Direct Patlak Reconstruction From Dynamic PET Data Using the Kernel Method With MRI Information Based on Structural Similarity

Combining deep learning with a kinetic model to predict dynamic PET images and generate parametric images

BACKGROUND

Dynamic positron emission tomography (PET) images are useful in clinical practice because they can be used to calculate the metabolic parameters (Ki) of tissues using graphical methods (such as Patlak plots). Ki is more stable than the standard uptake value and has a good reference value for clinical diagnosis. However, the long scanning time required for obtaining dynamic PET images, usually an hour, makes this method less useful in some ways. There is a tradeoff between the scan durations and the signal-to-noise ratios (SNRs) of Ki images. The purpose of our study is to obtain approximately the same image as that produced by scanning for one hour in just half an hour, improving the SNRs of images obtained by scanning for 30 min and reducing the necessary 1-h scanning time for acquiring dynamic PET images.

METHODS

In this paper, we use U-Net as a feature extractor to obtain feature vectors with a priori knowledge about the image structure of interest and then utilize a parameter generator to obtain five parameters for a two-tissue, three-compartment model and generate a time activity curve (TAC), which will become close to the original 1-h TAC through training. The above-generated dynamic PET image finally obtains the Ki parameter image.

RESULTS

A quantitative analysis showed that the network-generated Ki parameter maps improved the structural similarity index measure and peak SNR by averages of 2.27% and 7.04%, respectively, and decreased the root mean square error (RMSE) by 16.3% compared to those generated with a scan time of 30 min.

CONCLUSIONS

The proposed method is feasible, and satisfactory PET quantification accuracy can be achieved using the proposed deep learning method. Further clinical validation is needed before implementing this approach in routine clinical applications.

SPECT reconstruction with a trained regularizer using CT-side information: Application to 177Lu SPECT imaging

Improving low-count SPECT can shorten scans and support pre-therapy theranostic imaging for dosimetry-based treatment planning, especially with radionuclides like 177Lu known for low photon yields. Conventional methods often underperform in low-count settings, highlighting the need for trained regularization in model-based image reconstruction. This paper introduces a trained regularizer for SPECT reconstruction that leverages segmentation based on CT imaging. The regularizer incorporates CT-side information via a segmentation mask from a pre-trained network (nnUNet). In this proof-of-concept study, we used patient studies with 177Lu DOTATATE to train and tested with phantom and patient datasets, simulating pre-therapy imaging conditions. Our results show that the proposed method outperforms both standard unregularized EM algorithms and conventional regularization with CT-side information. Specifically, our method achieved marked improvements in activity quantification, noise reduction, and root mean square error. The enhanced low-count SPECT approach has promising implications for theranostic imaging, post-therapy imaging, whole body SPECT, and reducing SPECT acquisition times.

Direct Patlak Reconstruction of [68Ga]Ga-PSMA PET for the Evaluation of Primary Prostate Cancer Prior Total Prostatectomy: Results of a Pilot Study

To investigate the use of kinetic parameters derived from direct Patlak reconstructions of [68Ga]Ga-PSMA-11 positron emission tomography/computed tomography (PET/CT) to predict the histological grade of malignancy of the primary tumor of patients with prostate cancer (PCa). Thirteen patients (mean age 66 ± 10 years) with a primary, therapy-naïve PCa (median PSA 9.3 [range: 6.3-130 µg/L]) prior radical prostatectomy, were recruited in this exploratory prospective study. A dynamic whole-body [68Ga]Ga-PSMA-11 PET/CT scan was performed for all patients. Measured quantification parameters included Patlak slope (Ki: absolute rate of tracer consumption) and Patlak intercept (Vb: degree of tracer perfusion in the tumor). Additionally, the mean and maximum standardized uptake values (SUVmean and SUVmax) of the tumor were determined from a static PET 60 min post tracer injection. In every patient, initial PSA (iPSA) values that were also the PSA level at the time of the examination and final histology results with Gleason score (GS) grading were correlated with the quantitative readouts. Collectively, 20 individual malignant prostate lesions were ascertained and histologically graded for GS with ISUP classification. Six lesions were classified as ISUP 5, two as ISUP 4, eight as ISUP 3, and four as ISUP 2. In both static and dynamic PET/CT imaging, the prostate lesions could be visually distinguished from the background. The average values of the SUVmean, slope, and intercept of the background were 2.4 (±0.4), 0.015 1/min (±0.006), and 52% (±12), respectively. These were significantly lower than the corresponding parameters extracted from the prostate lesions (all p < 0.01). No significant differences were found between these values and the various GS and ISUP (all p > 0.05). Spearman correlation coefficient analysis demonstrated a strong correlation between static and dynamic PET/CT parameters (all r ≥ 0.70, p < 0.01). Both GS and ISUP grading revealed only weak correlations with the mean and maximum SUV and tumor-to-background ratio derived from static images and dynamic Patlak slope. The iPSA demonstrated no significant correlation with GS and ISUP grading or with dynamic and static PET parameter values. In this cohort of mainly high-risk PCa, no significant correlation between [68Ga]Ga-PSMA-11 perfusion and consumption and the aggressiveness of the primary tumor was observed. This suggests that the association between SUV values and GS may be more distinctive when distinguishing clinically relevant from clinically non-relevant PCa.

Neural KEM: A Kernel Method With Deep Coefficient Prior for PET Image Reconstruction

Image reconstruction of low-count positron emission tomography (PET) data is challenging. Kernel methods address the challenge by incorporating image prior information in the forward model of iterative PET image reconstruction. The kernelized expectation-maximization (KEM) algorithm has been developed and demonstrated to be effective and easy to implement. A common approach for a further improvement of the kernel method would be adding an explicit regularization, which however leads to a complex optimization problem. In this paper, we propose an implicit regularization for the kernel method by using a deep coefficient prior, which represents the kernel coefficient image in the PET forward model using a convolutional neural-network. To solve the maximum-likelihood neural network-based reconstruction problem, we apply the principle of optimization transfer to derive a neural KEM algorithm. Each iteration of the algorithm consists of two separate steps: a KEM step for image update from the projection data and a deep-learning step in the image domain for updating the kernel coefficient image using the neural network. This optimization algorithm is guaranteed to monotonically increase the data likelihood. The results from computer simulations and real patient data have demonstrated that the neural KEM can outperform existing KEM and deep image prior methods.

