Method for transforming CT images for attenuation correction in PET/CT imaging

Artificial intelligence-based joint attenuation and scatter correction strategies for multi-tracer total-body PET

BACKGROUND

Low-dose ungated CT is commonly used for total-body PET attenuation and scatter correction (ASC). However, CT-based ASC (CT-ASC) is limited by radiation dose risks of CT examinations, propagation of CT-based artifacts and potential mismatches between PET and CT. We demonstrate the feasibility of direct ASC for multi-tracer total-body PET in the image domain.

METHODS

Clinical uEXPLORER total-body PET/CT datasets of [18F]FDG (N = 52), [18F]FAPI (N = 46) and [68Ga]FAPI (N = 60) were retrospectively enrolled in this study. We developed an improved 3D conditional generative adversarial network (cGAN) to directly estimate attenuation and scatter-corrected PET images from non-attenuation and scatter-corrected (NASC) PET images. The feasibility of the proposed 3D cGAN-based ASC was validated using four training strategies: (1) Paired 3D NASC and CT-ASC PET images from three tracers were pooled into one centralized server (CZ-ASC). (2) Paired 3D NASC and CT-ASC PET images from each tracer were individually used (DL-ASC). (3) Paired NASC and CT-ASC PET images from one tracer ([18F]FDG) were used to train the networks, while the other two tracers were used for testing without fine-tuning (NFT-ASC). (4) The pre-trained networks of (3) were fine-tuned with two other tracers individually (FT-ASC). We trained all networks in fivefold cross-validation. The performance of all ASC methods was evaluated by qualitative and quantitative metrics using CT-ASC as the reference.

RESULTS

CZ-ASC, DL-ASC and FT-ASC showed comparable visual quality with CT-ASC for all tracers. CZ-ASC and DL-ASC resulted in a normalized mean absolute error (NMAE) of 8.51 ± 7.32% versus 7.36 ± 6.77% (p < 0.05), outperforming NASC (p < 0.0001) in [18F]FDG dataset. CZ-ASC, FT-ASC and DL-ASC led to NMAE of 6.44 ± 7.02%, 6.55 ± 5.89%, and 7.25 ± 6.33% in [18F]FAPI dataset, and NMAE of 5.53 ± 3.99%, 5.60 ± 4.02%, and 5.68 ± 4.12% in [68Ga]FAPI dataset, respectively. CZ-ASC, FT-ASC and DL-ASC were superior to NASC (p < 0.0001) and NFT-ASC (p < 0.0001) in terms of NMAE results.

CONCLUSIONS

CZ-ASC, DL-ASC and FT-ASC demonstrated the feasibility of providing accurate and robust ASC for multi-tracer total-body PET, thereby reducing the radiation hazards to patients from redundant CT examinations. CZ-ASC and FT-ASC could outperform DL-ASC for cross-tracer total-body PET AC.

Technical note: Can photon-counting CT improve PET/CT's quantitative accuracy?

BACKGROUND

Linear attenuation coefficients (LACs) in positron emission tomography combined with computed tomography (PET/CT) are derived from CT scans that utilize energy-integrating detectors (EID-CT). These LACs are inaccurate when iodine contrast has been injected. Photon counting detector CT (PCD-CT) may be able to improve the accuracy.

PURPOSE

To investigate whether PCD-CT can improve PET/CT quantitative accuracy.

METHODS

Two experiments were performed: one with CT only and one that combined PET and CT. The first experiment used an electron density phantom whose inserts were imaged with EID-CT and PCD-CT. The inserts simulated normal human tissues, including bone and iodinated blood. In the case of PCD-CT, virtual-monoenergetic images at 190 keV were created. LACs were derived in each case and compared against known values. For inserts with iodine, more accurate LACs were expected with PCD-CT. The second experiment involved a custom PET phantom with various materials simulating human tissues (blood, iodinated blood, and bone) and 18F radioactivity. Data were first acquired with an EID-CT-based PET/CT system and then separately in a PCD-CT system without PET. PET images were reconstructed using LAC from EID-CT and PCD-CT. PET image values were compared against known activity values using recovery coefficients (RC).

RESULTS

In the first experiment, LAC based on EID-CT were in error by as much as 18%, whereas the corresponding PCD-CT based measurements were within 3%. In the second experiment, minimum, maximum, and mean RC were (96.1%, 115.4%, and 103.8%) for the EID-CT method, and (95.8%, 105.5%, and 101.0%) for the PCD-CT method. The consistency of PET images in body and head orientations was improved.

CONCLUSIONS

PCD-CT can acquire the information needed for accurate LAC for PET reconstruction in a single spiral acquisition.

GAN-based generation of realistic 3D volumetric data: A systematic review and taxonomy

With the massive proliferation of data-driven algorithms, such as deep learning-based approaches, the availability of high-quality data is of great interest. Volumetric data is very important in medicine, as it ranges from disease diagnoses to therapy monitoring. When the dataset is sufficient, models can be trained to help doctors with these tasks. Unfortunately, there are scenarios where large amounts of data is unavailable. For example, rare diseases and privacy issues can lead to restricted data availability. In non-medical fields, the high cost of obtaining enough high-quality data can also be a concern. A solution to these problems can be the generation of realistic synthetic data using Generative Adversarial Networks (GANs). The existence of these mechanisms is a good asset, especially in healthcare, as the data must be of good quality, realistic, and without privacy issues. Therefore, most of the publications on volumetric GANs are within the medical domain. In this review, we provide a summary of works that generate realistic volumetric synthetic data using GANs. We therefore outline GAN-based methods in these areas with common architectures, loss functions and evaluation metrics, including their advantages and disadvantages. We present a novel taxonomy, evaluations, challenges, and research opportunities to provide a holistic overview of the current state of volumetric GANs.

Development of a Monte Carlo-based scatter correction method for total-body PET using the uEXPLORER PET/CT scanner

Objective.This study presents and evaluates a robust Monte Carlo-based scatter correction (SC) method for long axial field of view (FOV) and total-body positron emission tomography (PET) using the uEXPLORER total-body PET/CT scanner.Approach.Our algorithm utilizes the Monte Carlo (MC) tool SimSET to compute SC factors in between individual image reconstruction iterations within our in-house list-mode and time-of-flight-based image reconstruction framework. We also introduced a unique scatter scaling technique at the detector block-level for optimal estimation of the scatter contribution in each line of response. First image evaluations were derived from phantom data spanning the entire axial FOV along with image data from a human subject with a large body mass index. Data was evaluated based on qualitative inspections, and contrast recovery, background variability, residual scatter removal from cold regions, biases and axial uniformity were quantified and compared to non-scatter-corrected images.Main results.All reconstructed images demonstrated qualitative and quantitative improvements compared to non-scatter-corrected images: contrast recovery coefficients improved by up to 17.2% and background variability was reduced by up to 34.3%, and the residual lung error was between 1.26% and 2.08%. Low biases throughout the axial FOV indicate high quantitative accuracy and axial uniformity of the corrections. Up to 99% of residual activity in cold areas in the human subject was removed, and the reliability of the method was demonstrated in challenging body regions like in the proximity of a highly attenuating knee prosthesis.Significance.The MC SC method employed was demonstrated to be accurate and robust in TB-PET. The results of this study can serve as a benchmark for optimizing the quantitative performance of future SC techniques.

Application of geometric shape-based CT field-of-view extension algorithms in an all-digital positron emission tomography/computed tomography system

BACKGROUND

Computed tomography (CT)-based positron emission tomography (PET) attenuation correction (AC) is a commonly used method in PET AC. However, the CT truncation caused by the subject's limbs outside the CT field-of-view (FOV) leads to errors in PET AC.

PURPOSE

In order to enhance the quantitative accuracy of PET imaging in the all-digital DigitMI 930 PET/CT system, we assessed the impact of FOV truncation on its image quality and investigated the effectiveness of geometric shape-based FOV extension algorithms in this system.

METHODS

We implemented two geometric shape-based FOV extension algorithms. By setting the data from different numbers of detector channels on either side of the sinogram to zero, we simulated various levels of truncation. Specific regions of interest (ROI) were selected, and the mean values of these ROIs were calculated to visually compare the differences between truncated CT, CT extended using the FOV extension algorithms, and the original CT. Furthermore, we conducted statistical analyses on the mean and standard deviation of residual maps between truncated/extended CT and the original CT at different levels of truncation. Subsequently, similar data processing was applied to PET images corrected using original CT and those corrected using simulated truncated and extended CT images. This allowed us to evaluate the influence of FOV truncation on the images produced by the DigitMI 930 PET/CT system and assess the effectiveness of the FOV extension algorithms.

RESULTS

Truncation caused bright artifacts at the CT FOV edge and a slight increase in pixel values within the FOV. When using truncated CT data for PET AC, the PET activity outside the CT FOV decreased, while the extension algorithm effectively reduced these effects. Patient data showed that the activity within the CT FOV decreased by 60% in the truncated image compared to the base image, but this number could be reduced to at least 17.3% after extension.

CONCLUSION

The two geometric shape-based algorithms effectively eliminate CT truncation artifacts and restore the true distribution of CT shape and PET emission data outside the FOV in the all-digital DigitMI 930 PET/CT system. These two algorithms can be used as basic solutions for CT FOV extension in all-digital PET/CT systems.

MRI Coil Development Strategies for Hybrid MR-PET Systems: A Review

Simultaneously operating MR-PET systems have the potential to provide synergetic multi-parametric information, and, as such, interest surrounding their use and development is increasing. However, despite the potential advantages offered by fully combined MR-PET systems, implementing this hybrid integration is technically laborious, and any factors degrading the quality of either modality must be circumvented to ensure optimal performance. In order to attain the best possible quality from both systems, most full MR-PET integrations tend to place the shielded PET system inside the MRI system, close to the target volume of the subject. The radiofrequency (RF) coil used in MRI systems is a key factor in determining the quality of the MR images, and, in simultaneous acquisition, it is generally positioned inside the PET system and PET imaging region, potentially resulting in attenuation and artefacts in the PET images. Therefore, when designing hybrid MR-PET systems, it is imperative that consideration be given to the RF coils inside the PET system. In this review, we present current state-of-the-art RF coil designs used for hybrid MR-PET experiments and discuss various design strategies for constructing PET transparent RF coils.

