclinical PET studies involving simultaneous acquisition of multiple animals, the degradation of image resolution due to the depth of interaction (DOI) effect far from the center of the Field of View (FOV) becomes a significant concern. In this work, we incorporated a spatially-variant resolution model into a real time iterative reconstruction code to obtain accurate images of multi-animal acquisition. We estimated the spatially variant point spread function (SV-PSF) across the FOV using measurements and Monte Carlo (MC) simulations. The SV-PSF obtained was implemented in a GPU-based Ordered subset expectation maximization (OSEM) reconstruction code, which includes scatter, attenuation and random corrections. The method was evaluated with acquisitions from two preclinical PET/CT scanners of the SEDECAL Argus family: a Derenzo phantom placed 2 cm off center in the 4R-SuperArgus, and a multi-animal study with 4 mice in the 6R-SuperArgus. The SV-PSF reconstructions showed uniform spatial resolution without significant increase in reconstruction time, with superior image quality compared to the uniform PSF model.

Simultaneous quantitative imaging of two PET radiotracers via the detection of positron-electron annihilation and prompt gamma emissions

In conventional positron emission tomography (PET), only one radiotracer can be imaged at a time, because all PET isotopes produce the same two 511 keV annihilation photons. Here we describe an image reconstruction method for the simultaneous in vivo imaging of two PET tracers and thereby the independent quantification of two molecular signals. This method of multiplexed PET imaging leverages the 350-700 keV range to maximize the capture of 511 keV annihilation photons and prompt γ-ray emission in the same energy window, hence eliminating the need for energy discrimination during reconstruction or for signal separation beforehand. We used multiplexed PET to track, in mice with subcutaneous tumours, the biodistributions of intravenously injected [124I]I-trametinib and 2-deoxy-2-[18F]fluoro-D-glucose, [124I]I-trametinib and its nanoparticle carrier [89Zr]Zr-ferumoxytol, and the prostate-specific membrane antigen (PSMA) and infused PSMA-targeted chimaeric antigen receptor T cells after the systemic administration of [68Ga]Ga-PSMA-11 and [124I]I. Multiplexed PET provides more information depth, gives new uses to prompt γ-ray-emitting isotopes, reduces radiation burden by omitting the need for an additional computed-tomography scan and can be implemented on preclinical and clinical systems without any modifications in hardware or image acquisition software.

Hardware Architectures for Real-Time Medical Imaging

Medical imaging is considered one of the most important advances in the history of medicine and has become an essential part of the diagnosis and treatment of patients. Earlier prediction and treatment have been driving the acquisition of higher image resolutions as well as the fusion of different modalities, raising the need for sophisticated hardware and software systems for medical image registration, storage, analysis, and processing. In this scenario and given the new clinical pipelines and the huge clinical burden of hospitals, these systems are often required to provide both highly accurate and real-time processing of large amounts of imaging data. Additionally, lowering the prices of each part of imaging equipment, as well as its development and implementation, and increasing their lifespan is crucial to minimize the cost and lead to more accessible healthcare. This paper focuses on the evolution and the application of different hardware architectures (namely, CPU, GPU, DSP, FPGA, and ASIC) in medical imaging through various specific examples and discussing different options depending on the specific application. The main purpose is to provide a general introduction to hardware acceleration techniques for medical imaging researchers and developers who need to accelerate their implementations.

Deep-Learning Based Positron Range Correction of PET Images

Positron emission tomography (PET) is a molecular imaging technique that provides a 3D image of functional processes in the body in vivo. Some of the radionuclides proposed for PET imaging emit high-energy positrons, which travel some distance before they annihilate (positron range), creating significant blurring in the reconstructed images. Their large positron range compromises the achievable spatial resolution of the system, which is more significant when using high-resolution scanners designed for the imaging of small animals. In this work, we trained a deep neural network named Deep-PRC to correct PET images for positron range effects. Deep-PRC was trained with modeled cases using a realistic Monte Carlo simulation tool that considers the positron energy distribution and the materials and tissues it propagates into. Quantification of the reconstructed PET images corrected with Deep-PRC showed that it was able to restore the images by up to 95% without any significant noise increase. The proposed method, which is accessible via Github, can provide an accurate positron range correction in a few seconds for a typical PET acquisition.

