Attenuation Correction of Long Axial Field-of-View Positron Emission Tomography Using Synthetic Computed Tomography Derived from the Emission Data: Application to Low-Count Studies and Multiple Tracers.

Recent advancements in PET/CT, including the emergence of long axial field-of-view (LAFOV) PET/CT scanners, have increased PET sensitivity substantially. Consequently, there has been a significant reduction in the required tracer activity, shifting the primary source of patient radiation dose exposure to the attenuation correction (AC) CT scan during PET imaging. This study proposes a parameter-transferred conditional generative adversarial network (PT-cGAN) architecture to generate synthetic CT (sCT) images from non-attenuation corrected (NAC) PET images, with separate networks for [18F]FDG and [15O]H2O tracers. The study includes a total of 1018 subjects (n = 972 [18F]FDG, n = 46 [15O]H2O). Testing was performed on the LAFOV scanner for both datasets. Qualitative analysis found no differences in image quality in 30 out of 36 cases in FDG patients, with minor insignificant differences in the remaining 6 cases. Reduced artifacts due to motion between NAC PET and CT were found. For the selected organs, a mean average error of 0.45% was found for the FDG cohort, and that of 3.12% was found for the H2O cohort. Simulated low-count images were included in testing, which demonstrated good performance down to 45 s scans. These findings show that the AC of total-body PET is feasible across tracers and in low-count studies and might reduce the artifacts due to motion and metal implants.

Estimation of brain amyloid accumulation using deep learning in clinical [11C]PiB PET imaging.

INTRODUCTION: Estimation of brain amyloid accumulation is valuable for evaluation of patients with cognitive impairment in both research and clinical routine. The development of high throughput and accurate strategies for the determination of amyloid status could be an important tool in patient selection for clinical trials and amyloid directed treatment. Here, we propose the use of deep learning to quantify amyloid accumulation using standardized uptake value ratio (SUVR) and classify amyloid status based on their PET images. METHODS: A total of 1309 patients with cognitive impairment scanned with [11C]PIB PET/CT or PET/MRI were included. Two convolutional neural networks (CNNs) for reading-based amyloid status and SUVR prediction were trained using 75% of the PET/CT data. The remaining PET/CT (n = 300) and all PET/MRI (n = 100) data was used for evaluation. RESULTS: The prevalence of amyloid positive patients was 61%. The amyloid status classification model reproduced the expert reader's classification with 99% accuracy. There was a high correlation between reference and predicted SUVR (R2 = 0.96). Both reference and predicted SUVR had an accuracy of 97% compared to expert classification when applying a predetermined SUVR threshold of 1.35 for binary classification of amyloid status. CONCLUSION: The proposed CNN models reproduced both the expert classification and quantitative measure of amyloid accumulation in a large local dataset. This method has the potential to replace or simplify existing clinical routines and can facilitate fast and accurate classification well-suited for a high throughput pipeline.

Scanner agnostic large-scale evaluation of MS lesion delineation tool for clinical MRI.

Introduction: Patients with MS are MRI scanned continuously throughout their disease course resulting in a large manual workload for radiologists which includes lesion detection and size estimation. Though many models for automatic lesion segmentation have been published, few are used broadly in clinic today, as there is a lack of testing on clinical datasets. By collecting a large, heterogeneous training dataset directly from our MS clinic we aim to present a model which is robust to different scanner protocols and artefacts and which only uses MRI modalities present in routine clinical examinations. Methods: We retrospectively included 746 patients from routine examinations at our MS clinic. The inclusion criteria included acquisition at one of seven different scanners and an MRI protocol including 2D or 3D T2-w FLAIR, T2-w and T1-w images. Reference lesion masks on the training (n = 571) and validation (n = 70) datasets were generated using a preliminary segmentation model and subsequent manual correction. The test dataset (n = 100) was manually delineated. Our segmentation model https://github.com/CAAI/AIMS/ was based on the popular nnU-Net, which has won several biomedical segmentation challenges. We tested our model against the published segmentation models HD-MS-Lesions, which is also based on nnU-Net, trained with a more homogenous patient cohort. We furthermore tested model robustness to data from unseen scanners by performing a leave-one-scanner-out experiment. Results: We found that our model was able to segment MS white matter lesions with a performance comparable to literature: DSC = 0.68, precision = 0.90, recall = 0.70, f1 = 0.78. Furthermore, the model outperformed HD-MS-Lesions in all metrics except precision = 0.96. In the leave-one-scanner-out experiment there was no significant change in performance (p < 0.05) between any of the models which were only trained on part of the dataset and the full segmentation model. Conclusion: In conclusion we have seen, that by including a large, heterogeneous dataset emulating clinical reality, we have trained a segmentation model which maintains a high segmentation performance while being robust to data from unseen scanners. This broadens the applicability of the model in clinic and paves the way for clinical implementation.