Systematic evaluation of human soft tissue attenuation correction in whole-body PET/MR: Implications from PET/CT for optimization of MR-based AC in patients with normal lung tissue

BACKGROUND

Attenuation correction (AC) is an important methodical step in positron emission tomography/magnetic resonance imaging (PET/MRI) to correct for attenuated and scattered PET photons.

PURPOSE

The overall quality of magnetic resonance (MR)-based AC in whole-body PET/MRI was evaluated in direct comparison to computed tomography (CT)-based AC serving as reference. The quantitative impact of isolated tissue classes in the MR-AC was systematically investigated to identify potential optimization needs and strategies.

METHODS

Data of n = 60 whole-body PET/CT patients with normal lung tissue and without metal implants/prostheses were used to generate six different AC-models based on the CT data for each patient, simulating variations of MR-AC. The original continuous CT-AC (CT-org) is referred to as reference. A pseudo MR-AC (CT-mrac), generated from CT data, with four tissue classes and a bone atlas represents the MR-AC. Relative difference in linear attenuation coefficients (LAC) and standardized uptake values were calculated. From the results two improvements regarding soft tissue AC and lung AC were proposed and evaluated.

RESULTS

The overall performance of MR-AC is in good agreement compared to CT-AC. Lungs, heart, and bone tissue were identified as the regions with most deviation to the CT-AC (myocardium -15%, bone tissue -14%, and lungs ±20%). Using single-valued LACs for AC in the lung only provides limited accuracy. For improved soft tissue AC, splitting the combined soft tissue class into muscles and organs each with adapted LAC could reduce the deviations to the CT-AC to < ±1%. For improved lung AC, applying a gradient LAC in the lungs could remarkably reduce over- or undercorrections in PET signal compared to CT-AC (±5%).

CONCLUSIONS

The AC is important to ensure best PET image quality and accurate PET quantification for diagnostics and radiotherapy planning. The optimized segment-based AC proposed in this study, which was evaluated on PET/CT data, inherently reduces quantification bias in normal lung tissue and soft tissue compared to the CT-AC reference.

Ultra-low dose CT scanning for PET/CT

BACKGROUND

The use of computed tomography (CT) for attenuation correction (AC) in whole-body PET/CT can result in a significant contribution to radiation exposure. This can become a limiting factor for reducing considerably the overall radiation exposure of the patient when using the new long axial field of view (LAFOV) PET scanners. However, recent CT technology have introduced features such as the tin (Sn) filter, which can substantially reduce the CT radiation dose.

PURPOSE

The purpose of this study was to investigate the ultra-low dose CT for attenuation correction using the Sn filter together with other dose reduction options such as tube current (mAs) reduction. We explore the impact of dose reduction in the context of AC-CT and how it affects PET image quality.

METHODS

The study evaluated a range of ultra-low dose CT protocols using five physical phantoms that represented a broad collection of tissue electron densities. A long axial field of view (LAFOV) PET/CT scanner was used to scan all phantoms, applying various CT dose reduction parameters such as reducing tube current (mAs), increasing the pitch value, and applying the Sn filter. The effective dose resulting from the CT scans was determined using the CTDIVol reported by the scanner. Several voxel-based and volumes of interest (VOI)-based comparisons were performed to compare the ultra-low dose CT images, the generated attenuation maps, and corresponding PET images against those images acquired with the standard low dose CT protocol. Finally, two patient datasets were acquired using one of the suggested ultra-low dose CT settings.

RESULTS

By incorporating the Sn filter and adjusting mAs to the lowest available value, the radiation dose in CT images of PBU-60 phantom was significantly reduced; resulting in an effective dose of nearly 2% compared to the routine low dose CT protocols currently in clinical use. The assessment of PET images using VOI and voxel-based comparisons indicated relative differences (RD%) of under 6% for mean activity concentration (AC) in the torso phantom and patient dataset and under 8% for a source point in the CIRS phantom. The maximum RD% value of AC was 14% for the point source in the CIRS phantom. Increasing the tube current from 6 mAs to 30 mAs in patients with high BMI, or with arms down, can suppress the photon starvation artifact, whilst still preserving a dose reduction of 90%.

CONCLUSIONS

Introducing a Sn filter in CT imaging lowers radiation dose by more than 90%. This reduction has minimal effect on PET image quantification at least for patients without Body Mass Index (BMI) higher than 30. Notably, this study results need validation using a larger clinical PET/CT dataset in the future, including patients with higher BMI.

Optimisation of the air fraction correction for lung PET/CT: addressing resolution mismatch

BACKGROUND

Increased pulmonary [Formula: see text]F-FDG metabolism in patients with idiopathic pulmonary fibrosis, and other forms of diffuse parenchymal lung disease, can predict measurements of health and lung physiology. To improve PET quantification, voxel-wise air fractions (AF) determined from CT can be used to correct for variable air content in lung PET/CT. However, resolution mismatches between PET and CT can cause artefacts in the AF-corrected image.

METHODS

Three methodologies for determining the optimal kernel to smooth the CT are compared with noiseless simulations and non-TOF MLEM reconstructions of a patient-realistic digital phantom: (i) the point source insertion-and-subtraction method, [Formula: see text]; (ii) AF-correcting with varyingly smoothed CT to achieve the lowest RMSE with respect to the ground truth (GT) AF-corrected volume of interest (VOI), [Formula: see text]; iii) smoothing the GT image to match the reconstruction within the VOI, [Formula: see text]. The methods were evaluated both using VOI-specific kernels, and a single global kernel optimised for the six VOIs combined. Furthermore, [Formula: see text] was implemented on thorax phantom data measured on two clinical PET/CT scanners with various reconstruction protocols.

RESULTS

The simulations demonstrated that at [Formula: see text] iterations (200 i), the kernel width was dependent on iteration number and VOI position in the lung. The [Formula: see text] method estimated a lower, more uniform, kernel width in all parts of the lung investigated. However, all three methods resulted in approximately equivalent AF-corrected VOI RMSEs (<10%) at [Formula: see text]200i. The insensitivity of AF-corrected quantification to kernel width suggests that a single global kernel could be used. For all three methodologies, the computed global kernel resulted in an AF-corrected lung RMSE <10%  at [Formula: see text]200i, while larger lung RMSEs were observed for the VOI-specific kernels. The global kernel approach was then employed with the [Formula: see text] method on measured data. The optimally smoothed GT emission matched the reconstructed image well, both within the VOI and the lung background. VOI RMSE was <10%, pre-AFC, for all reconstructions investigated.

CONCLUSIONS

Simulations for non-TOF PET indicated that around 200i were needed to approach image resolution stability in the lung. In addition, at this iteration number, a single global kernel, determined from several VOIs, for AFC, performed well over the whole lung. The [Formula: see text] method has the potential to be used to determine the kernel for AFC from scans of phantoms on clinical scanners.

Hybrid PET/MR in Cardiac Imaging

In the last few years, technological advances in MR imaging, PET detectors, and attenuation correction algorithms have allowed the creation of truly integrated PET/MR imaging systems, for both clinical and research applications. These machines allow a comprehensive investigation of cardiovascular diseases, by offering a wide variety of detailed anatomical and functional data in combination. Despite significant pathophysiologic mechanisms being clarified by this new data, its clinical relevance and prognostic significance have not been demonstrated yet.

Ultra-low-dose CT for attenuation correction: dose savings and effect on PET quantification for protocols with and without tin filter

BACKGROUND

Ultra-low-dose (ULD) computed tomography (CT) scans should be used when CT is performed only for attenuation correction (AC) of positron emission tomography (PET) data. A tin filter can be used in addition to the standard aluminium bowtie filter to reduce CT radiation dose to patients. The aim was to determine how low CT doses can be, when utilised for PET AC, with and without the tin filter, whilst providing adequate PET quantification.

METHODS

A water-filled NEMA image quality phantom was imaged in three configurations with 18F-FDG: (1) water only (0HU); (2) with cylindrical insert containing homogenous mix of sand, flour and water (SFW, approximately 475HU); (3) with cylindrical insert containing sand (approximately 1100HU). Each underwent one-bed-position (26.3 cm) PET-CT comprising 1 PET and 13 CT acquisitions. CT acquisitions with tube current modulation were performed at 120 kV/50 mAs-ref (reference standard), 100 kV/7 mAs-ref (standard ULDCT for PET AC protocol), Sn140kV (mAs range 7-50-ref) and Sn100kV (mAs range 12-400-ref). PET data were reconstructed with μ-maps provided by each CT dataset, and PET activity concentration measured in each reconstruction. Differences in CT dose length product (DLP) and PET quantification were determined relative to the reference standard.

RESULTS

At each tube voltage, changes in PET quantification were greater with increasing density and reducing mAs. Compared with the reference standard, differences in PET quantification for the standard ULDCT protocol for the three phantoms were ≤ 1.7%, with the water phantom providing a DLP of 7mGy.cm. With tin filter at Sn100kV, differences in PET quantification were negligible (≤ 1.2%) for all phantoms down to 50mAs-ref, proving a DLP of 2.8mGy.cm, at 60% dose reduction compared with standard ULDCT protocol. Below 50mAs-ref, differences in PET quantification were > 2% for at least one phantom (2.3% at 25mAs-ref in SFW; 6.4% at 12mAs-ref in sand). At Sn140kV/7mAs-ref, quantification differences were ≤ 0.6% in water, giving 3.8mGy.cm DLP, but increased to > 2% at bone-equivalent densities.

