Rapid dual-echo ramped hybrid encoding MR-based attenuation correction (dRHE-MRAC) for PET/MR

PET/MRI in colorectal and anal cancers: an update

Positron emission tomography (PET) in the era of personalized medicine has a unique role in the management of oncological patients and offers several advantages over standard anatomical imaging. However, the role of molecular imaging in lower GI malignancies has historically been limited due to suboptimal anatomical evaluation on the accompanying CT, as well as significant physiological 18F-flurodeoxyglucose (FDG) uptake in the bowel. In the last decade, technological advancements have made whole-body FDG-PET/MRI a feasible alternative to PET/CT and MRI for lower GI malignancies. PET/MRI combines the advantages of molecular imaging with excellent soft tissue contrast resolution. Hence, it constitutes a unique opportunity to improve the imaging of these cancers. FDG-PET/MRI has a potential role in initial diagnosis, assessment of local treatment response, and evaluation for metastatic disease. In this article, we review the recent literature on FDG-PET/MRI for colorectal and anal cancers; provide an example whole-body FDG-PET/MRI protocol; highlight potential interpretive pitfalls; and provide recommendations on particular clinical scenarios in which FDG-PET/MRI is likely to be most beneficial for these cancer types.

Correction of B0 and linear eddy currents: Impact on morphological and quantitative ultrashort echo time double echo steady state (UTE-DESS) imaging

The purpose of the current study was to investigate the effects of B0 and linear eddy currents on ultrashort echo time double echo steady state (UTE-DESS) imaging and to determine whether eddy current correction (ECC) effectively resolves imaging artifacts caused by eddy currents. 3D UTE-DESS sequences based on either projection radial or spiral cones trajectories were implemented on a 3-T clinical MR scanner. An off-isocentered thin-slice excitation approach was used to measure eddy currents. The measurements were repeated four times using two sets of tested gradient waveforms with opposite polarities and two different slice locations to measure B0 and linear eddy currents simultaneously. Computer simulation was performed to investigate the eddy current effect. Finally, a phantom experiment, an ex vivo experiment with human synovium and ankle samples, and an in vivo experiment with human knee joints, were performed to demonstrate the effects of eddy currents and ECC in UTE-DESS imaging. In a computer simulation, the two echoes (S+ and S-) in UTE-DESS imaging exhibited strong distortion at different orientations in the presence of B0 and linear eddy currents, resulting in both image degradation as well as misalignment of pixel location between the two echoes. The same phenomenon was observed in the phantom, ex vivo, and in vivo experiments, where the presence of eddy currents degraded S+, S-, echo subtraction images, and T2 maps. The implementation of ECC dramatically improved both the image quality and image registration between the S+ and S- echoes. It was concluded that ECC is crucial for reliable morphological and quantitative UTE-DESS imaging.

Comparison of deep learning synthesis of synthetic CTs using clinical MRI inputs

There has been substantial interest in developing techniques for synthesizing CT-like images from MRI inputs, with important applications in simultaneous PET/MR and radiotherapy planning. Deep learning has recently shown great potential for solving this problem. The goal of this research was to investigate the capability of four common clinical MRI sequences (T1-weighted gradient-echo [T1], T2-weighted fat-suppressed fast spin-echo [T2-FatSat], post-contrast T1-weighted gradient-echo [T1-Post], and fast spin-echo T2-weighted fluid-attenuated inversion recovery [CUBE-FLAIR]) as inputs into a deep CT synthesis pipeline. Data were obtained retrospectively in 92 subjects who had undergone an MRI and CT scan on the same day. The patient's MR and CT scans were registered to one another using affine registration. The deep learning model was a convolutional neural network encoder-decoder with skip connections similar to the U-net architecture and Inception V3 inspired blocks instead of sequential convolution blocks. After training with 150 epochs and a batch size of 6, the model was evaluated using structural similarity index (SSIM), peak SNR (PSNR), mean absolute error (MAE), and dice coefficient. We found that feasible results were attainable for each image type, and no single image type was superior for all analyses. The MAE (in HU) of the resulting synthesized CT in the whole brain was 51.236 ± 4.504 for CUBE-FLAIR, 45.432 ± 8.517 for T1, 44.558 ± 7.478 for T1-Post, and 45.721 ± 8.7767 for T2, showing not only feasible, but also very compelling results on clinical images. Deep learning-based synthesis of CT images from MRI is possible with a wide range of inputs, suggesting that viable images can be created from a wide range of clinical input types.