A new approach to overcome the inconsistency between SPECT and the anatomical map in maximum A-posterior expectation-maximization reconstruction algorithm

Noise reduction while preserving spatial resolution is one of the most important challenges in the reconstructing of emission tomography images. One of the resolving methods is the Bowsher maximum a-posteriori expectation-maximization reconstruction (MAPEM) algorithm. This method considers a binary selection of the neighbors of each voxel based on the prior anatomical values to use in the regularization function. This method is particularly susceptible to imposing the wrong data into the reconstructed image due to the spatial or functional inconsistencies between the anatomical image and the actual activity distribution. Because of the poor spatial resolution of single-photon emission tomography (SPECT) images and the different nature of emission and anatomical imaging, there is not enough certainty of inconsistency with anatomical images. Therefore, we proposed a new weighted Bowsher method that can overcome this weakness while the image quality indexes, especially the spatial resolution, are almost preserved. In the proposed method, each of the neighbors of a specific voxel takes a constant weight depending on the order of its value and independent of its intensity quantity. The proposed method was evaluated using some different physical phantoms and a patient scan. The results show that the proposed method has superiority in the presence of inconsistency; moreover, the proposed method gives nearly similar results to the regular Bowsher MAPEM in case of consistency. In conclusion, we show that using a suitable constant weighting factor in Bowsher MAPEM, one can operatively reduce the image noise while preserving the image quality parameters where the emission tomography images are either consistent or inconsistent with the prior anatomical map.

Unsupervised PET logan parametric image estimation using conditional deep image prior

Recently, deep learning-based denoising methods have been gradually used for PET images denoising and have shown great achievements. Among these methods, one interesting framework is conditional deep image prior (CDIP) which is an unsupervised method that does not need prior training or a large number of training pairs. In this work, we combined CDIP with Logan parametric image estimation to generate high-quality parametric images. In our method, the kinetic model is the Logan reference tissue model that can avoid arterial sampling. The neural network was utilized to represent the images of Logan slope and intercept. The patient's computed tomography (CT) image or magnetic resonance (MR) image was used as the network input to provide anatomical information. The optimization function was constructed and solved by the alternating direction method of multipliers (ADMM) algorithm. Both simulation and clinical patient datasets demonstrated that the proposed method could generate parametric images with more detailed structures. Quantification results showed that the proposed method results had higher contrast-to-noise (CNR) improvement ratios (PET/CT datasets: 62.25%±29.93%; striatum of brain PET datasets : 129.51%±32.13%, thalamus of brain PET datasets: 128.24%±31.18%) than Gaussian filtered results (PET/CT datasets: 23.33%±18.63%; striatum of brain PET datasets: 74.71%±8.71%, thalamus of brain PET datasets: 73.02%±9.34%) and nonlocal mean (NLM) denoised results (PET/CT datasets: 37.55%±26.56%; striatum of brain PET datasets: 100.89%±16.13%, thalamus of brain PET datasets: 103.59%±16.37%).

Hybrid kernelised expectation maximisation for Bremsstrahlung SPECT reconstruction in SIRT with 90Y micro-spheres

Background

Selective internal radiation therapy with Yttrium-90 microspheres is an effective therapy for liver cancer and liver metastases. Yttrium-90 is mainly a high-energy beta particle emitter. These beta particles emit Bremsstrahlung radiation during their interaction with tissue making post-therapy imaging of the radioactivity distribution feasible. Nevertheless, image quality and quantification is difficult due to the continuous energy spectrum which makes resolution modelling, attenuation and scatter estimation challenging and therefore the dosimetry quantification is inaccurate. As a consequence a reconstruction algorithm able to improve resolution could be beneficial.

Methods

In this study, the hybrid kernelised expectation maximisation (HKEM) is used to improve resolution and contrast and reduce noise, in addition a modified HKEM called frozen HKEM (FHKEM) is investigated to further reduce noise. The iterative part of the FHKEM kernel was frozen at the 72nd sub-iteration. When using ordered subsets algorithms the data is divided in smaller subsets and the smallest algorithm iterative step is called sub-iteration. A NEMA phantom with spherical inserts was used for the optimisation and validation of the algorithm, and data from 5 patients treated with Selective internal radiation therapy were used as proof of clinical relevance of the method.

Results

The results suggest a maximum improvement of 56% for region of interest mean recovery coefficient at fixed coefficient of variation and better identification of the hot volumes in the NEMA phantom. Similar improvements were achieved with patient data, showing 47% mean value improvement over the gold standard used in hospitals.

Conclusions

Such quantitative improvements could facilitate improved dosimetry calculations with SPECT when treating patients with Selective internal radiation therapy, as well as provide a more visible position of the cancerous lesions in the liver.

Simultaneous Denoising of Dynamic PET Images Based on Deep Image Prior

Parametric imaging obtained from kinetic modeling analysis of dynamic positron emission tomography (PET) data is a useful tool for quantifying tracer kinetics. However, pixel-wise time-activity curves have high noise levels which lead to poor quality of parametric images. To solve this limitation, we proposed a new image denoising method based on deep image prior (DIP). Like the original DIP method, the proposed DIP method is an unsupervised method, in which no training dataset is required. However, the difference is that our method can simultaneously denoise all dynamic PET images. Moreover, we propose a modified version of the DIP method called double DIP (DDIP), which has two DIP architectures. The additional DIP model is used to generate high-quality input data for the second DIP model. Computer simulations were performed to evaluate the performance of the proposed DIP-based methods. Our simulation results showed that the DDIP method outperformed the single DIP method. In addition, the DDIP method combined with data augmentation could generate PET parametric images with superior image quality compared to the spatiotemporal-based non-local means filtering and high constrained backprojection. Our preliminary results show that our proposed DDIP method is a novel and effective unsupervised method for simultaneously denoising dynamic PET images.

Direct Reconstruction of Linear Parametric Images From Dynamic PET Using Nonlocal Deep Image Prior

Direct reconstruction methods have been developed to estimate parametric images directly from the measured PET sinograms by combining the PET imaging model and tracer kinetics in an integrated framework. Due to limited counts received, signal-to-noise-ratio (SNR) and resolution of parametric images produced by direct reconstruction frameworks are still limited. Recently supervised deep learning methods have been successfully applied to medical imaging denoising/reconstruction when large number of high-quality training labels are available. For static PET imaging, high-quality training labels can be acquired by extending the scanning time. However, this is not feasible for dynamic PET imaging, where the scanning time is already long enough. In this work, we proposed an unsupervised deep learning framework for direct parametric reconstruction from dynamic PET, which was tested on the Patlak model and the relative equilibrium Logan model. The training objective function was based on the PET statistical model. The patient's anatomical prior image, which is readily available from PET/CT or PET/MR scans, was supplied as the network input to provide a manifold constraint, and also utilized to construct a kernel layer to perform non-local feature denoising. The linear kinetic model was embedded in the network structure as a 1 ×1 ×1 convolution layer. Evaluations based on dynamic datasets of ¹⁸F-FDG and ¹¹C-PiB tracers show that the proposed framework can outperform the traditional and the kernel method-based direct reconstruction methods.