CONCLUSIONS

CT protocols for PET AC can provide ultra-low doses with adequate PET quantification. The tin filter can allow 60-87% lower dose than the standard ULDCT protocol for PET AC, depending on tissue density and accepted change in PET quantification.

Evaluation of MR anatomically-guided PET reconstruction using a convolutional neural network in PSMA patients

Background. Recently, approaches have utilized the superior anatomical information provided by magnetic resonance imaging (MRI) to guide the reconstruction of positron emission tomography (PET). One of those approaches is the Bowsher's prior, which has been accelerated lately with a convolutional neural network (CNN) to reconstruct MR-guided PET in the imaging domain in routine clinical imaging. Two differently trained Bowsher-CNN methods (B-CNN0 and B-CNN) have been trained and tested on brain PET/MR images with non-PSMA tracers, but so far, have not been evaluated in other anatomical regions yet.Methods. A NEMA phantom with five of its six spheres filled with the same, calibrated concentration of 18F-DCFPyL-PSMA, and thirty-two patients (mean age 64 ± 7 years) with biopsy-confirmed PCa were used in this study. Reconstruction with either of the two available Bowsher-CNN methods were performed on the conventional MR-based attenuation correction (MRAC) and T1-MR images in the imaging domain. Detectable volume of the spheres and tumors, relative contrast recovery (CR), and background variation (BV) were measured for the MRAC and the Bowsher-CNN images, and qualitative assessment was conducted by ranking the image sharpness and quality by two experienced readers.Results. For the phantom study, the B-CNN produced 12.7% better CR compared to conventional reconstruction. The small sphere volume (<1.8 ml) detectability improved from MRAC to B-CNN by nearly 13%, while measured activity was higher than the ground-truth by 8%. The signal-to-noise ratio, CR, and BV were significantly improved (p< 0.05) in B-CNN images of the tumor. The qualitative analysis determined that tumor sharpness was excellent in 76% of the PET images reconstructed with the B-CNN method, compared to conventional reconstruction.Conclusions. Applying the MR-guided B-CNN in clinical prostate PET/MR imaging improves some quantitative, as well as qualitative imaging measures. The measured improvements in the phantom are also clearly translated into clinical application.

A review of PET attenuation correction methods for PET-MR

Despite being thirteen years since the installation of the first PET-MR system, the scanners constitute a very small proportion of the total hybrid PET systems installed. This is in stark contrast to the rapid expansion of the PET-CT scanner, which quickly established its importance in patient diagnosis within a similar timeframe. One of the main hurdles is the development of an accurate, reproducible and easy-to-use method for attenuation correction. Quantitative discrepancies in PET images between the manufacturer-provided MR methods and the more established CT- or transmission-based attenuation correction methods have led the scientific community in a continuous effort to develop a robust and accurate alternative. These can be divided into four broad categories: (i) MR-based, (ii) emission-based, (iii) atlas-based and the (iv) machine learning-based attenuation correction, which is rapidly gaining momentum. The first is based on segmenting the MR images in various tissues and allocating a predefined attenuation coefficient for each tissue. Emission-based attenuation correction methods aim in utilising the PET emission data by simultaneously reconstructing the radioactivity distribution and the attenuation image. Atlas-based attenuation correction methods aim to predict a CT or transmission image given an MR image of a new patient, by using databases containing CT or transmission images from the general population. Finally, in machine learning methods, a model that could predict the required image given the acquired MR or non-attenuation-corrected PET image is developed by exploiting the underlying features of the images. Deep learning methods are the dominant approach in this category. Compared to the more traditional machine learning, which uses structured data for building a model, deep learning makes direct use of the acquired images to identify underlying features. This up-to-date review goes through the literature of attenuation correction approaches in PET-MR after categorising them. The various approaches in each category are described and discussed. After exploring each category separately, a general overview is given of the current status and potential future approaches along with a comparison of the four outlined categories.

ProTheRaMon - a GATE simulation framework for proton therapy range monitoring using PET imaging

OBJECTIVE

This paper reports on the implementation and shows examples of the use of the ProTheRaMon framework for simulating the delivery of proton therapy treatment plans and range monitoring using positron emission tomography (PET). ProTheRaMon offers complete processing of proton therapy treatment plans, patient CT geometries, and intra-treatment PET imaging, taking into account therapy and imaging coordinate systems and activity decay during the PET imaging protocol specific to a given proton therapy facility. We present the ProTheRaMon framework and illustrate its potential use case and data processing steps for a patient treated at the Cyclotron Centre Bronowice (CCB) proton therapy center in Krakow, Poland.

APPROACH

The ProTheRaMon framework is based on GATE Monte Carlo software, the CASToR reconstruction package and in-house developed Python and bash scripts. The framework consists of five separated simulation and data processing steps, that can be further optimized according to the user's needs and specific settings of a given proton therapy facility and PET scanner design.

MAIN RESULTS

ProTheRaMon is presented using example data from a patient treated at CCB and the J-PET scanner to demonstrate the application of the framework for proton therapy range monitoring. The output of each simulation and data processing stage is described and visualized.

SIGNIFICANCE

We demonstrate that the ProTheRaMon simulation platform is a high-performance tool, capable of running on a computational cluster and suitable for multi-parameter studies, with databases consisting of large number of patients, as well as different PET scanner geometries and settings for range monitoring in a clinical environment. Due to its modular structure, the ProTheRaMon framework can be adjusted for different proton therapy centers and/or different PET detector geometries. It is available to the community via github.

Intra-Individual Comparison of 124I-PET/CT and 124I-PET/MR Hybrid Imaging of Patients with Resected Differentiated Thyroid Carcinoma: Aspects of Attenuation Correction

Simple Summary

This study evaluates the qualitative and quantitative differences between 124-iodine PET/CT and PET/MR in oncologic patients with differentiated thyroid carcinoma after thyroidectomy. The impact of improved MR-based attenuation correction (AC) using a bone atlas was analysed in PET/MR data. Despite different patient positioning and AC methods PET/CT and PET/MR provide overall comparable results in a clinical setting. The overall number of detected ¹²⁴I-active lesions and the measured average SUV_mean values for congruent lesions were higher for PET/MR when compared to PET/CT. The addition of bone to the MR-based AC in PET/MR slightly increased the SUV_mean values for all detected lesions.

Abstract

Background: This study evaluates the quantitative differences between 124-iodine (I) positron emission tomography/computed tomography (PET/CT) and PET/magnetic resonance imaging (PET/MR) in patients with resected differentiated thyroid carcinoma (DTC). Methods: N = 43 ¹²⁴I PET/CT and PET/MR exams were included. CT-based attenuation correction (AC) in PET/CT and MR-based AC in PET/MR with bone atlas were compared concerning bone AC in the head-neck region. AC-map artifacts (e.g., dentures) were noted. Standardized uptake values (SUV) were measured in lesions in each PET data reconstruction. Relative differences in SUV_mean were calculated between PET/CT and PET/MR with bone atlas. Results: Overall, n = 111 ¹²⁴I-avid lesions were detected in all PET/CT, while n = 132 lesions were detected in PET/MR. The median in SUV_mean for n = 98 congruent lesions measured in PET/CT was 12.3. In PET/MR, the median in SUV_mean was 16.6 with bone in MR-based AC. Conclusions: ¹²⁴I-PET/CT and ¹²⁴I-PET/MR hybrid imaging of patients with DTC after thyroidectomy provides overall comparable quantitative results in a clinical setting despite different patient positioning and AC methods. The overall number of detected ¹²⁴I-avid lesions was higher for PET/MR compared to PET/CT. The measured average SUV_mean values for congruent lesions were higher for PET/MR.

Relating18F-FDG image signal-to-noise ratio to time-of-flight noise-equivalent count rate in total-body PET using the uEXPLORER scanner

Objective.This work assessed the relationship between image signal-to-noise ratio (SNR) and total-body noise-equivalent count rate (NECR)-for both non-time-of-flight (TOF) NECR and TOF-NECR-in a long uniform water cylinder and 14 healthy human subjects using the uEXPLORER total-body PET/CT scanner.Approach.A TOF-NEC expression was modified for list-mode PET data, and both the non-TOF NECR and TOF-NECR were compared using datasets from a long uniform water cylinder and 14 human subjects scanned up to 12 h after radiotracer injection.Main results.The TOF-NECR for the uniform water cylinder was found to be linearly proportional to the TOF-reconstructed image SNR²in the range of radioactivity concentrations studied, but not for non-TOF NECR as indicated by the reducedR²value. The results suggest that the use of TOF-NECR to estimate the count rate performance of TOF-enabled PET systems may be more appropriate for predicting the SNR of TOF-reconstructed images.Significance.Image quality in PET is commonly characterized by image SNR and, correspondingly, the NECR. While the use of NECR for predicting image quality in conventional PET systems is well-studied, the relationship between SNR and NECR has not been examined in detail in long axial field-of-view total-body PET systems, especially for human subjects. Furthermore, the current NEMA NU 2-2018 standard does not account for count rate performance gains due to TOF in the NECR evaluation. The relationship between image SNR and total-body NECR in long axial FOV PET was assessed for the first time using the uEXPLORER total-body PET/CT scanner.

Deep learning for Dixon MRI-based attenuation correction in PET/MRI of head and neck cancer patients

Background

Quantitative whole-body PET/MRI relies on accurate patient-specific MRI-based attenuation correction (AC) of PET, which is a non-trivial challenge, especially for the anatomically complex head and neck region. We used a deep learning model developed for dose planning in radiation oncology to derive MRI-based attenuation maps of head and neck cancer patients and evaluated its performance on PET AC.

Methods

Eleven head and neck cancer patients, referred for radiotherapy, underwent CT followed by PET/MRI with acquisition of Dixon MRI. Both scans were performed in radiotherapy position. PET AC was performed with three different patient-specific attenuation maps derived from: (1) Dixon MRI using a deep learning network (PET_Deep). (2) Dixon MRI using the vendor-provided atlas-based method (PET_Atlas). (3) CT, serving as reference (PET_CT). We analyzed the effect of the MRI-based AC methods on PET quantification by assessing the average voxelwise error within the entire body, and the error as a function of distance to bone/air. The error in mean uptake within anatomical regions of interest and the tumor was also assessed.