DeepDixon synthetic CT for [18F]FET PET/MRI attenuation correction of post-surgery glioma patients with metal implants.

Purpose: Conventional magnetic resonance imaging (MRI) can for glioma assessment be supplemented by positron emission tomography (PET) imaging with radiolabeled amino acids such as O-(2-[18F]fluoroethyl)-L-tyrosine ([18F]FET), which provides additional information on metabolic properties. In neuro-oncology, patients often undergo brain and skull altering treatment, which is known to challenge MRI-based attenuation correction (MR-AC) methods and thereby impact the simplified semi-quantitative measures such as tumor-to-brain ratio (TBR) used in clinical routine. The aim of the present study was to examine the applicability of our deep learning method, DeepDixon, for MR-AC in [18F]FET PET/MRI scans of a post-surgery glioma cohort with metal implants. Methods: The MR-AC maps were assessed for all 194 included post-surgery glioma patients (318 studies). The subgroup of 147 patients (222 studies, 200 MBq [18F]FET PET/MRI) with tracer uptake above 1 ml were subsequently reconstructed with DeepDixon, vendor-default atlas-based method, and a low-dose computed tomography (CT) used as reference. The biological tumor volume (BTV) was delineated on each patient by isocontouring tracer uptake above a TBR threshold of 1.6. We evaluated the MR-AC methods using the recommended clinical metrics BTV and mean and maximum TBR on a patient-by-patient basis against the reference with CT-AC. Results: Ninety-seven percent of the studies (310/318) did not have any major artifacts using DeepDixon, which resulted in a Dice coefficient of 0.89/0.83 for tissue/bone, respectively, compared to 0.84/0.57 when using atlas. The average difference between DeepDixon and CT-AC was within 0.2% across all clinical metrics, and no statistically significant difference was found. When using DeepDixon, only 3 out of 222 studies (1%) exceeded our acceptance criteria compared to 72 of the 222 studies (32%) with the atlas method. Conclusion: We evaluated the performance of a state-of-the-art MR-AC method on the largest post-surgical glioma patient cohort to date. We found that DeepDixon could overcome most of the issues arising from irregular anatomy and metal artifacts present in the cohort resulting in clinical metrics within acceptable limits of the reference CT-AC in almost all cases. This is a significant improvement over the vendor-provided atlas method and of particular importance in response assessment.

Evaluation of the HD-GLIO Deep Learning Algorithm for Brain Tumour Segmentation on Postoperative MRI.

In the context of brain tumour response assessment, deep learning-based three-dimensional (3D) tumour segmentation has shown potential to enter the routine radiological workflow. The purpose of the present study was to perform an external evaluation of a state-of-the-art deep learning 3D brain tumour segmentation algorithm (HD-GLIO) on an independent cohort of consecutive, post-operative patients. For 66 consecutive magnetic resonance imaging examinations, we compared delineations of contrast-enhancing (CE) tumour lesions and non-enhancing T2/FLAIR hyperintense abnormality (NE) lesions by the HD-GLIO algorithm and radiologists using Dice similarity coefficients (Dice). Volume agreement was assessed using concordance correlation coefficients (CCCs) and Bland-Altman plots. The algorithm performed very well regarding the segmentation of NE volumes (median Dice = 0.79) and CE tumour volumes larger than 1.0 cm3 (median Dice = 0.86). If considering all cases with CE tumour lesions, the performance dropped significantly (median Dice = 0.40). Volume agreement was excellent with CCCs of 0.997 (CE tumour volumes) and 0.922 (NE volumes). The findings have implications for the application of the HD-GLIO algorithm in the routine radiological workflow where small contrast-enhancing tumours will constitute a considerable share of the follow-up cases. Our study underlines that independent validations on clinical datasets are key to asserting the robustness of deep learning algorithms.

A zero-dose synthetic baseline for the personalized analysis of [18F]FDG-PET: Application in Alzheimer's disease.