Application of Dynamic Enhanced Magnetic Resonance Imaging in the Diagnosis of Hematological Malignancies

The use of dynamic enhanced magnetic resonance imaging technology can effectively explore the diagnosis and clinical application of hematological malignancies. This paper selected 60 patients with hematological malignancies from 2015 to 2019; all of whom were diagnosed with hematological malignancies, including 40 men and 20 women, aged between 40 and 77 years. The main clinical manifestations of the patient are hematological malignancies, fever, and other symptoms. We used Siemens 3.0T to perform MRI and dynamic enhanced MRI examinations on 30 patients with hematological tumors. The PACS system was used to collect and organize clinical data. All patients were pathologically confirmed and clinically diagnosed with hematological malignancies. Based on the clinical data of the patients, retrospective analysis and summary were conducted and the clinical manifestations of hematological malignancies were discussed. The results showed that the diagnostic accuracy of 30 cases of dynamic enhanced MRI was 100%, while the diagnostic accuracy of ordinary MRI was lower than that of dynamic enhanced MRI, P < 0.05, and the difference was statistically significant. In addition, compared with dynamic enhanced MRI and MRI, P > 0.05, the difference was not statistically significant. Therefore, the application of dynamic enhanced MRI in the diagnosis of hematological malignancies is valuable.

Dynamic PET image reconstruction incorporating a median nonlocal means kernel method

In dynamic positron emission tomography (PET) imaging, the reconstructed image of a single frame often exhibits high noise due to limited counting statistics of projection data. This study proposed a median nonlocal means (MNLM)-based kernel method for dynamic PET image reconstruction. The kernel matrix is derived from median nonlocal means of pre-reconstructed composite images. Then the PET image intensities in all voxels were modeled as a kernel matrix multiplied by coefficients and incorporated into the forward model of PET projection data. Then, the coefficients of each feature were estimated by the maximum likelihood method. Using simulated low-count dynamic data of Zubal head phantom, the quantitative performance of the proposed MNLM kernel method was investigated and compared with the maximum-likelihood method, conventional kernel method with and without median filter, and nonlocal means (NLM) kernel method. Simulation results showed that the MNLM kernel method achieved visual and quantitative accuracy improvements (in terms of the ensemble mean squared error, bias versus variance, and contrast versus noise performances). Especially for frame 2 with the lowest count level of a single frame, the MNLM kernel method achieves lower ensemble mean squared error (10.43%) than the NLM kernel method (13.68%), conventional kernel method with and without median filter (11.88% and 23.50%), and MLEM algorithm (24.77%). The study on real low-dose ¹⁸F-FDG rat data also showed that the MNLM kernel method outperformed other methods in visual and quantitative accuracy improvements (in terms of regional noise versus intensity mean performance).

Use of dynamic reconstruction for parametric Patlak imaging in dynamic whole body PET

Dynamic whole body (DWB) PET acquisition protocols enable the use of whole body parametric imaging for clinical applications. In FDG imaging, accurate parametric images of PatlakK_ican be complementary to regular standardised uptake value images and improve on current applications or enable new ones. In this study we consider DWB protocols implemented on clinical scanners with a limited axial field of view with the use of multiple whole body sweeps. These protocols result in temporal gaps in the dynamic data which produce noisier and potentially more biased parametric images, compared to single bed (SB) dynamic protocols. Dynamic reconstruction using the Patlak model has been previously proposed to overcome these limits and shown improved DWB parametric images ofK_i. In this work, we propose and make use of a spectral analysis based model for dynamic reconstruction and parametric imaging of PatlakK_i. Both dynamic reconstruction methods were evaluated for DWB FDG protocols and compared against 3D reconstruction based parametric imaging from SB dynamic protocols. This work was conducted on simulated data and results were tested against real FDG dynamic data. We showed that dynamic reconstruction can achieve levels of parametric image noise and bias comparable to 3D reconstruction in SB dynamic studies, with the spectral model offering additional flexibility and further reduction of image noise. Comparisons were also made between step and shoot and continuous bed motion (CBM) protocols, which showed that CBM can achieve lower parametric image noise due to reduced acquisition temporal gaps. Finally, our results showed that dynamic reconstruction improved VOI parametric mean estimates but did not result to fully converged values before resulting in undesirable levels of noise. Additional regularisation methods need to be considered for DWB protocols to ensure both accurate quantification and acceptable noise levels for clinical applications.

Anatomically aided PET image reconstruction using deep neural networks

PURPOSE

The developments of PET/CT and PET/MR scanners provide opportunities for improving PET image quality by using anatomical information. In this paper, we propose a novel co-learning three-dimensional (3D) convolutional neural network (CNN) to extract modality-specific features from PET/CT image pairs and integrate complementary features into an iterative reconstruction framework to improve PET image reconstruction.

METHODS

We used a pretrained deep neural network to represent PET images. The network was trained using low-count PET and CT image pairs as inputs and high-count PET images as labels. This network was then incorporated into a constrained maximum likelihood framework to regularize PET image reconstruction. Two different network structures were investigated for the integration of anatomical information from CT images. One was a multichannel CNN, which treated PET and CT volumes as separate channels of the input. The other one was multibranch CNN, which implemented separate encoders for PET and CT images to extract latent features and fed the combined latent features into a decoder. Using computer-based Monte Carlo simulations and two real patient datasets, the proposed method has been compared with existing methods, including the maximum likelihood expectation maximization (MLEM) reconstruction, a kernel-based reconstruction and a CNN-based deep penalty method with and without anatomical guidance.

RESULTS

Reconstructed images showed that the proposed constrained ML reconstruction approach produced higher quality images than the competing methods. The tumors in the lung region have higher contrast in the proposed constrained ML reconstruction than in the CNN-based deep penalty reconstruction. The image quality was further improved by incorporating the anatomical information. Moreover, the liver standard deviation was lower in the proposed approach than all the competing methods at a matched lesion contrast.

CONCLUSIONS

The supervised co-learning strategy can improve the performance of constrained maximum likelihood reconstruction. Compared with existing techniques, the proposed method produced a better lesion contrast versus background standard deviation trade-off curve, which can potentially improve lesion detection.