Results

The average (± standard deviation) PET voxel error was 0.0 ± 11.4% for PET_Deep and −1.3 ± 21.8% for PET_Atlas. The error in mean PET uptake in bone/air was much lower for PET_Deep (−4%/12%) than for PET_Atlas (−15%/84%) and PET_Deep also demonstrated a more rapidly decreasing error with distance to bone/air affecting only the immediate surroundings (less than 1 cm). The regions with the largest error in mean uptake were those containing bone (mandible) and air (larynx) for both methods, and the error in tumor mean uptake was −0.6 ± 2.0% for PET_Deep and −3.5 ± 4.6% for PET_Atlas.

Conclusion

The deep learning network for deriving MRI-based attenuation maps of head and neck cancer patients demonstrated accurate AC and exceeded the performance of the vendor-provided atlas-based method both overall, on a lesion-level, and in vicinity of challenging regions such as bone and air.

Technical Note: A PET/MR coil with an integrated, orbiting 511 keV transmission source for PET/MR imaging validated in an animal study

Background

Purpose

Methods

Results

Conclusion

MR-based truncation correction using an advanced HUGE method to improve attenuation correction in PET/MR imaging of obese patients

PURPOSE

Truncation artifacts in the periphery of the magnetic resonance (MR) field-of-view (FOV) and thus, in the MR-based attenuation correction (AC) map, may hamper accurate positron emission tomography (PET) quantification in whole-body PET/MR, which is especially problematic in patients with obesity with overall large body dimensions. Therefore, an advanced truncation correction (TC) method to extend the conventional MR FOV is needed.

METHODS

The extent of MR-based AC-map truncations in obese patients was determined in a data set including n  =  10 patients that underwent whole-body PET/MR exams. Patient inclusion criteria were defined as BMI > 30 kg/m² and body weight > 100 kg. Truncations in PET/MR patients with obesity were quantified comparing the MR-based AC-map volume to segmented non-AC PET data, serving as the reference body volume without truncations to demonstrate the need of improved TC. The new method implemented in this study, termed "advanced HUGE", was modified and extended from the original HUGE method by Blumhagen et al. in order to provide improved TC across the entire axial MR FOV and to unlock new clinical applications of PET/MR. Advanced HUGE was then systematically tested in PET/MR NEMA phantom measurements. Relative differences between computed tomography (CT) AC PET data of the phantom setup (reference) and MR-based Dixon AC, respectively Dixon + advanced HUGE AC, were calculated. The applicability of the method for advanced TC was then demonstrated in first MR-based measurements in healthy volunteers.

RESULTS

It was found that the MR-based AC maps of obese patients often reveal truncations in anterior-posterior direction. Especially the abdominal region could benefit from improved TC, where maximal relative differences in the AC-map volume up to -17 % were calculated. Applying advanced HUGE to improve the MR-based AC in PET/MR, PET quantification errors in the large-volume phantom setup could be considerably reduced from average -18.6 % (Dixon AC) to 4.6 % compared to the CT AC reference. Volunteer measurements demonstrate that formerly missing AC-map volume in the Dixon-VIBE AC-map could be added due to advanced HUGE in anterior-posterior direction and thus, potentially improves AC in PET/MR.

CONCLUSIONS

The advanced HUGE method for truncation correction considerably reduces truncations in anterior-posterior direction demonstrated in phantom measurements and healthy volunteers and thus, further improves MR-based AC in PET/MR imaging. This article is protected by copyright. All rights reserved.

Lesion detection in 18F-sodium fluoride bone imaging: a comparison of attenuation-corrected versus nonattenuation-corrected PET reconstructions from modern PET-CT systems

OBJECTIVES

An earlier study demonstrated comparable lesion detection between attenuation-corrected (AC) and nonattenuation-corrected (NAC) 18F-sodium fluoride (NaF) PET images, which is relevant for computed tomography (CT) radiation dose-saving. However, this finding may not be applicable to newer systems. The aim was to compare lesion detection between AC and NAC NaF PET images on modern PET-CT systems.

METHODS

One expert and one nonexpert observer retrospectively surveyed NaF PET data in 25 breast cancer patients. At both lesion and patient level, each observer classified bone abnormalities as malignant, equivocal or benign, from NAC and AC PET images in the absence of CT. Expert interpretation of NaF PET-CT with the review of all diagnostic imaging/pathology reports for at least the subsequent 12 months provided reference standard metastases status at the patient level. Two-tailed Wilcoxon signed-rank tests measured statistically significant differences in total lesion detection between AC and NAC PET. Quadratic-weighted kappa score measured agreement in patient metastases status between observers.

RESULTS

On a lesion-basis, AC PET images showed significantly more lesions than NAC for both the expert (122 versus 96; P = 0.002) and nonexpert (146 versus 132; P = 0.036) observers, with a large number of patients demonstrating disparity between AC and NAC images. For metastases status at the patient level without CT, NAC PET showed slightly better diagnostic accuracy than AC due to fewer false-positive results, as fewer lesions were identified.

CONCLUSION

AC PET data provided superior lesion detection to NAC in NaF bone examinations and are thus required for clinical interpretation.

Can a ToF-PET photon attenuation reconstruction test stopping-power estimations in proton therapy? A phantom study

Objective. The aim of the phantom study was to validate and to improve the computed tomography (CT) images used for the dose computation in proton therapy. It was tested, if the joint reconstruction of activity and attenuation images of time-of-flight PET (ToF-PET) scans could improve the estimation of the proton stopping-power.Approach. The attenuation images, i.e. CT images with 511 keV gamma-rays (γCTs), were jointly reconstructed with activity maps from ToF-PET scans. Theβ⁺activity was produced with FDG and in a separate experiment with proton-induced radioactivation. The phantoms contained slabs of tissue substitutes. The use of theγCTs for the prediction of the beam stopping in proton therapy was based on a linear relationship between theγ-ray attenuation, the electron density, and the stopping-power of fast protons.Main results. The FDG based experiment showed sufficient linearity to detect a bias of bony tissue in the heuristic look-up table, which maps between x-ray CT images and proton stopping-power.γCTs can be used for dose computation, if the electron density of one type of tissue is provided as a scaling factor. A possible limitation is imposed by the spatial resolution, which is inferior by a factor of 2.5 compared to the one of the x-ray CT.γCTs can also be derived from off-line, ToF-PET scans subsequent to the application of a proton field with a hypofractionated dose level.Significance. γCTs are a viable tool to support the estimation of proton stopping with radiotracer-based ToF-PET data from diagnosis or staging. This could be of higher potential relevance in MRI-guided proton therapy.γCTs could form an alternative approach to make use of in-beam or off-line PET scans of proton-inducedβ⁺activity with possible clinical limitations due to the low number of coincidence counts.

CAD-based hardware attenuation correction in PET/MRI: First methodical investigations and clinical application of a 16-channel RF breast coil

PURPOSE

Aim of this study was to evaluate the use of computer-aided design (CAD) models for attenuation correction (AC) of hardware components in positron emission tomography/magnetic resonance (PET/MR) imaging.

METHODS

The technical feasibility and quantitative impact of CAD-AC compared to computer tomography (CT)-based AC (reference) was investigated on a modular phantom consisting of 19 different material samples (plastics and metals arranged around a cylindrical emission phantom) typically used in phantoms, patient tables, and radiofrequency (RF) coils in PET/MR. The clinical applicability of the CAD-AC method was then evaluated on a 16-channel RF breast coil in a PET/MR patient study. The RF breast coil in this study was specifically designed PET compatible. Using this RF breast coil, the impact on clinical PET/MR breast imaging was systematically evaluated in breast phantom measurements and, furthermore, in n = 10 PET/MR patients with breast cancer. PET data were reconstructed three times: (1) no AC (NAC), (2) established CT-AC, and (3) CAD-AC. For both phantom measurements, a scan without attenuating hardware components (material probes or RF breast coil) was acquired serving as reference. Relative differences in PET data were calculated for all experiments.

RESULTS

In all phantom and patient measurements, significant gains in PET signal compared to NAC data were measurable with CT and CAD-AC. In initial phantom experiments, mean relative differences of -0.2% for CT-AC and 0.2% for CAD-AC were calculated compared to reference measurements without the material probes. The application to a RF breast coil depicts that CAD-AC results in significant gains compared to NAC data (10%) and a slight underestimation in PET signal of -1.3% in comparison to the no-coil reference measurement. In the patient study, a total of 15 congruent lesions in all 10 patients with a mean relative difference of 14% (CT and CAD-AC) in standardized uptake value compared to NAC data could be detected.

CONCLUSIONS

To ensure best possible PET image quality and accurate PET quantification in PET/MR imaging, the AC of hardware components such as phantoms and RF coils is important. In initial phantom experiments and in clinical application to an RF breast coil, it was found that CAD-based AC results in significant gains in PET signal compared to NAC data and provides comparably good results to the established method of CT-based AC.

Robustness and Generalizability of Deep Learning Synthetic Computed Tomography for Positron Emission Tomography/Magnetic Resonance Imaging-Based Radiation Therapy Planning of Patients With Head and Neck Cancer

Purpose

Radiotherapy planning based only on positron emission tomography/magnetic resonance imaging (PET/MRI) lacks computed tomography (CT) information required for dose calculations. In this study, a previously developed deep learning model for creating synthetic CT (sCT) from MRI in patients with head and neck cancer was evaluated in 2 scenarios: (1) using an independent external dataset, and (2) using a local dataset after an update of the model related to scanner software-induced changes to the input MRI.