Purpose: Brain 2-Deoxy-2-[18F]fluoroglucose ([18F]FDG-PET) is widely used in the diagnostic workup of Alzheimer's disease (AD). Current tools for uptake analysis rely on non-personalized templates, which poses a challenge as decreased glucose uptake could reflect neuronal dysfunction, or heterogeneous brain morphology associated with normal aging. Overcoming this, we propose a deep learning method for synthesizing a personalized [18F]FDG-PET baseline from the patient's own MRI, and showcase its applicability in detecting AD pathology. Methods: We included [18F]FDG-PET/MRI data from 123 patients of a local cohort and 600 patients from ADNI. A supervised, adversarial model with two connected Generative Adversarial Networks (GANs) was trained on cognitive normal (CN) patients with transfer-learning to generate full synthetic baseline volumes (sbPET) (192 × 192 × 192) which reflect healthy uptake conditioned on brain anatomy. Synthetic accuracy was measured by absolute relative %-difference (Abs%), relative %-difference (RD%), and peak signal-to-noise ratio (PSNR). Lastly, we deployed the sbPET images in a fully personalized method for localizing metabolic abnormalities. Results: The model achieved a spatially uniform Abs% of 9.4%, RD% of 0.5%, and a PSNR of 26.3 for CN subjects. The sbPET images conformed to the anatomical information dictated by the MRI and proved robust in presence of atrophy. The personalized abnormality method correctly mapped the pathology of AD subjects while showing little to no anomalies for CN subjects. Conclusion: This work demonstrated the feasibility of synthesizing fully personalized, healthy-appearing [18F]FDG-PET images. Using these, we showcased a promising application in diagnosing AD, and theorized the potential value of sbPET images in other neuroimaging routines.

Deep learning based low-activity PET reconstruction of [11C]PiB and [18F]FE-PE2I in neurodegenerative disorders.

PURPOSE: Positron Emission Tomography (PET) can support a diagnosis of neurodegenerative disorder by identifying disease-specific pathologies. Our aim was to investigate the feasibility of using activity reduction in clinical [18F]FE-PE2I and [11C]PiB PET/CT scans, simulating low injected activity or scanning time reduction, in combination with AI-assisted denoising. METHODS: A total of 162 patients with clinically uncertain Alzheimer's disease underwent amyloid [11C]PiB PET/CT and 509 patients referred for clinically uncertain Parkinson's disease underwent dopamine transporter (DAT) [18F]FE-PE2I PET/CT. Simulated low-activity data were obtained by random sampling of 5% of the events from the list-mode file and a 5% time window extraction in the middle of the scan. A three-dimensional convolutional neural network (CNN) was trained to denoise the resulting PET images for each disease cohort. RESULTS: Noise reduction of low-activity PET images was successful for both cohorts using 5% of the original activity with improvement in visual quality and all similarity metrics with respect to the ground-truth images. Clinically relevant metrics extracted from the low-activity images deviated < 2% compared to ground-truth values, which were not significantly changed when extracting the metrics from the denoised images. CONCLUSION: The presented models were based on the same network architecture and proved to be a robust tool for denoising brain PET images with two widely different tracer distributions (delocalized, ([11C]PiB, and highly localized, [18F]FE-PE2I). This broad and robust application makes the presented network a good choice for improving the quality of brain images to the level of the standard-activity images without degrading clinical metric extraction. This will allow for reduced dose or scan time in PET/CT to be implemented clinically.

A convolutional neural network for total tumor segmentation in [64Cu]Cu-DOTATATE PET/CT of patients with neuroendocrine neoplasms.

BACKGROUND: Segmentation of neuroendocrine neoplasms (NENs) in [64Cu]Cu-DOTATATE positron emission tomography makes it possible to extract quantitative measures useable for prognostication of patients. However, manual tumor segmentation is cumbersome and time-consuming. Therefore, we aimed to implement and test an artificial intelligence (AI) network for tumor segmentation. Patients with gastroenteropancreatic or lung NEN with [64Cu]Cu-DOTATATE PET/CT performed were included in our training (n = 117) and test cohort (n = 41). Further, 10 patients with no signs of NEN were included as negative controls. Ground truth segmentations were obtained by a standardized semiautomatic method for tumor segmentation by a physician. The nnU-Net framework was used to set up a deep learning U-net architecture. Dice score, sensitivity and precision were used for selection of the final model. AI segmentations were implemented in a clinical imaging viewer where a physician evaluated performance and performed manual adjustments. RESULTS: Cross-validation training was used to generate models and an ensemble model. The ensemble model performed best overall with a lesion-wise dice of 0.850 and pixel-wise dice, precision and sensitivity of 0.801, 0.786 and 0.872, respectively. Performance of the ensemble model was acceptable with some degree of manual adjustment in 35/41 (85%) patients. Final tumor segmentation could be obtained from the AI model with manual adjustments in 5 min versus 17 min for ground truth method, p < 0.01. CONCLUSION: We implemented and validated an AI model that achieved a high similarity with ground truth segmentation and resulted in faster tumor segmentation. With AI, total tumor segmentation may become feasible in the clinical routine.