Modified kernel MLAA using autoencoder for PET-enabled dual-energy CT

Combined use of PET and dual-energy CT provides complementary information for multi-parametric imaging. PET-enabled dual-energy CT combines a low-energy X-ray CT image with a high-energy γ-ray CT (GCT) image reconstructed from time-of-flight PET emission data to enable dual-energy CT material decomposition on a PET/CT scanner. The maximum-likelihood attenuation and activity (MLAA) algorithm has been used for GCT reconstruction but suffers from noise. Kernel MLAA exploits an X-ray CT image prior through the kernel framework to guide GCT reconstruction and has demonstrated substantial improvements in noise suppression. However, similar to other kernel methods for image reconstruction, the existing kernel MLAA uses image intensity-based features to construct the kernel representation, which is not always robust and may lead to suboptimal reconstruction with artefacts. In this paper, we propose a modified kernel method by using an autoencoder convolutional neural network (CNN) to extract an intrinsic feature set from the X-ray CT image prior. A computer simulation study was conducted to compare the autoencoder CNN-derived feature representation with raw image patches for evaluation of kernel MLAA for GCT image reconstruction and dual-energy multi-material decomposition. The results show that the autoencoder kernel MLAA method can achieve a significant image quality improvement for GCT and material decomposition as compared to the existing kernel MLAA algorithm. A weakness of the proposed method is its potential over-smoothness in a bone region, indicating the importance of further optimization in future work. This article is part of the theme issue 'Synergistic tomographic image reconstruction: part 2'.

Technical note: A preliminary study of dual-tracer PET image reconstruction guided by FDG and/or MR kernels

PURPOSE

Clinically, single radiotracer positron emission tomography (PET) imaging is a commonly used examination method; however, since each radioactive tracer reflects the information of only one kind of cell, it easily causes false negatives or false positives in disease diagnosis. Therefore, reasonably combining two or more radiotracers is recommended to improve the accuracy of diagnosis and the sensitivity and specificity of the disease when conditions permit.

METHODS

This paper proposes incorporating ¹⁸ F-fluorodeoxyglucose (FDG) as a higher-quality PET image to guide the reconstruction of other lower-count ¹¹ C-methionine (MET) PET datasets to compensate for the lower image quality by a popular kernel algorithm. Specifically, the FDG prior is needed to extract kernel features, and these features were used to build a kernel matrix using a k-nearest-neighbor (kNN) search for MET image reconstruction. We created a 2-D brain phantom to validate the proposed method by simulating sinogram data containing Poisson random noise and quantitatively compared the performance of the proposed FDG-guided kernelized expectation maximization (KEM) method with the performance of Gaussian and non-local means (NLM) smoothed maximum likelihood expectation maximization (MLEM), MR-guided KEM, and multi-guided-S KEM algorithms. Mismatch experiments between FDG/MR and MET data were also carried out to investigate the outcomes of possible clinical situations.

RESULTS

In the simulation study, the proposed method outperformed the other algorithms by at least 3.11% in the signal-to-noise ratio (SNR) and 0.68% in the contrast recovery coefficient (CRC), and it reduced the mean absolute error (MAE) by 8.07%. Regarding the tumor in the reconstructed image, the proposed method contained more pathological information. Furthermore, the proposed method was still superior to the MR-guided KEM method in the mismatch experiments.

CONCLUSIONS

The proposed FDG-guided KEM algorithm can effectively utilize and compensate for the tissue metabolism information obtained from dual-tracer PET to maximize the advantages of PET imaging.

Rapid high-quality PET Patlak parametric image generation based on direct reconstruction and temporal nonlocal neural network

Parametric imaging based on dynamic positron emission tomography (PET) has wide applications in neurology. Compared to indirect methods, direct reconstruction methods, which reconstruct parametric images directly from the raw PET data, have superior image quality due to better noise modeling and richer information extracted from the PET raw data. For low-dose scenarios, the advantages of direct methods are more obvious. However, the wide adoption of direct reconstruction is inevitably impeded by the excessive computational demand and deficiency of the accessible raw data. In addition, motion modeling inside dynamic PET image reconstruction raises more computational challenges for direct reconstruction methods. In this work, we focused on the ¹⁸F-FDG Patlak model, and proposed a data-driven approach which can estimate the motion corrected full-dose direct Patlak images from the dynamic PET reconstruction series, based on a proposed novel temporal non-local convolutional neural network. During network training, direct reconstruction with motion correction based on full-dose dynamic PET sinograms was performed to obtain the training labels. The reconstructed full-dose /low-dose dynamic PET images were supplied as the network input. In addition, a temporal non-local block based on the dynamic PET images was proposed to better recover the structural information and reduce the image noise. During testing, the proposed network can directly output high-quality Patlak parametric images from the full-dose /low-dose dynamic PET images in seconds. Experiments based on 15 full-dose and 15 low-dose ¹⁸F-FDG brain datasets were conducted and analyzed to validate the feasibility of the proposed framework. Results show that the proposed framework can generate better image quality than reference methods.

Direct and indirect parameter imaging methods for dynamic PET

The method of reconstructing parametric images from dynamic positron emission tomography (PET) data with the linear Patlak model has been widely used in scientific research and clinical practice. Whether for direct or indirect image reconstruction, researchers have deeply investigated the associated methods and effects. Among the existing methods, the traditional maximum likelihood expectation maximization (MLEM) reconstruction algorithm is fast but produces a substantial amount of noise. If the parameter images obtained by the MLEM algorithm are postfiltered, a large amount of image edge information is lost. Additionally, although the kernel method has a better noise reduction effect, its calculation costs are very high due to the complexity of the algorithm. Therefore, to obtain parametric images with a high signal-to-noise ratio (SNR) and good retention of detailed information, here, we use guided kernel means (GKM) and dynamic PET image information to conduct guided filtering and perform parametric image reconstruction. We apply this method to direct and indirect reconstruction, and through computer simulations, we show that our proposed method has higher identifiability and a greater SNR than conventional direct and indirect reconstruction methods. We also show that our method produces better images with direct than with indirect reconstruction.