Methods and Materials

Six patients from an external site and 17 patients from a local cohort were analyzed separately. Each patient underwent a CT and a PET/MRI with a Dixon MRI sequence over either one (external) or 2 (local) bed positions. For the external cohort, a previously developed deep learning model for deriving sCT from Dixon MRI was directly applied. For the local cohort, we adapted the model for an upgraded MRI acquisition using transfer learning and evaluated it in a leave-one-out process. The sCT mean absolute error for each patient was assessed. Radiotherapy dose plans based on sCT and CT were compared by assessing relevant absorbed dose differences in target volumes and organs at risk.

Results

The MAEs were 78 ± 13 HU and 76 ± 12 HU for the external and local cohort, respectively. For the external cohort, absorbed dose differences in target volumes were within ± 2.3% and within ± 1% in 95% of the cases. Differences in organs at risk were <2%. Similar results were obtained for the local cohort.

Conclusions

We have demonstrated a robust performance of a deep learning model for deriving sCT from MRI when applied to an independent external dataset. We updated the model to accommodate a larger axial field of view and software-induced changes to the input MRI. In both scenarios dose calculations based on sCT were similar to those of CT suggesting a robust and reliable method.

MRI-guided attenuation correction in torso PET/MRI: Assessment of segmentation-, atlas-, and deep learning-based approaches in the presence of outliers

Purpose

We compare the performance of three commonly used MRI‐guided attenuation correction approaches in torso PET/MRI, namely segmentation‐, atlas‐, and deep learning‐based algorithms.

Methods

Twenty‐five co‐registered torso ¹⁸F‐FDG PET/CT and PET/MR images were enrolled. PET attenuation maps were generated from in‐phase Dixon MRI using a three‐tissue class segmentation‐based approach (soft‐tissue, lung, and background air), voxel‐wise weighting atlas‐based approach, and a residual convolutional neural network. The bias in standardized uptake value (SUV) was calculated for each approach considering CT‐based attenuation corrected PET images as reference. In addition to the overall performance assessment of these approaches, the primary focus of this work was on recognizing the origins of potential outliers, notably body truncation, metal‐artifacts, abnormal anatomy, and small malignant lesions in the lungs.

Results

The deep learning approach outperformed both atlas‐ and segmentation‐based methods resulting in less than 4% SUV bias across 25 patients compared to the segmentation‐based method with up to 20% SUV bias in bony structures and the atlas‐based method with 9% bias in the lung. The deep learning‐based method exhibited superior performance. Yet, in case of sever truncation and metallic‐artifacts in the input MRI, this approach was outperformed by the atlas‐based method, exhibiting suboptimal performance in the affected regions. Conversely, for abnormal anatomies, such as a patient presenting with one lung or small malignant lesion in the lung, the deep learning algorithm exhibited promising performance compared to other methods.

Conclusion

The deep learning‐based method provides promising outcome for synthetic CT generation from MRI. However, metal‐artifact and body truncation should be specifically addressed.

The impact of MR-based attenuation correction in spinal cord FDG-PET/MR imaging for neurological studies

Purpose

Positron emission tomography (PET) attenuation correction (AC) in positron emission tomography‐magnetic resonance (PET/MR) scanners constitutes a critical and barely explored issue in spinal cord investigation, mainly due to the limitations in accounting for highly attenuating bone structures which surround the spinal canal. Our study aims at evaluating the clinical suitability of MR‐driven AC (MRAC) for 18‐fluorodeoxy‐glucose positron emission tomography (¹⁸F‐FDG‐PET) in spinal cord.

Methods

Thirty‐six patients, undergoing positron emission tomography‐computed tomography (PET/CT) and PET/MR in the same session for oncological examination, were retrospectively analyzed.

For each patient, raw PET data from PET/MR scanner were reconstructed with 4‐ and 5‐class MRAC maps, generated by hybrid PET/MR system (PET_MRAC4 and PET_MRAC5, respectively, where PET_MRAC is PET images reconstructed using MR‐based attenuation correction map), and an AC map derived from CT data after a custom co‐registration pipeline (PET_rCTAC, where PET_rCTAC is PET images reconstructed using CT‐based attenuation correction map), which served as reference. Mean PET standardized uptake values (SUVm) were extracted from the three reconstructed PET images by regions of interest (ROIs) identified on T2‐weighted MRI, in the spinal cord, lumbar cerebrospinal fluid (CSF), and vertebral marrow at five levels (C2, C5, T6, T12, and L3). SUVm values from PET_MRAC4 and PET_MRAC5 were compared with each other and with the reference by means of paired t‐test, and correlated using Pearson's correlation (r) to assess their consistency. Cohen's d was calculated to assess the magnitude of differences between PET images.

Results

SUVmvalues from PET_MRAC4 were lower than those from PET_MRAC5 in almost all analyzed ROIs, with a mean difference ranging from 0.03 to 0.26 (statistically significant in the vertebral marrow at C2 and C5, spinal cord at T6 and T2, and CSF at L3). This was also confirmed by the effect size, with highest values at low spinal levels (d = 0.45 at T12 in spinal cord, d = 0.95 at L3 in CSF). SUVm values from PET_MRAC4 and PET_MRAC5 showed a very good correlation (0.81 < r < 0.97, p < 0.05) in all spinal ROIs. Underestimation of SUVm between PET_MRAC4 and PET_rCTAC was observed at each level, with a mean difference ranging from 0.02 to 0.32 (statistically significant in the vertebral marrow at C2 and T6, and CSF at L3). Although PET_MRAC5 underestimates PET_rCTAC (mean difference ranging from 0.02 to 0.3), an overall decrease in effect size could be observed for PET_MRAC5, mainly at lower spinal levels (T12, L3). SUVm from both PET_MRAC4 and PET_MRAC5 methods showed r value from good to very good with respect to PET_rCTAC (0.67 < r < 0.9 and 0.73 < r < 0.94, p < 0.05, respectively).

Conclusions

Our results showed that neglecting bones in AC can underestimate the FDG uptake measurement of the spinal cord. The inclusion of bones in MRAC is far from negligible and improves the AC in spinal cord, mainly at low spinal levels. Therefore, care must be taken in the spinal canal region, and the use of AC map reconstruction methods accounting for bone structures could be beneficial.

Toward PET/MRI as one-stop shop for radiotherapy planning in cervical cancer patients

BACKGROUND

Radiotherapy (RT) planning for cervical cancer patients entails the acquisition of both Computed Tomography (CT) and Magnetic Resonance Imaging (MRI). Further, molecular imaging by Positron Emission Tomography (PET) could contribute to target volume delineation as well as treatment response monitoring. The objective of this study was to investigate the feasibility of a PET/MRI-only RT planning workflow of patients with cervical cancer. This includes attenuation correction (AC) of MRI hardware and dedicated positioning equipment as well as evaluating MRI-derived synthetic CT (sCT) of the pelvic region for positioning verification and dose calculation to enable a PET/MRI-only setup.

MATERIAL AND METHODS

16 patients underwent PET/MRI using a dedicated RT setup after the routine CT (or PET/CT), including eight pilot patients and eight cervical cancer patients who were subsequently referred for RT. Data from 18 patients with gynecological cancer were added for training a deep convolutional neural network to generate sCT from Dixon MRI. The mean absolute difference between the dose distributions calculated on sCT and a reference CT was measured in the RT target volume and organs at risk. PET AC by sCT and a reference CT were compared in the tumor volume.

RESULTS

All patients completed the examination. sCT was inferred for each patient in less than 5 s. The dosimetric analysis of the sCT-based dose planning showed a mean absolute error (MAE) of 0.17 ± 0.12 Gy inside the planning target volumes (PTV). PET images reconstructed with sCT and CT had no significant difference in quantification for all patients.

CONCLUSIONS

These results suggest that multiparametric PET/MRI can be successfully integrated as a one-stop-shop in the RT workflow of patients with cervical cancer.

Pitfalls on PET/CT Due to Artifacts and Instrumentation

PET/CT has become a preferred imaging modality over PET-only scanners in clinical practice. However, along with the significant improvement in diagnostic accuracy and patient throughput, pitfalls on PET/CT are reported as well. This review provides a general overview on the potential influence of the limitations with respect to PET/CT instrumentation and artifacts associated with the modality integration on the image appearance and quantitative accuracy of PET. Approaches proposed in literature to address the limitations or minimize the artifacts are discussed as well as their current challenges for clinical applications. Although the CT component can play an important role in assisting clinical diagnosis, we concentrate on the imaging scenarios where CT is used to provide auxiliary information for attenuation compensation and scatter correction in PET.

Deep learning-based T1-enhanced selection of linear attenuation coefficients (DL-TESLA) for PET/MR attenuation correction in dementia neuroimaging

PURPOSE

The accuracy of existing PET/MR attenuation correction (AC) has been limited by a lack of correlation between MR signal and tissue electron density. Based on our finding that longitudinal relaxation rate, or R1 , is associated with CT Hounsfield unit in bone and soft tissues in the brain, we propose a deep learning T1 -enhanced selection of linear attenuation coefficients (DL-TESLA) method to incorporate quantitative R1 for PET/MR AC and evaluate its accuracy and longitudinal test-retest repeatability in brain PET/MR imaging.

METHODS

DL-TESLA uses a 3D residual UNet (ResUNet) for pseudo-CT (pCT) estimation. With a total of 174 participants, we compared PET AC accuracy of DL-TESLA to 3 other methods adopting similar 3D ResUNet structures but using UTE R 2 ∗ , or Dixon, or T1 -MPRAGE as input. With images from 23 additional participants repeatedly scanned, the test-retest differences and within-subject coefficient of variation of standardized uptake value ratios (SUVR) were compared between PET images reconstructed using either DL-TESLA or CT for AC.

RESULTS

DL-TESLA had (1) significantly lower mean absolute error in pCT, (2) the highest Dice coefficients in both bone and air, (3) significantly lower PET relative absolute error in whole brain and various brain regions, (4) the highest percentage of voxels with a PET relative error within both ±3% and ±5%, (5) similar to CT test-retest differences in SUVRs from the cerebrum and mean cortical (MC) region, and (6) similar to CT within-subject coefficient of variation in cerebrum and MC.