Assessment of Artificial Intelligence Automatic Multiple Sclerosis Lesion Delineation Tool for Clinical Use.

PURPOSE: To implement and validate an existing algorithm for automatic delineation of white matter lesions on magnetic resonance imaging (MRI) in patients with multiple sclerosis (MS) on a local single-center dataset. METHODS: We implemented a white matter hyperintensity segmentation model, based on a 2D convolutional neural network, using the conventional T2-weighted fluid attenuated inversion recovery (FLAIR) MRI sequence as input. The model was adapted for delineation of MS lesions by further training on a local dataset of 93 MS patients with a total of 3040 lesions. A quantitative evaluation was performed on ten test patients, in which model-generated masks were compared to manually delineated masks from two expert delineators. A subsequent qualitative evaluation of the implemented model was performed by two expert delineators, in which generated delineation masks on a clinical dataset of 53 patients were rated acceptable (< 10% errors) or unacceptable (> 10% errors) based on the total number of true lesions. RESULTS: The quantitative evaluation resulted in an average accuracy score (F1) of 0.71, recall of 0.77 and dice similarity coefficient of 0.62. Our implemented model obtained the highest scores in all three metrics, when compared to three out of the box lesion segmentation models. In the clinical evaluation an average of 94% of our 53 model-generated masks were rated acceptable. CONCLUSION: After adaptation to our local dataset, the implemented segmentation model was able to delineate MS lesions with a high clinical value as rated by delineation experts while outperforming popular out of the box applications. This serves as a promising step towards implementation of automatic lesion delineation in our MS clinic.

Semiautomatic Tumor Delineation for Evaluation of 64Cu-DOTATATE PET/CT in Patients with Neuroendocrine Neoplasms: Prognostication Based on Lowest Lesion Uptake and Total Tumor Volume.

Patients with neuroendocrine neoplasms (NENs) have heterogeneous somatostatin receptor expression, with highly differentiated lesions having higher expression. Receptor expression of the total tumor burden may be visualized by somatostatin receptor imaging, such as with 64Cu-DOTATATE PET/CT. Assessment of maximal lesion uptake is associated with progression-free survival (PFS) but not overall survival (OS). We hypothesized that the lesion with the lowest, rather than the highest, 64Cu-DOTATATE uptake would be more prognostic, and we developed a semiautomatic method for evaluating this hypothesis. Methods: Patients with NENs underwent 64Cu-DOTATATE PET/CT. A standardized semiautomatic tumor delineation method was developed and used to identify the lesion with the lowest uptake, that is, with the lowest SUVmean Additionally, we assessed total tumor volume derived from the semiautomatic tumor delineation. Kaplan-Meier and Cox regression analyses were used to determine whether there was any association with OS and PFS. Results: In 116 patients with NENs, median PFS (95% CI) was 23 mo (range, 20-31 mo) and median OS was 85 mo (range, 68-113 mo). Minimum SUVmean and total tumor volume were significantly associated with PFS and OS in univariate Cox regression analyses, whereas SUVmax was significant only for PFS. In multivariate Cox analyses, both minimum SUVmean and total tumor volume remained statistically significant. Minimum SUVmean and total tumor volume were then dichotomized by their median, and patients were categorized into 4 groups: high or low total tumor volume and high or low minimum SUVmean Patients with a low total tumor volume and high minimum SUVmean had a hazard ratio of 0.32 (95% CI, 0.20-0.51) for PFS and 0.24 (95% CI, 0.13-0.43) for OS, both with P values of less than 0.001 (reference: high total tumor volume and low minimum SUVmean). Conclusion: We propose a standardized semiautomatic tumor delineation method to identify the lesion with the lowest 64Cu-DOTATATE uptake and total tumor volume. Assessment of the lowest, rather than the highest, lesion uptake greatly increases prognostication by 64Cu-DOTATATE PET/CT. Combining lesion uptake and total tumor volume, we derived a novel prognostic classification system for patients with NENs.