Learning non-local perfusion textures for high-quality computed tomography perfusion imaging

Background. Computed tomography perfusion (CTP) imaging plays a critical role in the acute stroke syndrome assessment due to its widespread availability, speed of image acquisition, and relatively low cost. However, due to its repeated scanning protocol, CTP imaging involves a substantial radiation dose, which might increase potential cancer risks.Methods. In this work, we present a novel deep learning model called non-local perfusion texture learning network (NPTN) for high-quality CTP imaging at low-dose cases. Specifically, considering abundant similarities in the CTP images, i.e. latent self-similarities within the non-local region in the CTP images, we firstly search the most similar pixels from the adjacent frames within a fixed search window to obtain the non-local similarities and to construct non-local textures vector. Then, both the low-dose frame and these non-local textures from adjacent frames are fed into a convolution neural network to predict high-quality CTP images, which can help better characterize the structure details and contrast variants in the targeted CTP image rather than simply utilizing the targeted frame itself. The residual learning strategy and batch normalization are utilized to boost the performance of the convolution neural network. In the experiment, the CTP images of 31 patients with suspected stroke disease are collected to demonstrate the performance of the presented NPTN method.Results. The results show the presented NPTN method obtains superior performance compared with the competing methods. From numerical value, at all dose levels, the presented NPTN method has achieved around 3.0 dB improvement of average PSNR, an increase of around 1.4% of average SSIM, and a decrease of around 4.8% of average RMSE in the low-dose CTP reconstruction task, and also has achieved an increase of around 3.4% of average SSIM and a decrease of around 61.1% of average RMSE in the cerebral blood flow (CBF) estimation task.Conclusions. The presented NPTN method can obtain high-quality CTP images and estimate high-accuracy CBF map by characterizing more structure details and contrast variants in the CTP image and outperform the competing methods at low-dose cases.

4D deep image prior: dynamic PET image denoising using an unsupervised four-dimensional branch convolutional neural network

Although convolutional neural networks (CNNs) demonstrate the superior performance in denoising positron emission tomography (PET) images, a supervised training of the CNN requires a pair of large, high-quality PET image datasets. As an unsupervised learning method, a deep image prior (DIP) has recently been proposed; it can perform denoising with only the target image. In this study, we propose an innovative procedure for the DIP approach with a four-dimensional (4D) branch CNN architecture in end-to-end training to denoise dynamic PET images. Our proposed 4D CNN architecture can be applied to end-to-end dynamic PET image denoising by introducing a feature extractor and a reconstruction branch for each time frame of the dynamic PET image. In the proposed DIP method, it is not necessary to prepare high-quality and large patient-related PET images. Instead, a subject's own static PET image is used as additional information, dynamic PET images are treated as training labels, and denoised dynamic PET images are obtained from the CNN outputs. Both simulation with [¹⁸F]fluoro-2-deoxy-D-glucose (FDG) and preclinical data with [¹⁸F]FDG and [¹¹C]raclopride were used to evaluate the proposed framework. The results showed that our 4D DIP framework quantitatively and qualitatively outperformed 3D DIP and other unsupervised denoising methods. The proposed 4D DIP framework thus provides a promising procedure for dynamic PET image denoising.

3D/4D Reconstruction and Quantitative Total Body Imaging

Total-body PET image reconstruction follows a similar procedure to the image reconstruction process for standard whole-body PET scanners. One unique aspect of total-body imaging is simultaneous coverage of the entire human body, which makes it convenient to perform total-body dynamic PET scans. Therefore, four-dimensional dynamic PET reconstruction and parametric imaging are of great interest in total-body imaging. This article covers some basics of PET image reconstruction and then focuses on three- and four-dimensional PET reconstruction for total-body imaging. Methods for image formation from raw measurements in total-body PET are described. Challenges and opportunities in total-body PET image reconstruction are discussed.

PET-enabled dual-energy CT: image reconstruction and a proof-of-concept computer simulation study

Standard dual-energy computed tomography (CT) uses two different x-ray energies to obtain energy-dependent tissue attenuation information to allow quantitative material decomposition. The combined use of dual-energy CT and positron emission tomography (PET) may provide a more comprehensive characterization of disease states in cancer and other diseases. However, the integration of dual-energy CT with PET is not trivial, either requiring costly hardware upgrades or increasing radiation exposure. This paper proposes a different dual-energy CT imaging method that is enabled by PET. Instead of using a second x-ray CT scan with a different energy, this method exploits time-of-flight PET image reconstruction via the maximum likelihood attenuation and activity (MLAA) algorithm to obtain a 511 keV gamma-ray attenuation image from PET emission data. The high-energy gamma-ray attenuation image is then combined with the low-energy x-ray CT of PET/CT to provide a pair of dual-energy CT images. A major challenge with the standard MLAA reconstruction is the high noise present in the reconstructed 511 keV attenuation map, which would not compromise the PET activity reconstruction too much but may significantly affect the performance of the gamma-ray attenuation image for material decomposition. To overcome the problem, we further propose a kernel MLAA algorithm to exploit the prior information from the available x-ray CT image. We conducted a computer simulation to test the concept and algorithm for the task of material decomposition. The simulation results demonstrate that this PET-enabled dual-energy CT method is promising for quantitative material decomposition. The proposed method can be readily implemented on time-of-flight PET/CT scanners to enable simultaneous PET and dual-energy CT imaging.

Penalized-likelihood PET Image Reconstruction Using 3D Structural Convolutional Sparse Coding

Positron emission tomography (PET) is widely used for clinical diagnosis. As PET suffers from low resolution and high noise, numerous efforts try to incorporate anatomical priors into PET image reconstruction, especially with the development of hybrid PET/CT and PET/MRI systems. In this work, we proposed a cube-based 3D structural convolutional sparse coding (CSC) concept for penalized-likelihood PET image reconstruction, named 3D PET-CSC. The proposed 3D PET-CSC takes advantage of the convolutional operation and manages to incorporate anatomical priors without the need of registration or supervised training. As 3D PET-CSC codes the whole 3D PET image, instead of patches, it alleviates the staircase artifacts commonly presented in traditional patch-based sparse coding methods. Compared with traditional coding methods in Fourier domain, the proposed method extends the 3D CSC to a straightforward approach based on the pursuit of localized cubes. Moreover, we developed the residual-image and order-subset mechanisms to further reduce the computational cost and accelerate the convergence for the proposed 3D PET-CSC method. Experiments based on computer simulations and clinical datasets demonstrate the superiority of 3D PET-CSC compared with other reference methods.

Generative adversarial network based regularized image reconstruction for PET

Positron emission tomography (PET) is an ill-posed inverse problem and suffers high noise due to limited number of detected events. Prior information can be used to improve the quality of reconstructed PET images. Deep neural networks have also been applied to regularized image reconstruction. One method is to use a pretrained denoising neural network to represent the PET image and to perform a constrained maximum likelihood estimation. In this work, we propose to use a generative adversarial network (GAN) to further improve the network performance. We also modify the objective function to include a data-matching term on the network input. Experimental studies using computer-based Monte Carlo simulations and real patient datasets demonstrate that the proposed method leads to noticeable improvements over the kernel-based and U-net-based regularization methods in terms of lesion contrast recovery versus background noise trade-offs.