Attenuation correction for human PET/MRI studies

Attenuation correction has been one of the main methodological challenges in the integrated positron emission tomography and magnetic resonance imaging (PET/MRI) field. As standard transmission or computed tomography approaches are not available in integrated PET/MRI scanners, MR-based attenuation correction approaches had to be developed. Aspects that have to be considered for implementing accurate methods include the need to account for attenuation in bone tissue, normal and pathological lung and the MR hardware present in the PET field-of-view, to reduce the impact of subject motion, to minimize truncation and susceptibility artifacts, and to address issues related to the data acquisition and processing both on the PET and MRI sides. The standard MR-based attenuation correction techniques implemented by the PET/MRI equipment manufacturers and their impact on clinical and research PET data interpretation and quantification are first discussed. Next, the more advanced methods, including the latest generation deep learning-based approaches that have been proposed for further minimizing the attenuation correction related bias are described. Finally, a future perspective focused on the needed developments in the field is given.

Rapid single scan ramped hybrid-encoding for bicomponent T2* mapping in a human knee joint: A feasibility study

The purpose of this study is to determine the feasibility of using a single scan ramped hybrid-encoding (RHE) method for rapid bicomponent T2* analysis of the human knee joint. The proposed method utilizes RHE to acquire ultrashort echo time (UTE) and subsequent gradient echo images at 16 different echo times ranging between 40 μs and 30 ms in a single scan. In the proposed RHE technique, UTE imaging was followed by acquisition of 14 gradient recalled echo images, where an additional UTE image was obtained within the first readout by oversampling single point imaging (SPI) encoding. The single scan RHE method with a 9-minute scan time was performed on human cadaveric knee joints from six donors and in vivo knee joints from four healthy volunteers at 3 T. A bicomponent signal model was used to characterize the short T2* and long T2* water components. Mean bicomponent T2* parameters for patellar tendon, anterior cruciate ligament (ACL), posterior cruciate ligament (PCL) and meniscus were calculated. In the experimental results, the RHE technique provided bicomponent T2* parameter estimations of tendon, ACL, PCL and meniscus, which were similar to previously reported values in the literature. In conclusion, the proposed single scan RHE technique provides rapid bicomponent T2* analysis of the human knee joint with a total scan time of less than 9 minutes.

MR Image-Based Attenuation Correction of Brain PET Imaging: Review of Literature on Machine Learning Approaches for Segmentation

Recent emerging hybrid technology of positron emission tomography/magnetic resonance (PET/MR) imaging has generated a great need for an accurate MR image-based PET attenuation correction. MR image segmentation, as a robust and simple method for PET attenuation correction, has been clinically adopted in commercial PET/MR scanners. The general approach in this method is to segment the MR image into different tissue types, each assigned an attenuation constant as in an X-ray CT image. Machine learning techniques such as clustering, classification and deep networks are extensively used for brain MR image segmentation. However, only limited work has been reported on using deep learning in brain PET attenuation correction. In addition, there is a lack of clinical evaluation of machine learning methods in this application. The aim of this review is to study the use of machine learning methods for MR image segmentation and its application in attenuation correction for PET brain imaging. Furthermore, challenges and future opportunities in MR image-based PET attenuation correction are discussed.

Self-Navigated Three-Dimensional Ultrashort Echo Time Technique for Motion-Corrected Skull MRI