Deep-Learning Based Positron Range Correction of PET Images

Positron emission tomography (PET) is a molecular imaging technique that provides a 3D image of functional processes in the body in vivo. Some of the radionuclides proposed for PET imaging emit high-energy positrons, which travel some distance before they annihilate (positron range), creating significant blurring in the reconstructed images. Their large positron range compromises the achievable spatial resolution of the system, which is more significant when using high-resolution scanners designed for the imaging of small animals. In this work, we trained a deep neural network named Deep-PRC to correct PET images for positron range effects. Deep-PRC was trained with modeled cases using a realistic Monte Carlo simulation tool that considers the positron energy distribution and the materials and tissues it propagates into. Quantification of the reconstructed PET images corrected with Deep-PRC showed that it was able to restore the images by up to 95% without any significant noise increase. The proposed method, which is accessible via Github, can provide an accurate positron range correction in a few seconds for a typical PET acquisition.

Ultrafast Ultrasound Imaging for Super-Resolution Preclinical Cardiac PET

PURPOSE

Physiological motion and partial volume effect (PVE) significantly degrade the quality of cardiac positron emission tomography (PET) images in the fast-beating hearts of rodents. Several Super-resolution (SR) techniques using a priori anatomical information have been proposed to correct motion and PVE in PET images. Ultrasound is ideally suited to capture real-time high-resolution cine images of rodent hearts. Here, we evaluated an ultrasound-based SR method using simultaneously acquired and co-registered PET-CT-Ultrafast Ultrasound Imaging (UUI) of the beating heart in closed-chest rodents.

PROCEDURES

The method was tested with numerical and animal data (n = 2) acquired with the non-invasive hybrid imaging system PETRUS that acquires simultaneously PET, CT, and UUI.

RESULTS

We showed that ultrasound-based SR drastically enhances the quality of PET images of the beating rodent heart. For the simulations, the deviations between expected and mean reconstructed values were 2 % after applying SR. For the experimental data, when using Ultrasound-based SR correction, contrast was improved by a factor of two, signal-to-noise ratio by 11 %, and spatial resolution by 56 % (~ 0.88 mm) with respect to static PET. As a consequence, the metabolic defect following an acute cardiac ischemia was delineated with much higher anatomical precision.

CONCLUSIONS

Our results provided a proof-of-concept that image quality of cardiac PET in fast-beating rodent hearts can be significantly improved by ultrasound-based SR, a portable low-cost technique. Improved PET imaging of the rodent heart may allow new explorations of physiological and pathological situations related with cardiac metabolism.

Ultrafast Ultrasound Imaging for Super-Resolution Preclinical Cardiac PET

Purpose

Physiological motion and partial volume effect (PVE) significantly degrade the quality of cardiac positron emission tomography (PET) images in the fast-beating hearts of rodents. Several Super-resolution (SR) techniques using a priori anatomical information have been proposed to correct motion and PVE in PET images. Ultrasound is ideally suited to capture real-time high-resolution cine images of rodent hearts. Here, we evaluated an ultrasound-based SR method using simultaneously acquired and co-registered PET-CT-Ultrafast Ultrasound Imaging (UUI) of the beating heart in closed-chest rodents.

Procedures

The method was tested with numerical and animal data (n = 2) acquired with the non-invasive hybrid imaging system PETRUS that acquires simultaneously PET, CT, and UUI.