Probabilistic Graphical Models for Dynamic PET: A Novel Approach to Direct Parametric Map Estimation and Image Reconstruction

In the context of dynamic emission tomography, the conventional processing pipeline consists of independent image reconstruction of single-time frames, followed by the application of a suitable kinetic model to time-activity curves (TACs) at the voxel or region-of-interest level. Direct 4D positron emission tomography (PET) reconstruction, by contrast, seeks to move beyond this scheme and incorporate information from multiple time frames within the reconstruction task. Established direct methods are based on a deterministic description of voxelwise TACs, captured by the chosen kinetic model, considering the photon counting process the only source of uncertainty. In this paper, we introduce a new probabilistic modeling strategy based on the key assumption that activity time course would be subject to uncertainty even if the parameters of the underlying dynamic process are known. This leads to a hierarchical model that we formulate using the formalism of probabilistic graphical modeling. The inference is addressed using a new iterative algorithm, in which kinetic modeling results are treated as prior expectation of activity time course, rather than as a deterministic match, making it possible to control the trade-off between a data-driven and a model-driven reconstruction. The proposed method is flexible to an arbitrary choice of (linear and nonlinear) kinetic models, it enables the inclusion of arbitrary (sub)differentiable priors for parametric maps, and it is simple to implement. Computer simulations and an application to a real-patient scan show how the proposed method is able to generalize over conventional indirect and direct approaches, providing a bridge between them by properly tuning the impact of the kinetic modeling step on image reconstruction.

3D Tensor Based Nonlocal Low Rank Approximation in Dynamic PET Reconstruction

Reconstructing images from multi-view projections is a crucial task both in the computer vision community and in the medical imaging community, and dynamic positron emission tomography (PET) is no exception. Unfortunately, image quality is inevitably degraded by the limitations of photon emissions and the trade-off between temporal and spatial resolution. In this paper, we develop a novel tensor based nonlocal low-rank framework for dynamic PET reconstruction. Spatial structures are effectively enhanced not only by nonlocal and sparse features, but momentarily by tensor-formed low-rank approximations in the temporal realm. Moreover, the total variation is well regularized as a complementation for denoising. These regularizations are efficiently combined into a Poisson PET model and jointly solved by distributed optimization. The experiments demonstrated in this paper validate the excellent performance of the proposed method in dynamic PET.

Intercomparison of MR-informed PET image reconstruction methods

PURPOSE

Numerous image reconstruction methodologies for positron emission tomography (PET) have been developed that incorporate magnetic resonance (MR) imaging structural information, producing reconstructed images with improved suppression of noise and reduced partial volume effects. However, the influence of MR structural information also increases the possibility of suppression or bias of structures present only in the PET data (PET-unique regions). To address this, further developments for MR-informed methods have been proposed, for example, through inclusion of the current reconstructed PET image, alongside the MR image, in the iterative reconstruction process. In this present work, a number of kernel and maximum a posteriori (MAP) methodologies are compared, with the aim of identifying methods that enable a favorable trade-off between the suppression of noise and the retention of unique features present in the PET data.

METHODS

The reconstruction methods investigated were: the MR-informed conventional and spatially compact kernel methods, referred to as KEM and KEM largest value sparsification (LVS) respectively; the MR-informed Bowsher and Gaussian MR-guided MAP methods; and the PET-MR-informed hybrid kernel and anato-functional MAP methods. The trade-off between improving the reconstruction of the whole brain region and the PET-unique regions was investigated for all methods in comparison with postsmoothed maximum likelihood expectation maximization (MLEM), evaluated in terms of structural similarity index (SSIM), normalized root mean square error (NRMSE), bias, and standard deviation. Both simulated BrainWeb (10 noise realizations) and real [18 F] fluorodeoxyglucose (FDG) three-dimensional datasets were used. The real [18 F]FDG dataset was augmented with simulated tumors to allow comparison of the reconstruction methodologies for the case of known regions of PET-MR discrepancy and evaluated at full counts (100%) and at a reduced (10%) count level.

RESULTS

For the high-count simulated and real data studies, the anato-functional MAP method performed better than the other methods under investigation (MR-informed, PET-MR-informed and postsmoothed MLEM), in terms of achieving the best trade-off for the reconstruction of the whole brain and PET-unique regions, assessed in terms of the SSIM, NRMSE, and bias vs standard deviation. The inclusion of PET information in the anato-functional MAP method enables the reconstruction of PET-unique regions to attain similarly low levels of bias as unsmoothed MLEM, while moderately improving the whole brain image quality for low levels of regularization. However, for low count simulated datasets the anato-functional MAP method performs poorly, due to the inclusion of noisy PET information in the regularization term. For the low counts simulated dataset, KEM LVS and to a lesser extent, HKEM performed better than the other methods under investigation in terms of achieving the best trade-off for the reconstruction of the whole brain and PET-unique regions, assessed in terms of the SSIM, NRMSE, and bias vs standard deviation.

CONCLUSION

For the reconstruction of noisy data, multiple MR-informed methods produce favorable whole brain vs PET-unique region trade-off in terms of the image quality metrics of SSIM and NRMSE, comfortably outperforming the whole image denoising of postsmoothed MLEM.

PET Image Reconstruction Using Deep Image Prior

Recently, deep neural networks have been widely and successfully applied in computer vision tasks and have attracted growing interest in medical imaging. One barrier for the application of deep neural networks to medical imaging is the need for large amounts of prior training pairs, which is not always feasible in clinical practice. This is especially true for medical image reconstruction problems, where raw data are needed. Inspired by the deep image prior framework, in this paper, we proposed a personalized network training method where no prior training pairs are needed, but only the patient's own prior information. The network is updated during the iterative reconstruction process using the patient-specific prior information and measured data. We formulated the maximum-likelihood estimation as a constrained optimization problem and solved it using the alternating direction method of multipliers algorithm. Magnetic resonance imaging guided positron emission tomography reconstruction was employed as an example to demonstrate the effectiveness of the proposed framework. Quantification results based on simulation and real data show that the proposed reconstruction framework can outperform Gaussian post-smoothing and anatomically guided reconstructions using the kernel method or the neural-network penalty.