Ultrashort echo time (UTE) MRI is capable of detecting signals from protons with very short T₂ relaxation times, and thus has potential for skull-selective imaging as a radiation-free alternative to computed tomography. However, relatively long scan times make the technique vulnerable to artifacts from involuntary subject motion. Here, we developed a self-navigated, three-dimensional (3D) UTE pulse sequence, which builds on dual-RF, dual-echo UTE imaging, and a retrospective motion correction scheme for motion-resistant skull MRI. Full echo signals in the second readout serve as a self-navigator that yields a time-course of center of mass, allowing for adaptive determination of motion states. Furthermore, golden-means based k-space trajectory was employed to achieve a quasi-uniform distribution of sampling views on a spherical k-space surface for any subset of the entire data collected, thereby allowing reconstruction of low-resolution images pertaining to each motion state for subsequent estimation of rigid-motion parameters. Finally, the extracted trajectory of the head was used to make the whole k-space datasets motion-consistent, leading to motion-corrected, high-resolution images. Additionally, we posit that hardware-related k-space trajectory errors, if uncorrected, result in obscured bone contrast. Thus, a calibration scan was performed once to measure k-space encoding locations, subsequently used during image reconstruction of actual imaging data. In vivo studies were performed to evaluate the effectiveness of the proposed correction schemes in combination with approaches to accelerated bone-selective imaging. Results illustrating effective removal of motion artifacts and clear depiction of skull bone voxels suggest that the proposed method is robust to intermittent head motions during scanning.

Characterization of hardware-related spatial distortions for IR-PETRA pulse sequence using a brain specific phantom

OBJECTIVE

Inversion recovery-pointwise encoding time reduction with radial acquisition (IR-PETRA) is an effective magnetic resonance (MR) pulse sequence in generating pseudo-CTs. The hardware-related spatial-distortion (HRSD) in MR images potentially deteriorates the accuracy of pseudo-CTs. Thus, we aimed at characterizing HRSD for IR-PETRA.

MATERIALS AND METHODS

gross-HRSD_overall (Euclidean-sum of gross-HRSD_i (i = x, y, z)) for IR-PETRA was assessed using a brain-specific phantom for two MR scanners (1.5 T-Aera and 3.0 T-Prisma). Moreover, hardware imperfections were analyzed by determining gradient-nonlinearity spatial-distortion (GNSD) and B₀-inhomogeneity spatial-distortion (B₀ISD) for magnetization-prepared rapid acquisition gradient-echo (MP-RAGE) which has well-known distortion characteristics.

RESULTS

In 3.0 T, maximum of gross-GNSD_overall (Euclidean-sum of gross-GNSD_i) and gross-B₀ISD for MP-RAGE was 2.77 mm and 0.57 mm, respectively. For this scanner, the mean and maximum of gross-HRSD_overall for IR-PETRA were 0.63 ± 0.38 mm and 1.91 mm, respectively. In 1.5 T, maximum of gross-GNSD_overall and gross-B₀ISD for MP-RAGE was 3.41 mm and 0.78 mm, respectively. The mean and maximum of gross-HRSD_overall for IR-PETRA were 1.02 ± 0.50 mm and 3.12 mm, respectively.

DISCUSSION

The spatial accuracy of MR images, besides being impacted by hardware performance, scanner capabilities, and imaging parameters, is mainly affected by its imaging strategy and data acquisition scheme. In 3.0 T, even without applying vendor correction algorithms, spatial accuracy of IR-PETRA image is sufficient for generating pseudo-CTs. In 1.5 T, distortion-correction is required to provide this accuracy.

Inversion recovery zero echo time (IR-ZTE) imaging for direct myelin detection in human brain: a feasibility study

Background

Myelin alteration is closely associated with neurological diseases such as multiple sclerosis (MS). Unfortunately, due to myelin's extremely short T2* (~0.3 ms or shorter at 3T), it cannot be directly imaged with conventional MR imaging techniques. Recently, ultrashort echo time (UTE) imaging-based methods have been proposed for direct imaging of myelin. In this study, we explore the feasibility and efficacy of inversion recovery prepared zero echo time (IR-ZTE) imaging for direct volumetric imaging of myelin in white matter of the brain in vivo.

Methods

In the proposed method, an adiabatic IR preparation pulse is used to suppress long T2 white matter signal, followed by dual echo ZTE imaging where the remaining long T2 components, including gray matter, are suppressed by dual echo subtraction. In the implementation of ZTE, the sampling strategy introduced in Water- and Fat-Suppressed Proton Projection MRI (WASPI) was incorporated to acquire the k-space data missing due to the radiofrequency (RF) transmit/receiver switching time. The IR-ZTE sequence was implemented on a 3T clinical MR system and evaluated using a myelin phantom composed of six different myelin concentrations (0% to 20%), a cadaveric human brain, four healthy volunteers, and seven MS patients.