Results

We showed that ultrasound-based SR drastically enhances the quality of PET images of the beating rodent heart. For the simulations, the deviations between expected and mean reconstructed values were 2 % after applying SR. For the experimental data, when using Ultrasound-based SR correction, contrast was improved by a factor of two, signal-to-noise ratio by 11 %, and spatial resolution by 56 % (~ 0.88 mm) with respect to static PET. As a consequence, the metabolic defect following an acute cardiac ischemia was delineated with much higher anatomical precision.

Conclusions

Our results provided a proof-of-concept that image quality of cardiac PET in fast-beating rodent hearts can be significantly improved by ultrasound-based SR, a portable low-cost technique. Improved PET imaging of the rodent heart may allow new explorations of physiological and pathological situations related with cardiac metabolism.

Comparison of GPU reconstruction based on different symmetries for dual-head PET

Purpose

Dual‐head positron emission tomography (PET) scanners have increasingly attracted the attention of many researchers. However, with the compact geometry, the depth‐of‐interaction blurring will reduce the image resolution considerably. Monte Carlo (MC)‐based system response matrix (SRM) is able to describe the physical process of PET imaging accurately and improve reconstruction quality significantly. The MC‐based SRM is large and precomputed, which leads to a longer image reconstruction time with indexing and retrieving precomputed system matrix elements. In this study, we proposed a GPU acceleration algorithm to accelerate the iterative reconstruction.

Methods

It has been demonstrated that the line‐of‐response (LOR)‐based symmetry and the Graphics Processing Unit (GPU) technology can accelerate the reconstruction tremendously. LOR‐based symmetry is suitable for the forward projection calculation, but not for the backprojection. In this study, we proposed a GPU acceleration algorithm that combined the LOR‐based symmetry and voxel‐based symmetry together, in which the LOR‐based symmetry is responsible for the forward projection, and the voxel‐based symmetry is used for the backprojection.

Results

Simulation and real experiments verify the efficiency of the algorithm. Compared with the CPU‐based calculation, the acceleration ratios of the forward projection and the backprojection operation are 130 and 110, respectively. The total acceleration ratio is 113×. In order to compare the acceleration effect of the different symmetries, we realized the reconstruction with the voxel‐based symmetry and the LOR‐based symmetry strategies. Compared with the LOR‐based GPU reconstruction, the acceleration ratio is 3.5×. Compared with the voxel‐based GPU reconstruction, the acceleration ratio is 12×.

Conclusion

We have proposed a new acceleration algorithm for the dual‐head PET system, in which both the forward and backprojection operations are accelerated by GPU.

A review of GPU-based medical image reconstruction

Tomographic image reconstruction is a computationally demanding task, even more so when advanced models are used to describe a more complete and accurate picture of the image formation process. Such advanced modeling and reconstruction algorithms can lead to better images, often with less dose, but at the price of long calculation times that are hardly compatible with clinical workflows. Fortunately, reconstruction tasks can often be executed advantageously on Graphics Processing Units (GPUs), which are exploited as massively parallel computational engines. This review paper focuses on recent developments made in GPU-based medical image reconstruction, from a CT, PET, SPECT, MRI and US perspective. Strategies and approaches to get the most out of GPUs in image reconstruction are presented as well as innovative applications arising from an increased computing capacity. The future of GPU-based image reconstruction is also envisioned, based on current trends in high-performance computing.

Fast Patch-Based Pseudo-CT Synthesis from T1-Weighted MR Images for PET/MR Attenuation Correction in Brain Studies

Attenuation correction in hybrid PET/MR scanners is still a challenging task. This paper describes a methodology for synthesizing a pseudo-CT volume from a single T1-weighted volume, thus allowing us to create accurate attenuation correction maps.

METHODS

We propose a fast pseudo-CT volume generation from a patient-specific MR T1-weighted image using a groupwise patch-based approach and an MRI-CT atlas dictionary. For every voxel in the input MR image, we compute the similarity of the patch containing that voxel to the patches of all MR images in the database that lie in a certain anatomic neighborhood. The pseudo-CT volume is obtained as a local weighted linear combination of the CT values of the corresponding patches. The algorithm was implemented in a graphical processing unit (GPU).