A kernel-based image denoising method for improving parametric image generation

One of the main challenges in the pixel-wise modeling analysis is the presence of high noise levels. Wang and Qi proposed a kernel-based method for dynamic positron emission tomgraphy reconstruction. Inspired by this method, we propose a kernel-based image denoising method based on the minimization of a kernel-based lp-norm regularized problem. To solve the kernel-based image denoising problem, we used the general-threshold filtering algorithm in combination with total difference. In the present study, we investigated whether diffusion-weighted magnetic resonance imaging (DW-MRI) data denoised using the proposed method can provide improved intravoxel incoherent motion (IVIM) parametric images. We also compared the proposed method with the method using the local principal component analysis (LPCA). The simulated DW-MR magnitude images are assumed to have Rician distributed noise. Computer simulations show that the proposed image denoising method can achieve a better bias-variance trade-off than the LPCA method. Moreover, the proposed method can reduce variance while simultaneously preserving edges in the parametric images. We tested our image denoising method on in vivo DW-MRI data, and the result showed that the denoised DWI-MRI data obtained using the proposed method can substantially improve the quality of IVIM parametric images.

High Temporal-Resolution Dynamic PET Image Reconstruction Using a New Spatiotemporal Kernel Method

Current clinical dynamic PET has an effective temporal resolution of 5-10 seconds, which can be adequate for traditional compartmental modeling but is inadequate for exploiting the benefit of more advanced tracer kinetic modeling for characterization of diseases (e.g., cancer and heart disease). There is a need to improve dynamic PET to allow fine temporal sampling of 1-2 seconds. However, the reconstruction of these short-time frames from tomographic data is extremely challenging as the count level of each frame is very low and high noise presents in both spatial and temporal domains. Previously, the kernel framework has been developed and demonstrated as a statistically efficient approach to utilizing image prior for low-count PET image reconstruction. Nevertheless, the existing kernel methods mainly explore spatial correlations in the data and only have a limited ability in suppressing temporal noise. In this paper, we propose a new kernel method which extends the previous spatial kernel method to the general spatiotemporal domain. The new kernelized model encodes both spatial and temporal correlations obtained from image prior information and are incorporated into the PET forward projection model to improve themaximumlikelihood(ML) image reconstruction. Computer simulations and an application to real patient scan have shown that the proposed approach can achieve effective noise reduction in both spatial and temporal domains and outperform the spatial kernel method and conventional ML reconstruction method for improving the high temporal-resolution dynamic PET imaging.

Iterative PET Image Reconstruction Using Convolutional Neural Network Representation

PET image reconstruction is challenging due to the ill-poseness of the inverse problem and limited number of detected photons. Recently, the deep neural networks have been widely and successfully used in computer vision tasks and attracted growing interests in medical imaging. In this paper, we trained a deep residual convolutional neural network to improve PET image quality by using the existing inter-patient information. An innovative feature of the proposed method is that we embed the neural network in the iterative reconstruction framework for image representation, rather than using it as a post-processing tool. We formulate the objective function as a constrained optimization problem and solve it using the alternating direction method of multipliers algorithm. Both simulation data and hybrid real data are used to evaluate the proposed method. Quantification results show that our proposed iterative neural network method can outperform the neural network denoising and conventional penalized maximum likelihood methods.

PET Image Denoising Using a Deep Neural Network Through Fine Tuning

Positron emission tomography (PET) is a functional imaging modality widely used in clinical diagnosis. In this work, we trained a deep convolutional neural network (CNN) to improve PET image quality. Perceptual loss based on features derived from a pre-trained VGG network, instead of the conventional mean squared error, was employed as the training loss function to preserve image details. As the number of real patient data set for training is limited, we propose to pre-train the network using simulation data and fine-tune the last few layers of the network using real data sets. Results from simulation, real brain and lung data sets show that the proposed method is more effective in removing noise than the traditional Gaussian filtering method.

Multi-energy computed tomography reconstruction using a nonlocal spectral similarity model

Multi-energy computed tomography (MECT) is able to acquire simultaneous multi-energy measurements from one scan. In addition, it allows material differentiation and quantification effectively. However, due to the limited energy bin width, the number of photons detected in an energy-specific channel is smaller than that in traditional CT, which results in image quality degradation. To address this issue, in this work, we develop a statistical iterative reconstruction algorithm to acquire high-quality MECT images and high-accuracy material-specific images. Specifically, this algorithm fully incorporates redundant self-similarities within nonlocal regions in the MECT image at one bin and rich spectral similarities among MECT images at all bins. For simplicity, the presented algorithm is referred to as 'MECT-NSS'. Moreover, an efficient optimization algorithm is developed to solve the MECT-NSS objective function. Then, a comprehensive evaluation of parameter selection for the MECT-NSS algorithm is conducted. In the experiment, the datasets include images from three phantoms and one patient to validate and evaluate the MECT-NSS reconstruction performance. The qualitative and quantitative results demonstrate that the presented MECT-NSS can successfully yield better MECT image quality and more accurate material estimation than the competing algorithms.

Hybrid PET/MR Kernelised Expectation Maximisation Reconstruction for Improved Image-Derived Estimation of the Input Function from the Aorta of Rabbits

Positron emission tomography (PET) provides simple noninvasive imaging biomarkers for multiple human diseases which can be used to produce quantitative information from single static images or to monitor dynamic processes. Such kinetic studies often require the tracer input function (IF) to be measured but, in contrast to direct blood sampling, the image-derived input function (IDIF) provides a noninvasive alternative technique to estimate the IF. Accurate estimation can, in general, be challenging due to the partial volume effect (PVE), which is particularly important in preclinical work on small animals. The recently proposed hybrid kernelised ordered subsets expectation maximisation (HKEM) method has been shown to improve accuracy and contrast across a range of different datasets and count levels and can be used on PET/MR or PET/CT data. In this work, we apply the method with the purpose of providing accurate estimates of the aorta IDIF for rabbit PET studies. In addition, we proposed a method for the extraction of the aorta region of interest (ROI) using the MR and the HKEM image, to minimise the PVE within the rabbit aortic region-a method which can be directly transferred to the clinical setting. A realistic simulation study was performed with ten independent noise realisations while two, real data, rabbit datasets, acquired with the Biograph Siemens mMR PET/MR scanner, were also considered. For reference and comparison, the data were reconstructed using OSEM, OSEM with Gaussian postfilter and KEM, as well as HKEM. The results across the simulated datasets and different time frames show reduced PVE and accurate IDIF values for the proposed method, with 5% average bias (0.8% minimum and 16% maximum bias). Consistent results were obtained with the real datasets. The results of this study demonstrate that HKEM can be used to accurately estimate the IDIF in preclinical PET/MR studies, such as rabbit mMR data, as well as in clinical human studies. The proposed algorithm is made available as part of an open software library, and it can be used equally successfully on human or animal data acquired from a variety of PET/MR or PET/CT scanners.