Results

In the myelin phantom experiment, the ZTE signal intensity showed high linearity to the myelin concentrations (R²=0.98). In the ex vivo and in vivo experiments, the IR-ZTE sequence provided high contrast volumetric imaging of myelin in human brains. The IR-ZTE sequence was able to detect demyelinated foci lesions in all MS patients.

Conclusions

Adiabatic IR prepared dual echo ZTE imaging allows for direct, volumetric imaging of myelin in white matter of the brain in vivo.

MR-based PET attenuation correction using a combined ultrashort echo time/multi-echo Dixon acquisition

PURPOSE

To develop a magnetic resonance (MR)-based method for estimation of continuous linear attenuation coefficients (LACs) in positron emission tomography (PET) using a physical compartmental model and ultrashort echo time (UTE)/multi-echo Dixon (mUTE) acquisitions.

METHODS

We propose a three-dimensional (3D) mUTE sequence to acquire signals from water, fat, and short T₂ components (e.g., bones) simultaneously in a single acquisition. The proposed mUTE sequence integrates 3D UTE with multi-echo Dixon acquisitions and uses sparse radial trajectories to accelerate imaging speed. Errors in the radial k-space trajectories are measured using a special k-space trajectory mapping sequence and corrected for image reconstruction. A physical compartmental model is used to fit the measured multi-echo MR signals to obtain fractions of water, fat, and bone components for each voxel, which are then used to estimate the continuous LAC map for PET attenuation correction.

RESULTS

The performance of the proposed method was evaluated via phantom and in vivo human studies, using LACs from computed tomography (CT) as reference. Compared to Dixon- and atlas-based MRAC methods, the proposed method yielded PET images with higher correlation and similarity in relation to the reference. The relative absolute errors of PET activity values reconstructed by the proposed method were below 5% in all of the four lobes (frontal, temporal, parietal, and occipital), cerebellum, whole white matter, and gray matter regions across all subjects (n = 6).

CONCLUSIONS

The proposed mUTE method can generate subject-specific, continuous LAC map for PET attenuation correction in PET/MR.

PET/MRI attenuation estimation in the lung: A review of past, present, and potential techniques

Positron emission tomography/magnetic resonance imaging (PET/MRI) potentially offers several advantages over positron emission tomography/computed tomography (PET/CT), for example, no CT radiation dose and soft tissue images from MR acquired at the same time as the PET. However, obtaining accurate linear attenuation correction (LAC) factors for the lung remains difficult in PET/MRI. LACs depend on electron density and in the lung, these vary significantly both within an individual and from person to person. Current commercial practice is to use a single‐valued population‐based lung LAC, and better estimation is needed to improve quantification. Given the under‐appreciation of lung attenuation estimation as an issue, the inaccuracy of PET quantification due to the use of single‐valued lung LACs, the unique challenges of lung estimation, and the emerging status of PET/MRI scanners in lung disease, a review is timely. This paper highlights past and present methods, categorizing them into segmentation, atlas/mapping, and emission‐based schemes. Potential strategies for future developments are also presented.

Short-T2 MRI: Principles and recent advances

Among current modalities of biomedical and diagnostic imaging, MRI stands out by virtue of its versatile contrast obtained without ionizing radiation. However, in various cases, e.g., water protons in tissues such as bone, tendon, and lung, MRI performance is limited by the rapid decay of resonance signals associated with short transverse relaxation times T₂ or T₂*. Efforts to address this shortcoming have led to a variety of specialized short-T₂ techniques. Recent progress in this field expands the choice of methods and prompts fresh considerations with regard to instrumentation, data acquisition, and signal processing. In this review, the current status of short-T₂ MRI is surveyed. In an attempt to structure the growing range of techniques, the presentation highlights overarching concepts and basic methodological options. The most frequently used approaches are described in detail, including acquisition strategies, image reconstruction, hardware requirements, means of introducing contrast, sources of artifacts, limitations, and applications.

Inversion recovery UTE based volumetric myelin imaging in human brain using interleaved hybrid encoding

PURPOSE

Direct myelin imaging can improve the characterization of myelin-related diseases such as multiple sclerosis. In this study, we explore a novel method to directly image myelin using inversion recovery-prepared hybrid encoding (IR-HE) UTE MRI.