CONCLUSION

DL-TESLA demonstrates excellent PET/MR AC accuracy and test-retest repeatability.

Deep learning for whole-body medical image generation

BACKGROUND

Artificial intelligence (AI) algorithms based on deep convolutional networks have demonstrated remarkable success for image transformation tasks. State-of-the-art results have been achieved by generative adversarial networks (GANs) and training approaches which do not require paired data. Recently, these techniques have been applied in the medical field for cross-domain image translation.

PURPOSE

This study investigated deep learning transformation in medical imaging. It was motivated to identify generalizable methods which would satisfy the simultaneous requirements of quality and anatomical accuracy across the entire human body. Specifically, whole-body MR patient data acquired on a PET/MR system were used to generate synthetic CT image volumes. The capacity of these synthetic CT data for use in PET attenuation correction (AC) was evaluated and compared to current MR-based attenuation correction (MR-AC) methods, which typically use multiphase Dixon sequences to segment various tissue types.

MATERIALS AND METHODS

This work aimed to investigate the technical performance of a GAN system for general MR-to-CT volumetric transformation and to evaluate the performance of the generated images for PET AC. A dataset comprising matched, same-day PET/MR and PET/CT patient scans was used for validation.

RESULTS

A combination of training techniques was used to produce synthetic images which were of high-quality and anatomically accurate. Higher correlation was found between the values of mu maps calculated directly from CT data and those derived from the synthetic CT images than those from the default segmented Dixon approach. Over the entire body, the total amounts of reconstructed PET activities were similar between the two MR-AC methods, but the synthetic CT method yielded higher accuracy for quantifying the tracer uptake in specific regions.

CONCLUSION

The findings reported here demonstrate the feasibility of this technique and its potential to improve certain aspects of attenuation correction for PET/MR systems. Moreover, this work may have larger implications for establishing generalized methods for inter-modality, whole-body transformation in medical imaging. Unsupervised deep learning techniques can produce high-quality synthetic images, but additional constraints may be needed to maintain medical integrity in the generated data.

Validation of CARE kV automated tube voltage selection for PET-CT: PET quantification and CT radiation dose reduction in phantoms

Background

Applied tube voltage (kilovolts, kV) and tube current (milliampere seconds, mAs) affect CT radiation dose and image quality and should be optimised for the individual patient. CARE kV determines the kV and mAs providing the lowest dose to the patient, whilst maintaining user-defined reference image quality. Given that kV changes affect CT values which are used to obtain attenuation maps, the aim was to evaluate the effect of kV changes on PET quantification and CT radiation dose using phantoms.

Method

Four phantoms (‘Lungman’, ‘Lungman plus fat’, ‘Esser’ and ‘NEMA image quality’ (NEMA IQ)) containing F-18 sources underwent 1 PET and 5 CT scans, with CARE kV on (automatic kV selection and mAs modulation) and in semi mode with specified tube voltages of 140, 120, 100 and 80 kV (mAs modulation only). A CARE kV image quality reference of 120 kV/50 mAs was used. Impact on PET quantification was determined by comparing measured activity concentrations for PET reconstructions from different CT scans with the reconstruction using the 120 kV reference, and dose (DLP, CTDI_vol) differences calculated by comparing doses from all kV settings with the 120 kV reference.

Results

CARE kV-determined optimal tube voltage and CARE kV ‘on’ dose (DLP) savings compared with the 120 kV reference were: Lungman, 100 kV, 2.0%; Lungman plus fat, 120 kV, 0%; Esser, 100 kV, 9.3%; NEMA IQ, 100 kV, 3.4%. Using tube voltages in CARE kV ‘semi’ mode which were not advised by CARE kV ‘on’ resulted in dose increases ≤ 65% compared with the 120 kV reference (greatest difference Lungman plus fat, 80 kV). Clinically insignificant differences in PET activity quantification of up to 0.7% (Lungman, 100 kV, mean measured activity concentration) were observed when using the optimal tube voltage advised by CARE kV. Differences in PET quantification of up to 4.0% (Lungman, 140 kV, maximum measured activity concentration) were found over the full selection of tube voltages in semi mode, with the greatest differences seen at the most suboptimal kV for each phantom. However, most differences were within 1%.

Conclusions

CARE kV on can provide CT radiation dose savings without concern over changes in PET quantification.

Improved PET/MRI accuracy by use of static transmission source in empirically derived hardware attenuation correction

Background

Accurate quantification of radioactivity, measured by an integrated positron emission tomography (PET) and magnetic resonance imaging (MRI) system, is still a challenge. One aspect of such a challenge is to correct for the hardware attenuation, such as the patient table and radio frequency (RF) resonators. For PET/MRI systems, computed tomography (CT) is commonly used to produce hardware attenuation correction (AC) maps, by converting Hounsfield units (HU) to a linear attenuation coefficients (LAC) map at the PET energy level 511 keV, using a bilinear model. The model does not address beam hardening, nor higher density materials, which can lead to inaccurate corrections.

Purpose

In this study, we introduce a transmission-based (TX-based) AC technique with a static Germanium-68 (Ge-68) transmission source to generate hardware AC maps using the PET/MRI system itself, without the need for PET or medical CT scanners. The AC TX-based maps were generated for a homogeneous cylinder, made of acrylic as a validator. The technique thereafter was applied to the patient table and posterior part of an RF-phased array used in cardiovascular PET/MRI imaging. The proposed TX-based, and the CT-based, hardware maps were used in reconstructing PET images of one cardiac patient, and the results were analysed and compared.

Results

The LAC derived by the TX-based method for the acrylic cylinder is estimated to be 0.10851 ± 0.00380 cm⁻¹ compared to the 0.10698 ± 0.00321 cm⁻¹ theoretical value reported in the literature. The PET photon counts were reduced by 8.7 ± 1.1% with the patient table, at the region used in cardiac scans, while the CT-based map, used for correction, over-estimated counts by 4.3 ± 1.3%. Reconstructed in vivo images using TX-based AC hardware maps have shown 4.1 ± 0.9% mean difference compared to those reconstructed images using CT-based AC.

Conclusions

The LAC of the acrylic cylinder measurements using the TX-based technique was in agreement with those in the literature confirming the validity of the technique. The over-estimation of photon counts caused by the CT-based model used for the patient table was improved by the TX-based technique. Therefore, TX-based AC of hardware using the PET/MRI system itself is possible and can produce more accurate images when compared to the CT-based hardware AC in cardiac PET images.

MR-based Attenuation Correction for Brain PET Using 3D Cycle-Consistent Adversarial Network

Attenuation correction (AC) is important for the quantitative merits of positron emission tomography (PET). However, attenuation coefficients cannot be derived from magnetic resonance (MR) images directly for PET/MR systems. In this work, we aimed to derive continuous AC maps from Dixon MR images without the requirement of MR and computed tomography (CT) image registration. To achieve this, a 3D generative adversarial network with both discriminative and cycle-consistency loss (Cycle-GAN) was developed. The modified 3D U-net was employed as the structure of the generative networks to generate the pseudo CT/MR images. The 3D patch-based discriminative networks were used to distinguish the generated pseudo CT/MR images from the true CT/MR images. To evaluate its performance, datasets from 32 patients were used in the experiment. The Dixon segmentation and atlas methods provided by the vendor and the convolutional neural network (CNN) method which utilized registered MR and CT images were employed as the reference methods. Dice coefficients of the pseudo-CT image and the regional quantification in the reconstructed PET images were compared. Results show that the Cycle-GAN framework can generate better AC compared to the Dixon segmentation and atlas methods, and shows comparable performance compared to the CNN method.

Standard MRI-based attenuation correction for PET/MRI phantoms: a novel concept using MRI-visible polymer

Background

PET/MRI phantom studies are challenged by the need of phantom-specific attenuation templates to account for attenuation properties of the phantom material. We present a PET/MRI phantom built from MRI-visible material for which attenuation correction (AC) can be performed using the standard MRI-based AC.

Methods

A water-fillable phantom was 3D-printed with a commercially available MRI-visible polymer. The phantom had a cylindrical shape and the fillable compartment consisted of a homogeneous region and a region containing solid rods of different diameters. The phantom was filled with a solution of water and [18F]FDG. A 30 min PET/MRI acquisition including the standard Dixon-based MR-AC method was performed. In addition, a CT scan of the phantom was acquired on a PET/CT system.

From the Dixon in-phase, opposed-phase and fat images, a phantom-specific AC map (Phantom MR-AC) was produced by separating the phantom material from the water compartment using a thresholding-based method and assigning fixed attenuation coefficients to the individual compartments. The PET data was reconstructed using the Phantom MR-AC, the original Dixon MR-AC, and an MR-AC just containing the water compartment (NoWall-AC) to estimate the error of ignoring the phantom walls. CT-based AC was employed as the reference standard. Average %-differences in measured activity between the CT corrected PET and the PET corrected with the other AC methods were calculated.

Results

The phantom housing and the liquid compartment were both visible and distinguishable from each other in the Dixon images and allowed the segmentation of a phantom-specific MR-based AC. Compared to the CT-AC PET, average differences in measured activity in the whole water compartment in the phantom of −0.3%, 9.4%, and −24.1% were found for Dixon phantom MR-AC, MR-AC, and NoWall-AC based PET, respectively. Average differences near the phantom wall in the homogeneous region were −0.3%, 6.6%, and −34.3%, respectively. Around the rods, activity differed from the CT-AC PET by 0.7%, 8.9%, and −45.5%, respectively.

Conclusion

The presented phantom material is visible using standard MR sequences, and thus, supports the use of standard, phantom-independent MR measurements for MR-AC in PET/MRI phantom studies.