Low-dose PET image noise reduction using deep learning: application to cardiac viability FDG imaging in patients with ischemic heart disease.

INTRODUCTION: Cardiac [18F]FDG-PET is widely used for viability testing in patients with chronic ischemic heart disease. Guidelines recommend injection of 200-350 MBq [18F]FDG, however, a reduction of radiation exposure has become increasingly important, but might come at the cost of reduced diagnostic accuracy due to the increased noise in the images. We aimed to explore the use of a common deep learning (DL) network for noise reduction in low-dose PET images, and to validate its accuracy using the clinical quantitative metrics used to determine cardiac viability in patients with ischemic heart disease. METHODS: We included 168 patients imaged with cardiac [18F]FDG-PET/CT. We simulated a reduced dose by keeping counts at thresholds 1% and 10%. 3D U-net with five blocks was trained to de-noise full PET volumes (128 × 128 × 111). The low-dose and de-noised images were compared in Corridor4DM to the full-dose PET images. We used the default segmentation of the left ventricle to extract the quantitative metrics end-diastolic volume (EDV), end-systolic volume (ESV), and left ventricular ejection fraction (LVEF) from the gated images, and FDG defect extent from the static images. RESULTS: Our de-noising models were able to recover the PET signal for both the static and gated images in either dose-reduction. For the 1% low-dose images, the error is most pronounced for EDV and ESV, where the average underestimation is 25%. No bias was observed using the proposed DL de-noising method. De-noising minimized the outliers found for the 1% and 10% low-dose measurements of LVEF and extent. Accuracy of differential diagnosis based on LVEF threshold was highly improved after de-noising. CONCLUSION: A significant dose reduction can be achieved for cardiac [18F]FDG images used for viability testing in patients with ischemic heart disease without significant loss of diagnostic accuracy when using our DL model for noise reduction. Both 1% and 10% dose reductions are possible with clinically quantitative metrics comparable to that obtained with a full dose.

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.

[Artificial intelligence for diagnostic imaging].

Artificial intelligence (AI) is a computer-based system, which in diagnostic imaging can improve patient flow, optimise image processing, shorten scan time, reduce radiation dose and be used as decision aid in image interpretation. In this review, we argue that AI algorithms should be based on evidence with initial hypothesis, then a choice of algorithm and development with training on the initial data set; afterwards the algorithms should be tested on a new representative dataset, and finally it should be tested in a prospective study. If the AI is evidence-based and can solve a task better or cheaper than the usual methodology, it can be implemented.

Quantitative and clinical impact of MRI-based attenuation correction methods in [18F]FDG evaluation of dementia.

BACKGROUND: Positron emission tomography/magnetic resonance imaging (PET/MRI) is a promising diagnostic imaging tool for the diagnosis of dementia, as PET can add complementary information to the routine imaging examination with MRI. The purpose of this study was to evaluate the influence of MRI-based attenuation correction (MRAC) on diagnostic assessment of dementia with [18F]FDG PET. Quantitative differences in both [18F]FDG uptake and z-scores were calculated for three clinically available (DixonNoBone, DixonBone, UTE) and two research MRAC methods (UCL, DeepUTE) compared to CT-based AC (CTAC). Furthermore, diagnoses based on visual evaluations were made by three nuclear medicine physicians and one neuroradiologist (PETCT, PETDeepUTE, PETDixonBone, PETUTE, PETCT + MRI, PETDixonBone + MRI). In addition, pons and cerebellum were compared as reference regions for normalization. RESULTS: The mean absolute difference in z-scores were smallest between MRAC and CTAC with cerebellum as reference region: 0.15 ± 0.11 σ (DeepUTE), 0.15 ± 0.12 σ (UCL), 0.23 ± 0.20 σ (DixonBone), 0.32 ± 0.28 σ (DixonNoBone), and 0.54 ± 0.40 σ (UTE). In the visual evaluation, the diagnoses agreed with PETCT in 74% (PETDeepUTE), 67% (PETDixonBone), and 70% (PETUTE) of the patients, while PETCT + MRI agreed with PETDixonBone + MRI in 89% of the patients. CONCLUSION: The MRAC research methods performed close to that of CTAC in the quantitative evaluation of [18F]FDG uptake and z-scores. Among the clinically implemented MRAC methods, DixonBone should be preferred for diagnostic assessment of dementia with [18F]FDG PET/MRI. However, as artifacts occur in DixonBone attenuation maps, they must be visually inspected to assure proper quantification.