METHODS

The IR-HE sequence uses an adiabatic inversion pulse to suppress the long T₂ white matter signal, followed by 3D dual-echo HE utilizing both single point imaging and radial frequency encoding, for which the subtraction image between 2 echoes reveals the myelin signal with high contrast. To reduce scan time, it is common to obtain multiple spokes per IR. Here, we invented a novel method to improve the HE, adapted for the multi-spoke IR imaging-termed interleaved HE-for which single point imaging encoding is interleaved between radial frequency encodings near nulling point to allow more efficient IR-signal suppression. To evaluate the proposed approach, a computer simulation, myelin phantom experiment, an ex vivo experiment with a cadaveric multiple sclerosis brain, and an in vivo experiment with 8 healthy volunteers and 13 multiple sclerosis patients were performed.

RESULTS

The computer simulation showed that IR-interleaved HE allows for improved contrast of myelin signal with reduced imaging artifacts. The myelin phantom experiment showed IR-interleaved HE allows direct imaging of myelin lipid with excellent suppression of water signal. In the ex vivo and in vivo experiments, the proposed method demonstrated highly specific imaging of myelin in white matter of the brain.

CONCLUSION

IR-interleaved HE allows for time-efficient, high-contrast direct myelin imaging and can detect demyelinated lesions in multiple sclerosis patients.

Fat suppression for ultrashort echo time imaging using a single-point Dixon method

PURPOSE

In ultrashort echo time (UTE) imaging, fat suppression can improve short T₂ * contrast but can also reduce short T₂ * signals. The conventional two-point Dixon (2p-Dixon) method does not perform well due to short T₂ * decay. In this study, we propose a new method to suppress fat for high contrast UTE imaging of short T₂ tissues, utilizing a single-point Dixon (1p-Dixon) method.

METHODS

The proposed method utilizes dual-echo UTE imaging, where UTE is followed by the second TE, chosen flexibly. Fat is estimated by applying a 1p-Dixon method to the non-UTE image after correction of phase errors, which is used to suppress fat in the UTE image. In vivo ankle and knee imaging were performed at 3 T to evaluate the proposed method.

RESULT

It was observed that fat and water signals in tendons were misestimated by the 2p-Dixon method due to signal decay, while the 1p-Dixon method showed reliable fat and water separation not affected by the short T₂ * signal decay. Compared with the conventional chemical shift based fat saturation technique, the 1p-Dixon based approach showed much stronger signal intensities in the Achilles, quadriceps, and patellar tendons, with significantly improved contrast to noise ratios (CNRs) of 11.8 ± 2.2, 16.0 ± 1.6, and 26.8 ± 1.3 with the 1p-Dixon method and 0.6 ± 0.2, 4.6 ± 1.0, and 17.5 ± 1.4 with regular fat saturation, respectively.

CONCLUSION

The proposed 1p-Dixon based fat suppression allows more flexible selection of imaging parameters and more accurate fat and water separation over the conventional 2p-Dixon in UTE imaging. Moreover, the proposed method provides much improved CNR for short T₂ tissues over the conventional fat saturation method.

Rapid dual-RF, dual-echo, 3D ultrashort echo time craniofacial imaging: A feasibility study

PURPOSE

To develop a dual-radiofrequency (RF), dual-echo, 3D ultrashort echo-time (UTE) pulse sequence and bone-selective image reconstruction for rapid high-resolution craniofacial MRI.

METHODS

The proposed pulse sequence builds on recently introduced dual-RF UTE imaging. While yielding enhanced bone specificity by exploiting high sensitivity of short T₂ signals to variable RF pulse widths, the parent technique exacts a 2-fold scan time penalty relative to standard dual-echo UTE. In the proposed method, the parent sequence's dual-RF scheme was incorporated into dual-echo acquisitions while radial view angles are varied every pulse-to-pulse repetition period. The resulting 4 echoes (2 for each RF) were combined by view-sharing to construct 2 sets of k-space data sets, corresponding to short and long TEs, respectively, leading to a 2-fold increase in imaging efficiency. Furthermore, by exploiting the sparsity of bone signals in echo-difference images, acceleration was achieved by solving a bone-sparsity constrained image reconstruction problem. In vivo studies were performed to evaluate the effectiveness of the proposed acceleration approaches in comparison to the parent method.