Effect of PET-MR Inconsistency in the Kernel Image Reconstruction Method

Anatomically-driven image reconstruction algorithms have become very popular in positron emission tomography (PET) where they have demonstrated improved image resolution and quantification. This work, consider the effect of spatial inconsistency between MR and PET images in hot and cold regions of the PET image. We investigate these effects on the kernel method from machine learning, in particular, the hybrid kernelized expectation maximization (HKEM). These were applied to Jaszczak phantom and patient data acquired with the Biograph Siemens mMR. The results show that even a small shift can cause a significant change in activity concentration. In general, the PET-MR inconsistencies can induce the partial volume effect, more specifically the 'spill-in' of the affected cold regions and the 'spill-out' from the hot regions. The maximum change was about 100% for the cold region and 10% for the hot lesion using KEM, against the 37% and 8% obtained with HKEM. The findings of this work suggest that including PET information in the kernel enhances the flexibility of the reconstruction in case of spatial inconsistency. Nevertheless, accurate registration and choice of the appropriate MR image for the creation of the kernel is essential to avoid artifacts, blurring, and bias.

Three-Dimensional Holographic Electromagnetic Imaging for Accessing Brain Stroke

The authors recently developed a two-dimensional (2D) holographic electromagnetic induction imaging (HEI) for biomedical imaging applications. However, this method was unable to detect small inclusions accurately. For example, only one of two inclusions can be detected in the reconstructed image if the two inclusions were located at the same XY plane but in different Z-directions. This paper provides a theoretical framework of three-dimensional (3D) HEI to accurately and effectively detect inclusions embedded in a biological object. A numerical system, including a realistic head phantom, a 16-element excitation sensor array, a 16-element receiving sensor array, and image processing model has been developed to evaluate the effectiveness of the proposed method for detecting small stroke. The achieved 3D HEI images have been compared with 2D HEI images. Simulation results show that the 3D HEI method can accurately and effectively identify small inclusions even when two inclusions are located at the same XY plane but in different Z-directions. This preliminary study shows that the proposed method has the potential to develop a useful imaging tool for the diagnosis of neurological diseases and injuries in the future.

Spatially-Compact MR-Guided Kernel EM for PET Image Reconstruction

Positron emission tomography (PET) is a highly sensitive functional and molecular imaging modality which can measure picomolar concentrations of an injected radionuclide. However, the physical sensitivity of PET is limited, and reducing the injected dose leads to low count data and noisy reconstructed images. A highly effective way of reducing noise is to reparameterise the reconstruction in terms of MR-derived spatial basis functions. Spatial basis functions derived using the kernel method have demonstrated excellent noise reduction properties and maintain shared PET-MR detailed structures. However, as previously shown in the literature, the MR-guided kernel method may lead to excessive smoothing of structures that are only present in the PET data. This work makes two main contributions in order to address this problem: first, we exploit the potential of the MR-guided kernel method to form more spatially-compact basis functions which are able to preserve PET-unique structures, and secondly, we consider reconstruction at the native MR resolution. The former contribution notably improves the recovery of structures which are unique to the PET data. These adaptations of the kernel method were compared to the conventional implementation of the MR-guided kernel method and also to MLEM, in terms of ability to recover PET unique structures for both simulated and real data. The spatially-compact kernel method showed clear visual and quantitative improvements in the reconstruction of the PET unique structures, relative to the conventional kernel method for all sizes of PET unique structures investigated, whilst maintaining to a large extent the impressive noise mitigating and detail preserving properties of the conventional MR-guided kernel method. We therefore conclude that a spatially-compact parameterisation of the MR-guided kernel method, should be the preferred implementation strategy in order to obviate unnecessary losses in PET-unique details.

Corrections to "Direct Patlak Reconstruction From Dynamic PET Data Using the Kernel Method With MRI Information Based on Structural Similarity"

In the above paper [1], there are typos in Algorithm 1 table. The correct version of Algorithm 1 is given below.

An Efficient Approach to Perform MR-assisted PET Data Optimization in Simultaneous PET/MR Neuroimaging Studies

A main advantage of PET is that it provides quantitative measures of the radiotracer concentration, but its accuracy is confounded by several factors, including attenuation, subject motion, and limited spatial resolution. Using the information from one simultaneously acquired morphological MR sequence with embedded navigators, we propose an efficient method called MR-assisted PET data optimization (MaPET) to perform attenuation correction (AC), motion correction, and anatomy-aided reconstruction. Methods: For attenuation correction, voxel-wise linear attenuation coefficient maps were generated using an SPM8-based approach method on the MR volume. The embedded navigators were used to derive head motion estimates for event-based PET motion correction. The anatomy provided by the MR volume was incorporated into the PET image reconstruction using a kernel-based method. Region-based analyses were carried out to assess the quality of images generated through various stages of PET data optimization. Results: The optimized PET images reconstructed with MaPET was superior in image quality compared to images reconstructed using only attenuation correction, with high SNR and low coefficient of variation (5.08 and 0.229 in a composite cortical region compared to 3.12 and 0.570). The optimized images were also shown using the Cohen's d metric to achieve a greater effect size in distinguishing cortical regions with hypometabolism from regions of preserved metabolism in each individual for different diagnosis groups. Conclusion: We have shown the spatiotemporally correlated data acquired using a single MR sequence can be used for PET attenuation, motion and partial volume effects corrections and the MaPET method may enable more accurate assessment of pathological changes in dementia and other brain disorders.

Attenuation correction for brain PET imaging using deep neural network based on Dixon and ZTE MR images

Positron emission tomography (PET) is a functional imaging modality widely used in neuroscience studies. To obtain meaningful quantitative results from PET images, attenuation correction is necessary during image reconstruction. For PET/MR hybrid systems, PET attenuation is challenging as magnetic resonance (MR) images do not reflect attenuation coefficients directly. To address this issue, we present deep neural network methods to derive the continuous attenuation coefficients for brain PET imaging from MR images. With only Dixon MR images as the network input, the existing U-net structure was adopted and analysis using forty patient data sets shows it is superior to other Dixon-based methods. When both Dixon and zero echo time (ZTE) images are available, we have proposed a modified U-net structure, named GroupU-net, to efficiently make use of both Dixon and ZTE information through group convolution modules when the network goes deeper. Quantitative analysis based on fourteen real patient data sets demonstrates that both network approaches can perform better than the standard methods, and the proposed network structure can further reduce the PET quantification error compared to the U-net structure.