Metal artifact correction strategies in MRI-based attenuation correction in PET/MRI.

In hybrid positron emission tomography (PET) and MRI systems, attenuation correction for PET image reconstruction is commonly based on processing of dedicated MR images. The image quality of the latter is strongly affected by metallic objects inside the body, such as e.g. dental implants, endoprostheses, or surgical clips which all lead to substantial artifacts that propagate into MRI-based attenuation images. In this work, we review publications about metal artifact correction strategies in MRI-based attenuation correction in PET/MRI. Moreover, we also give an overview about publications investigating the impact of MRI-based attenuation correction metal artifacts on the reconstructed PET image quality and quantification.

Deep Learning Based Attenuation Correction of PET/MRI in Pediatric Brain Tumor Patients: Evaluation in a Clinical Setting.

Aim: Positron emission tomography (PET) imaging is a useful tool for assisting in correct differentiation of tumor progression from reactive changes. O-(2-18F-fluoroethyl)-L-tyrosine (FET)-PET in combination with MRI can add valuable information for clinical decision making. Acquiring FET-PET/MRI simultaneously allows for a one-stop-shop that limits the need for a second sedation or anesthesia as with PET and MRI in sequence. PET/MRI is challenged by lack of a direct measure of photon attenuation. Accepted solutions for attenuation correction (AC) might not be applicable to pediatrics. The aim of this study was to evaluate the use of the subject-specific MR-derived AC method RESOLUTE, modified to a pediatric cohort, against the performance of an MR-AC technique based on deep learning in a pediatric brain tumor cohort. Methods: The modifications to RESOLUTE and the implementation of a deep learning method were performed using 79 pediatric patient examinations. We analyzed the 36 of these with active brain tumor area above 1 mL. We measured background (B), tumor mean and maximal activity (TMEAN, TMAX), biological tumor volume (BTV), and calculated the clinical metrics TMEAN/B and TMAX/B. Results: Overall, we found both RESOLUTE and our DeepUTE methodologies to accurately reproduce the CT-AC clinical metrics. Regardless of age, both methods were able to obtain AC maps similar to the CT-AC, albeit with DeepUTE producing the most similar based on both quantitative metrics and visual inspection. In the patient-by-patient analysis DeepUTE was the only technique with all patients inside the predefined acceptable clinical limits. It also had a higher precision with relative %-difference to the reference CT-AC (TMAX/B mean: -0.1%, CI: [-0.8%, 0.5%], p = 0.54) compared to RESOLUTE (TMAX/B mean: 0.3%, CI: [-0.6%, 1.2%], p = 0.67) and DIXON-AC (TMAX/B mean: 5.9%, CI: [4.5%, 7.4%], p < 0.0001). Conclusion: Overall, we found DeepUTE to be the AC method that most robustly reproduced the CT-AC clinical metrics per se, closely followed by RESOLUTE modified to pediatric cohorts. The added accuracy due to better noise handling of DeepUTE, ease of use, as well as the improved runtime makes DeepUTE the method of choice for PET/MRI attenuation correction.

Reproducibility of Quantitative Brain Imaging Using a PET-Only and a Combined PET/MR System.

The purpose of this study was to test the feasibility of migrating a quantitative brain imaging protocol from a positron emission tomography (PET)-only system to an integrated PET/MR system. Potential differences in both absolute radiotracer concentration as well as in the derived kinetic parameters as a function of PET system choice have been investigated. Five healthy volunteers underwent dynamic (R)-[11C]verapamil imaging on the same day using a GE-Advance (PET-only) and a Siemens Biograph mMR system (PET/MR). PET-emission data were reconstructed using a transmission-based attenuation correction (AC) map (PET-only), whereas a standard MR-DIXON as well as a low-dose CT AC map was applied to PET/MR emission data. Kinetic modeling based on arterial blood sampling was performed using a 1-tissue-2-rate constant compartment model, yielding kinetic parameters (K1 and k2) and distribution volume (V T ). Differences for parametric values obtained in the PET-only and the PET/MR systems were analyzed using a 2-way Analysis of Variance (ANOVA). Comparison of DIXON-based AC (PET/MR) with emission data derived from the PET-only system revealed average inter-system differences of -33 ± 14% (p < 0.05) for the K1 parameter and -19 ± 9% (p < 0.05) for k2. Using a CT-based AC for PET/MR resulted in slightly lower systematic differences of -16 ± 18% for K1 and -9 ± 10% for k2. The average differences in V T were -18 ± 10% (p < 0.05) for DIXON- and -8 ± 13% for CT-based AC. Significant systematic differences were observed for kinetic parameters derived from emission data obtained from PET/MR and PET-only imaging due to different standard AC methods employed. Therefore, a transfer of imaging protocols from PET-only to PET/MR systems is not straightforward without application of proper correction methods. Clinical Trial Registration: www.clinicaltrialsregister.eu, identifier 2013-001724-19.