RESULTS

The proposed technique achieves 1.1-mm isotropic skull imaging in 3 minutes without visual loss of image quality, compared to the parent technique (scan time = 12 minutes). Bone-specific images and corresponding 3D renderings of the skull were found to depict the expected craniofacial anatomy over the entire head.

CONCLUSION

The proposed method is able to achieve high-resolution volumetric craniofacial images in a clinically practical imaging time, and thus may prove useful as a potential alternative to computed tomography.

A deep learning approach for 18F-FDG PET attenuation correction

Background

To develop and evaluate the feasibility of a data-driven deep learning approach (deepAC) for positron-emission tomography (PET) image attenuation correction without anatomical imaging. A PET attenuation correction pipeline was developed utilizing deep learning to generate continuously valued pseudo-computed tomography (CT) images from uncorrected ¹⁸F-fluorodeoxyglucose (¹⁸F-FDG) PET images. A deep convolutional encoder-decoder network was trained to identify tissue contrast in volumetric uncorrected PET images co-registered to CT data. A set of 100 retrospective 3D FDG PET head images was used to train the model. The model was evaluated in another 28 patients by comparing the generated pseudo-CT to the acquired CT using Dice coefficient and mean absolute error (MAE) and finally by comparing reconstructed PET images using the pseudo-CT and acquired CT for attenuation correction. Paired-sample t tests were used for statistical analysis to compare PET reconstruction error using deepAC with CT-based attenuation correction.

Results

deepAC produced pseudo-CTs with Dice coefficients of 0.80 ± 0.02 for air, 0.94 ± 0.01 for soft tissue, and 0.75 ± 0.03 for bone and MAE of 111 ± 16 HU relative to the PET/CT dataset. deepAC provides quantitatively accurate ¹⁸F-FDG PET results with average errors of less than 1% in most brain regions.

Conclusions

We have developed an automated approach (deepAC) that allows generation of a continuously valued pseudo-CT from a single ¹⁸F-FDG non-attenuation-corrected (NAC) PET image and evaluated it in PET/CT brain imaging.

True phase quantitative susceptibility mapping using continuous single-point imaging: a feasibility study

PURPOSE

In this study, we explore the feasibility of a new imaging scheme for quantitative susceptibility mapping (QSM): continuous single-point imaging (CSPI), which uses a pure phase encoding strategy to achieve true phase imaging and improve QSM accuracy.

METHODS

The proposed CSPI is a modification of conventional SPI to allow acquisition of multiple echoes in a single scan. Immediately following a phase encoding gradient, the free induction decay is continuously sampled with extremely high temporal resolution to obtain k-space data at a fixed spatial frequency (i.e., at a fixed k-space coordinate). By having near-0 readout duration, CSPI results in a true snapshot of the transverse magnetization at each TE. Additionally, parallel imaging with autocalibration is utilized to reduce scan time, and an optional temporal averaging strategy is presented to improve signal-to-noise ratio for objects with low proton density or short T2* decay. The reconstructed CSPI images were input to a QSM framework based on morphology enabled dipole inversion.

RESULT

In an experiment performed using iron phantoms, susceptibility estimated using CSPI showed high linearity (R² = 0.9948) with iron concentration. Additionally, reconstructed CSPI phase images showed much reduced ringing artifact compared with phase images obtained using a frequency encoding strategy. In an ex vivo experiment performed using human tibia samples, estimated susceptibilities ranged from -1.6 to -2.1 ppm, in agreement with values reported in the literature (ranging from -1.2 to -2.2 ppm).

CONCLUSION

We have demonstrated the feasibility of using CSPI to obtain true phase images for QSM.

Zero-gradient-excitation ramped hybrid encoding (zGRF -RHE) sodium MRI

PURPOSE

Fast bi-exponential transverse signal decay compounds sodium image quality. This work aims at enhancing image characteristics using a special case of ramped hybrid encoding (RHE). Zero-gradient-excitation (zG_RF )-RHE provides (1) gradient-free excitation for high flip angle, artifact-free excitation profiles and (2) gradient ramping during dead-time for the optimization of encoding time (t_enc ) to reduce T₂ ^* signal decay influence during acquisition.

METHODS

Radial zG_RF -RHE and standard radial UTE were investigated over a range of receiver bandwidths in simulations, phantom and in vivo brain experiments. Central k-space in zG_RF -RHE was acquired through single point measurements at the minimum achievable TE. T₂ ^* blurring artifacts and image SNR and CNR were assessed.