An evaluation of the diagnostic equivalence of 18F-FDG-PET between hybrid PET/MRI and PET/CT in drug-resistant epilepsy: A pilot study

OBJECTIVE

Hybrid PET/MRI may improve detection of seizure-onset zone (SOZ) in drug-resistant epilepsy (DRE), however, concerns over PET bias from MRI-based attenuation correction (MRAC) have limited clinical adoption of PET/MRI. This study evaluated the diagnostic equivalency and potential clinical value of PET/MRI against PET/CT in DRE.

MATERIALS AND METHODS

MRI, FDG-PET and CT images (n = 18) were acquired using a hybrid PET/MRI and a CT scanner. To assess diagnostic equivalency, PET was reconstructed using MRAC (RESOLUTE) and CT-based attenuation correction (CTAC) to generate PET/MRI and PET/CT images, respectively. PET/MRI and PET/CT images were compared qualitatively through visual assessment and quantitatively through regional standardized uptake value (SUV) and z-score assessment. Diagnostic accuracy and sensitivity of PET/MRI and PET/CT for SOZ detection were calculated through comparison to reference standards (clinical hypothesis and histopathology, respectively).

RESULTS

Inter-reader agreement in visual assessment of PET/MRI and PET/CT images was 78 % and 81 %, respectively. PET/MRI and PET/CT were strongly correlated in mean SUV (r = 0.99, p < 0.001) and z-scores (r = 0.92, p < 0.001) across all brain regions. MRAC SUV bias was <5% in most brain regions except the inferior temporal gyrus, temporal pole, and cerebellum. Diagnostic accuracy and sensitivity were similar between PET/MRI and PET/CT (87 % vs. 85 % and 83 % vs. 83 %, respectively).

CONCLUSION

We demonstrate here that PET/MRI with optimal MRAC can yield similar diagnostic performance as PET/CT. Nevertheless, further exploration of the potential added value of PET/MRI is necessary before clinical adoption of PET/MRI for epilepsy imaging.

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.

Accuracy and precision of zero-echo-time, single- and multi-atlas attenuation correction for dynamic [11C]PE2I PET-MR brain imaging

BACKGROUND

A valid photon attenuation correction (AC) method is instrumental for obtaining quantitatively correct PET images. Integrated PET/MR systems provide no direct information on attenuation, and novel methods for MR-based AC (MRAC) are still under investigation. Evaluations of various AC methods have mainly focused on static brain PET acquisitions. In this study, we determined the validity of three MRAC methods in a dynamic PET/MR study of the brain.

METHODS

Nine participants underwent dynamic brain PET/MR scanning using the dopamine transporter radioligand [11C]PE2I. Three MRAC methods were evaluated: single-atlas (Atlas), multi-atlas (MaxProb) and zero-echo-time (ZTE). The 68Ge-transmission data from a previous stand-alone PET scan was used as reference method. Parametric relative delivery (R1) images and binding potential (BPND) maps were generated using cerebellar grey matter as reference region. Evaluation was based on bias in MRAC maps, accuracy and precision of [11C]PE2I BPND and R1 estimates, and [11C]PE2I time-activity curves. BPND was examined for striatal regions and R1 in clusters of regions across the brain.

RESULTS

For BPND, ZTE-MRAC showed the highest accuracy (bias < 2%) in striatal regions. Atlas-MRAC exhibited a significant bias in caudate nucleus (- 12%) while MaxProb-MRAC revealed a substantial, non-significant bias in the putamen (9%). R1 estimates had a marginal bias for all MRAC methods (- 1.0-3.2%). MaxProb-MRAC showed the largest intersubject variability for both R1 and BPND. Standardized uptake values (SUV) of striatal regions displayed the strongest average bias for ZTE-MRAC (~ 10%), although constant over time and with the smallest intersubject variability. Atlas-MRAC had highest variation in bias over time (+10 to - 10%), followed by MaxProb-MRAC (+5 to - 5%), but MaxProb showed the lowest mean bias. For the cerebellum, MaxProb-MRAC showed the highest variability while bias was constant over time for Atlas- and ZTE-MRAC.

CONCLUSIONS

Both Maxprob- and ZTE-MRAC performed better than Atlas-MRAC when using a 68Ge transmission scan as reference method. Overall, ZTE-MRAC showed the highest precision and accuracy in outcome parameters of dynamic [11C]PE2I PET analysis with use of kinetic modelling.

Hybrid Imaging of Vascular Cognitive Impairment

Cerebrovascular disease is a significant cause of cognitive impairment leading to a reduction or loss of functioning, including social and occupational. The connection cause-effect between cerebrovascular disease and cerebral infarction was originally theorized by the studies from Newcastle-Upon-Tyne, England, in the 1960s, where vascular dementia (VaD) was defined as a disease originated from several infarctions that overcome a determined threshold. It differs from Alzheimer's disease (AD), although there are various overlaps in risk factors, symptomatology, the similarity of vascular lesions, and treatment benefits. Nevertheless, AD is one-half of all cases of dementia. Cognitive impairment and dementia (VCID) has recently been proposed to include different entities such as VaD, Vascular cognitive impairment, subcortical (ischemic) VaD, and vascular cognitive disorders. VaD is the most common cause of dementia after AD. Neuroimaging is an essential part of the workup of patients with cognitive decline and in those with suspected VCID it should be used to assess the extent, location, and type of vascular lesions. Computed tomography (CT) or structural magnetic resonance imaging (MRI) are usually used for the diagnosis of vascular diseases of the brain. However, images obtained from new hybrid devices could help the neurologist in the differential diagnosis between various neuropathological entities related to VCID. Single-photon emission computed tomography (SPECT) combined with CT or MRI and positron emission tomography (PET) combined with CT or MRI represent the future of neuroimaging tools as morphological and functional data can be provided simultaneously. New prospects have been developed such as hybrid PET/SPECT/CT, a high-performance prototype able to produce high-quality images but for now suitable only for small animals. Nowadays, PET/CT and PET/MRI are good performance and high-quality instruments, even if the magnetic field of MRI represents a limitation that affects the PET electronics and positron detection ability. SPECT/MRI delineates as a potential and tempting device. It could give us both functional and anatomical details, with the advantage of lack of extra ionizing radiation and high soft-tissue contrast, important features, and considerable auxiliary for differential diagnosis in the variegate word of vascular cognitive impairment. The aim of this review is to summarize the newest viewpoints in hybrid imaging in the diagnosis of VaD and to highlight pros and cons of each methodic.

Quantitative positron emission tomography imaging in the presence of iodinated contrast media using electron density quantifications from dual-energy computed tomography

PURPOSE

As preparation for future positron emission tomography (PET)/dual-energy computed tomography (DECT)T imaging modality and new possible clinical applications, the study aimed to evaluate the utility of clinically available spectral results from a DECT system for improving attenuation corrections of PET acquisitions in the presence of iodinated contrast media. The dependence of the accuracy of PET quantification values, reconstructed with conventional and spectral-based attenuation corrections, was examined as a function of the amount of iodine content and x-ray radiation exposure.

METHODS

Measurements were performed on commercial PET/CT and DECT systems, using a semi-anthropomorphic phantom with seven centrifuge tubes in its bore. Five different configurations of tube contents were scanned by both PET/CT and DECT. With the aim of mimicking clinically observed concentrations, in all phantom configurations the center tube contained a high concentration of radionuclide while the peripheral tubes contained a lower concentration of radionuclide. Iodine content was incrementally increased between phantom configurations by replacing iodine-free tubes with tubes that contained the original radionuclide concentration within a 10 mg/ml iodine dilution. DECT-based attenuation correction maps were generated by scaling electron density spectral results into corresponding 511 keV photon linear attenuation coefficients.

RESULTS

Mean SUV values obtained from the nominal PET reconstruction, using conventional CT images as input for the attenuation correction, demonstrate a monotonic increase of 8.6% when the water and radionuclide mixtures were replaced by iodine, water, and radionuclide (same level of activity) mixture. Mean SUV values obtained from the DECT-based reconstruction, in which the attenuation correction utilizes electron density values as input, demonstrate different, more stable behavior across all iodine insert configurations, with a standard deviation to mean ratio of less than 1%. This observed behavior was independent of the area size used for measurement. A minor radiation dose dependency of the electron density values (below 0.5%) was observed. This resulted in consistent (iodine independent) PET quantification behavior, which persisted even at the lowest radiation dose levels tested in our experiment, that is, 25% of the radiation dose utilized for CT acquisition in the clinical PET/CT protocol.

CONCLUSIONS

Utilization of DECT-generated electron density estimations for attenuation correction benefit PET quantification consistency in the presence of iodine and at nominal and low DECT radiation exposure levels. The ability to correctly account for iodinated contrast media in PET acquisitions will allow the development of new clinical applications that rely on the quantitative capabilities of spectral CT technologies and modern PET systems.

Advances in multimodal data fusion in neuroimaging: Overview, challenges, and novel orientation

Multimodal fusion in neuroimaging combines data from multiple imaging modalities to overcome the fundamental limitations of individual modalities. Neuroimaging fusion can achieve higher temporal and spatial resolution, enhance contrast, correct imaging distortions, and bridge physiological and cognitive information. In this study, we analyzed over 450 references from PubMed, Google Scholar, IEEE, ScienceDirect, Web of Science, and various sources published from 1978 to 2020. We provide a review that encompasses (1) an overview of current challenges in multimodal fusion (2) the current medical applications of fusion for specific neurological diseases, (3) strengths and limitations of available imaging modalities, (4) fundamental fusion rules, (5) fusion quality assessment methods, and (6) the applications of fusion for atlas-based segmentation and quantification. Overall, multimodal fusion shows significant benefits in clinical diagnosis and neuroscience research. Widespread education and further research amongst engineers, researchers and clinicians will benefit the field of multimodal neuroimaging.

Respiratory Motion Detection and Correction for MR Using the Pilot Tone: Applications for MR and Simultaneous PET/MR Examinations

OBJECTIVES

The aim of this study was to develop a method for tracking respiratory motion throughout full MR or PET/MR studies that requires only minimal additional hardware and no modifications to the sequences.