RESULTS

We evaluated our method both qualitatively and quantitatively for PET/MR correction. The approach performed successfully in all cases considered. We compared the SUVs of the PET image obtained after attenuation correction using the patient-specific CT volume and using the corresponding computed pseudo-CT volume. The patient-specific correlation between SUV obtained with both methods was high (R(2) = 0.9980, P < 0.0001), and the Bland-Altman test showed that the average of the differences was low (0.0006 ± 0.0594). A region-of-interest analysis was also performed. The correlation between SUVmean and SUVmax for every region was high (R(2) = 0.9989, P < 0.0001, and R(2) = 0.9904, P < 0.0001, respectively).

CONCLUSION

The results indicate that our method can accurately approximate the patient-specific CT volume and serves as a potential solution for accurate attenuation correction in hybrid PET/MR systems. The quality of the corrected PET scan using our pseudo-CT volume is comparable to having acquired a patient-specific CT scan, thus improving the results obtained with the ultrashort-echo-time-based attenuation correction maps currently used in the scanner. The GPU implementation substantially decreases computational time, making the approach suitable for real applications.

Medical image processing on the GPU - past, present and future

Graphics processing units (GPUs) are used today in a wide range of applications, mainly because they can dramatically accelerate parallel computing, are affordable and energy efficient. In the field of medical imaging, GPUs are in some cases crucial for enabling practical use of computationally demanding algorithms. This review presents the past and present work on GPU accelerated medical image processing, and is meant to serve as an overview and introduction to existing GPU implementations. The review covers GPU acceleration of basic image processing operations (filtering, interpolation, histogram estimation and distance transforms), the most commonly used algorithms in medical imaging (image registration, image segmentation and image denoising) and algorithms that are specific to individual modalities (CT, PET, SPECT, MRI, fMRI, DTI, ultrasound, optical imaging and microscopy). The review ends by highlighting some future possibilities and challenges.

Distributed MLEM: an iterative tomographic image reconstruction algorithm for distributed memory architectures

The processing speed for positron emission tomography (PET) image reconstruction has been greatly improved in recent years by simply dividing the workload to multiple processors of a graphics processing unit (GPU). However, if this strategy is generalized to a multi-GPU cluster, the processing speed does not improve linearly with the number of GPUs. This is because large data transfer is required between the GPUs after each iteration, effectively reducing the parallelism. This paper proposes a novel approach to reformulate the maximum likelihood expectation maximization (MLEM) algorithm so that it can scale up to many GPU nodes with less frequent inter-node communication. While being mathematically different, the new algorithm maximizes the same convex likelihood function as MLEM, thus converges to the same solution. Experiments on a multi-GPU cluster demonstrate the effectiveness of the proposed approach.

High Performance 3D PET Reconstruction Using Spherical Basis Functions on a Polar Grid

Statistical iterative methods are a widely used method of image reconstruction in emission tomography. Traditionally, the image space is modelled as a combination of cubic voxels as a matter of simplicity. After reconstruction, images are routinely filtered to reduce statistical noise at the cost of spatial resolution degradation. An alternative to produce lower noise during reconstruction is to model the image space with spherical basis functions. These basis functions overlap in space producing a significantly large number of non-zero elements in the system response matrix (SRM) to store, which additionally leads to long reconstruction times. These two problems are partly overcome by exploiting spherical symmetries, although computation time is still slower compared to non-overlapping basis functions. In this work, we have implemented the reconstruction algorithm using Graphical Processing Unit (GPU) technology for speed and a precomputed Monte-Carlo-calculated SRM for accuracy. The reconstruction time achieved using spherical basis functions on a GPU was 4.3 times faster than the Central Processing Unit (CPU) and 2.5 times faster than a CPU-multi-core parallel implementation using eight cores. Overwriting hazards are minimized by combining a random line of response ordering and constrained atomic writing. Small differences in image quality were observed between implementations.