RESULTS

zG_RF -RHE enabled 90° flip angle artifact-free excitation, whereas gradient pre-ramping provided greater t_enc efficiency for any readout bandwidths. Experiments confirmed simulation results, revealing sharper edge characteristics particularly at short readout durations (T_RO ). Significant SNR improvements of up to 4.8% were observed for longer T_RO .

CONCLUSION

zG_RF -RHE allows for artifact-free high flip angle excitation with time-efficient encoding improving on image characteristics. This hybrid encoding concept with gradient pre-ramping is trajectory independent and can be introduced in any center-out UTE trajectory design.

Feasibility of Deep Learning-Based PET/MR Attenuation Correction in the Pelvis Using Only Diagnostic MR Images

This study evaluated the feasibility of using only diagnostically relevant magnetic resonance (MR) images together with deep learning for positron emission tomography (PET)/MR attenuation correction (deepMRAC) in the pelvis. Such an approach could eliminate dedicated MRAC sequences that have limited diagnostic utility but can substantially lengthen acquisition times for multibed position scans. We used axial T2 and T1 LAVA Flex magnetic resonance imaging images that were acquired for diagnostic purposes as inputs to a 3D deep convolutional neural network. The network was trained to produce a discretized (air, water, fat, and bone) substitute computed tomography (CT) (CTsub). Discretized (CTref-discrete) and continuously valued (CTref) reference CT images were created to serve as ground truth for network training and attenuation correction, respectively. Training was performed with data from 12 subjects. CTsub, CTref, and the system MRAC were used for PET/MR attenuation correction, and quantitative PET values of the resulting images were compared in 6 test subjects. Overall, the network produced CTsub with Dice coefficients of 0.79 ± 0.03 for cortical bone, 0.98 ± 0.01 for soft tissue (fat: 0.94 ± 0.0; water: 0.88 ± 0.02), and 0.49 ± 0.17 for bowel gas when compared with CTref-discrete. The root mean square error of the whole PET image was 4.9% by using deepMRAC and 11.6% by using the system MRAC. In evaluating 16 soft tissue lesions, the distribution of errors for maximum standardized uptake value was significantly narrower using deepMRAC (-1.0% ± 1.3%) than using system MRAC method (0.0% ± 6.4%) according to the Brown-Forsy the test (P < .05). These results indicate that improved PET/MR attenuation correction can be achieved in the pelvis using only diagnostically relevant MR images.

Technical Note: Deep learning based MRAC using rapid ultrashort echo time imaging

PURPOSE

In this study, we explore the feasibility of a novel framework for MR-based attenuation correction for PET/MR imaging based on deep learning via convolutional neural networks, which enables fully automated and robust estimation of a pseudo CT image based on ultrashort echo time (UTE), fat, and water images obtained by a rapid MR acquisition.

METHODS

MR images for MRAC are acquired using dual echo ramped hybrid encoding (dRHE), where both UTE and out-of-phase echo images are obtained within a short single acquisition (35 s). Tissue labeling of air, soft tissue, and bone in the UTE image is accomplished via a deep learning network that was pre-trained with T1-weighted MR images. UTE images are used as input to the network, which was trained using labels derived from co-registered CT images. The tissue labels estimated by deep learning are refined by a conditional random field based correction. The soft tissue labels are further separated into fat and water components using the two-point Dixon method. The estimated bone, air, fat, and water images are then assigned appropriate Hounsfield units, resulting in a pseudo CT image for PET attenuation correction. To evaluate the proposed MRAC method, PET/MR imaging of the head was performed on eight human subjects, where Dice similarity coefficients of the estimated tissue labels and relative PET errors were evaluated through comparison to a registered CT image.

RESULT

Dice coefficients for air (within the head), soft tissue, and bone labels were 0.76 ± 0.03, 0.96 ± 0.006, and 0.88 ± 0.01. In PET quantitation, the proposed MRAC method produced relative PET errors less than 1% within most brain regions.

CONCLUSION

The proposed MRAC method utilizing deep learning with transfer learning and an efficient dRHE acquisition enables reliable PET quantitation with accurate and rapid pseudo CT generation.