MATERIALS AND METHODS

Patient motion that is caused by respiration affects the quality of the signal of the individual radiofrequency receive coil elements. This effect can be detected as a modulation of a monofrequent signal that is emitted by a small portable transmitter placed inside the bore (Pilot Tone). The frequency is selected such that it is located outside of the frequency band of the actual MR readout experiment but well within the bandwidth of the radiofrequency receiver, that is, the oversampling area. Temporal variations of the detected signal indicate motion. After extraction of the signal from the raw data, principal component analysis was used to identify respiratory motion. The approach and potential applications during MR and PET/MR examinations that rely on a continuous respiratory signal were validated with an anthropomorphic, PET/MR-compatible motion phantom as well as in a volunteer study.

RESULTS

Respiratory motion detection and correction were presented for MR and PET data in phantom and volunteer studies. The Pilot Tone successfully recovered the ground-truth respiratory signal provided by the phantom.

CONCLUSIONS

The presented method provides reliable respiratory motion tracking during arbitrary imaging sequences throughout a full PET/MR study. All results can directly be transferred to MR-only applications as well.

Combined dual energy and iterative metal artefact reduction for PET/CT in head and neck cancer

Metal artefacts in PET/CT images hamper diagnostic accuracy in head and neck cancer (HNC). The aim of this study is to characterise the clinical effects of metal artefacts on PET/CT in HNC and to inform decision-making concerning implementation of MAR techniques. We study a combined dual energy CT and inpainting-based metal artefact reduction (DECT-I-MAR) technique for PET/CT in three settings: (A) A dental phantom with a removable amalgam-filled tooth to evaluate the PET error in comparison to a known reference. (B) PET-positive patients with metallic implants to demostrate the relationship between CT metal artefacts and PET error. (C) Metabolic tumour volumes (MTVs) delineated in PET-positive patients with metal implants to evaluate the clinical impact. In (A) DECT-I-MAR reduced the PET error significantly. In (B) we demonstrate an increasing PET error with increasing CT artefact severity in patients. In (C) it is shown that the presence of artefacts in the same axial slices as the tumour significantly decrease biomarker stability and increase delineation variability. This work shows the practical feasibility of DECT-I-MAR based PET/CT imaging, and indicates a positive clinical impact of using the technique routinely for HNC patients. The impact of CT artefacts on PET is considerable, especially in workflows where quantitative PET biomarkers and tumour volumes are used. In such cases, and for patients with tumours in proximity of metals, we recommend that a MAR technique for PET/CT is employed.

Visual stimuli induce serotonin release in occipital cortex: A simultaneous positron emission tomography/magnetic resonance imaging study

Endogenous serotonin (5-HT) release can be measured noninvasively using positron emission tomography (PET) imaging in combination with certain serotonergic radiotracers. This allows us to investigate effects of pharmacological and nonpharmacological interventions on brain 5-HT levels in living humans. Here, we study the neural responses to a visual stimulus using simultaneous PET/MRI. In a cross-over design, 11 healthy individuals were PET/MRI scanned with the 5-HT_1B receptor radioligand [¹¹ C]AZ10419369, which is sensitive to changes in endogenous 5-HT. During the last part of the scan, participants either viewed autobiographical images with positive valence (n = 11) or kept their eyes closed (n = 7). The visual stimuli increased cerebral blood flow (CBF) in the occipital cortex, as measured with pseudo-continuous arterial spin labeling. Simultaneously, we found decreased 5-HT_1B receptor binding in the occipital cortex (-3.6 ± 3.6%), indicating synaptic 5-HT release. Using a linear regression model, we found that the change in 5-HT_1B receptor binding was significantly negatively associated with change in CBF in the occipital cortex (p = .004). For the first time, we here demonstrate how cerebral 5-HT levels change in response to nonpharmacological stimuli in humans, as measured with PET. Our findings more directly support a link between 5-HT signaling and visual processing and/or visual attention.

Geraldi N, C. Pike L, Pawelke J, L. Hoffmann A, Doy N, L. Stafford J, Spicer A, I. Newton M. Advanced Sandwich Composite Cores for Patient Support in Advanced Clinical Imaging and Oncology Treatment

Ongoing advances in both imaging and treatment for oncology purposes have seen a significant rise in the use of not only the individual imaging modalities, but also their combination in single systems such as Positron Emission Tomography combined with Computed Tomography (PET-CT) and PET-MRI (Magnetic Resonance Imaging) when planning for advanced oncology treatment, the most demanding of which is proton therapy. This has identified issues in the availability of suitable materials upon which to support the patient undergoing imaging and treatment owing to the differing requirements for each of the techniques. Sandwich composites are often selected to solve this issue but there is little information regarding optimum materials for their cores. In this paper, we presented a range of materials which are suitable for such purposes and evaluated the performance for use in terms of PET signal attenuation, proton beam stopping, MRI signal shading and X-Ray CT visibility. We found that Extruded Polystyrene offers the best compromise for patient support and positioning structures across all modalities tested, allowing for significant savings in treatment planning time and delivering more efficient treatment with lower margins.

AI-driven attenuation correction for brain PET/MRI: Clinical evaluation of a dementia cohort and importance of the training group size

INTRODUCTION

Robust and reliable attenuation correction (AC) is a prerequisite for accurate quantification of activity concentration. In combined PET/MRI, AC is challenged by the lack of bone signal in the MRI from which the AC maps has to be derived. Deep learning-based image-to-image translation networks present itself as an optimal solution for MRI-derived AC (MR-AC). High robustness and generalizability of these networks are expected to be achieved through large training cohorts. In this study, we implemented an MR-AC method based on deep learning, and investigated how training cohort size, transfer learning, and MR input affected robustness, and subsequently evaluated the method in a clinical setup, with the overall aim to explore if this method could be implemented in clinical routine for PET/MRI examinations.

METHODS

A total cohort of 1037 adult subjects from the Siemens Biograph mMR with two different software versions (VB20P and VE11P) was used. The software upgrade included updates to all MRI sequences. The impact of training group size was investigated by training a convolutional neural network (CNN) on an increasing training group size from 10 to 403. The ability to adapt to changes in the input images between software versions were evaluated using transfer learning from a large cohort to a smaller cohort, by varying training group size from 5 to 91 subjects. The impact of MRI sequence was evaluated by training three networks based on the Dixon VIBE sequence (DeepDixon), T1-weighted MPRAGE (DeepT1), and ultra-short echo time (UTE) sequence (DeepUTE). Blinded clinical evaluation relative to the reference low-dose CT (CT-AC) was performed for DeepDixon in 104 independent 2-[¹⁸F]fluoro-2-deoxy-d-glucose ([¹⁸F]FDG) PET patient studies performed for suspected neurodegenerative disorder using statistical surface projections.

RESULTS

Robustness increased with group size in the training data set: 100 subjects were required to reduce the number of outliers compared to a state-of-the-art segmentation-based method, and a cohort >400 subjects further increased robustness in terms of reduced variation and number of outliers. When using transfer learning to adapt to changes in the MRI input, as few as five subjects were sufficient to minimize outliers. Full robustness was achieved at 20 subjects. Comparable robust and accurate results were obtained using all three types of MRI input with a bias below 1% relative to CT-AC in any brain region. The clinical PET evaluation using DeepDixon showed no clinically relevant differences compared to CT-AC.

CONCLUSION

Deep learning based AC requires a large training cohort to achieve accurate and robust performance. Using transfer learning, only five subjects were needed to fine-tune the method to large changes to the input images. No clinically relevant differences were found compared to CT-AC, indicating that clinical implementation of our deep learning-based MR-AC method will be feasible across MRI system types using transfer learning and a limited number of subjects.

Evaluation of 511 keV photon attenuation by a novel 32-channel phased array prospectively designed for cardiovascular hybrid PET/MRI imaging

BACKGROUND

Simultaneous cardiovascular imaging with positron emission tomography (PET) and magnetic resonance imaging (MRI) requires tools such as radio frequency (RF) phased arrays to achieve high temporal and spatial resolution in the MRI, as well as accurate quantification of PET. Today, high-density phased arrays (> 16 channels) used for cardiovascular PET/MRI are not designed to achieve low PET attenuation, and correcting the PET attenuation they cause requires off-line reconstruction, extra time and resources.

PURPOSE

Motivated by previous work assessing the MRI performance of a novel prospectively designed 32-channel phased array, this study assessed the PET image quality with this array in place. Guided by NEMA standards, PET performance was measured using global PET counts, regional background variation (BV), contrast recovery (CR) and contrast-to-noise ratio (CNR) for both the novel array and standard arrays (mMR 12-channel and MRI 32-channel). Nonattenuation-corrected (NAC) data from all arrays (and each part of the array) were processed and compared to no-array, and relative percentage difference (RPD) of the global means was estimated and reported for each part of the arrays. Attenuation correction (AC) of PET images (water in the phantom) using two approaches, MR-based AC map (MRAC) and dual-energy CT-based map (DCTAC), was performed, and RPD compared for each part of the arrays. Percent mean attenuation within regions of interests of the phantom images from each array were compared using a two-way analysis of variance (ANOVA).

RESULTS

The NAC data of the anterior part of the novel array recorded the least PET attenuation (≤ 2%); while the full novel array (anterior and posterior together) AC data, produced by MRAC and DCTAC approaches, recorded attenuation of 1.5 ± 2.9% and 0.0 ± 2.5%, respectively. The novel array PET count loss was significantly lower (p = 0.001) than those caused by the standard arrays.

CONCLUSIONS

Results of this novel 32-channel cardiac array PET performance evaluation, together with its previously reported MRI performance assessment, suggest the novel array to be a strong alternative to the standard arrays currently used for cardiovascular hybrid PET/MRI imaging. It enables accurate PET quantification and high-temporal and spatial resolution for MR imaging.