Impact of incorrect tissue classification in Dixon-based MR-AC: fat-water tissue inversion.

BACKGROUND: The current MR-based attenuation correction (AC) used in combined PET/MR systems computes a Dixon attenuation map (MR-ACDixon) based on fat and water images derived from in- and opposed-phase MRI. We observed an occasional fat/water inversion in MR-ACDixon. The aim of our study was to estimate the prevalence of this phenomenon in a large patient cohort and assess the possible bias on PET data. METHODS: PET/MRI was performed on a Siemens Biograph mMR (Siemens AG, Erlangen, Germany). We visually inspected attenuation maps of 283 brain or head/neck (H/N) patients, classified them as non-inverted or inverted, and calculated the fat/water tissue fraction. We selected ten FDG-PET brain patients with non-inverted attenuation maps for further analysis. Tissue inversion was simulated, and PET images were reconstructed using both original and inverted attenuation maps. The FDG-PET images of the ten brain patients were analyzed using 11 concentric annulus regions of 5 mm width placed over a central transaxial image plane traversing PETDixon. RESULTS: Out of the 283 patients, a fat/water inversion in 23 patients (8.1%) was observed. The average fraction of fat in the correct MR-ACDixon was 13% for brain and 17% for H/N patients. In the inverted cases, we found an average fat fraction of 56% for the brain patients and 41% for the H/N patients. The effect of the simulated tissue inversion in the brain studies was clearly seen on AC-PET images. The percent-difference image revealed a radial error where the largest difference was at the ventricles (30% ± 3%) and smallest at the cortical region (10% ± 2%). CONCLUSIONS: Tissue inversion in Dixon MRI is well known and can occur when there is an error in the off-resonance correction method. Tissue inversion needs to be considered if, based on Dixon-AC, the construction of normal PET databases is performed or any quantitative physiological parameters are fitted. Visual inspection is needed if Dixon-AC is to be used in clinical routine.

Combined PET/MR imaging in neurology: MR-based attenuation correction implies a strong spatial bias when ignoring bone.

AIM: Combined PET/MR systems have now become available for clinical use. Given the lack of integrated standard transmission (TX) sources in these systems, attenuation and scatter correction (AC) must be performed using the available MR-images. Since bone tissue cannot easily be accounted for during MR-AC, PET quantification can be biased, in particular, in the vicinity of the skull. Here, we assess PET quantification in PET/MR imaging of patients using phantoms and patient data. MATERIALS AND METHODS: Nineteen patients referred to our clinic for a PET/CT exam as part of the diagnostic evaluation of suspected dementia were included in our study. The patients were injected with 200MBq [(18)F]FDG and imaged with PET/CT and PET/MR in random sequence within 1h. Both, PET/CT and PET/MR were performed as single-bed acquisitions without contrast administration. PET/CT and PET/MR data were reconstructed following CT-based and MR-based AC, respectively. MR-AC was performed based on: (A) standard Dixon-Water-Fat segmentation (DWFS), (B) DWFS with co-registered and segmented CT bone values superimposed, and (C) with co-registered full CT-based attenuation image. All PET images were reconstructed using AW-OSEM, with neither resolution recovery nor time-of-flight option employed. PET/CT (D) or PET/MR (A-C) images were decay-corrected to the start time of the first examination. PET images following AC were evaluated visually and quantitatively using 10 homeomorphic regions of interest drawn on a transaxial T1w-MR image traversing the central basal ganglia. We report the relative difference (%) of the mean ROI values for (A)-(C) in reference to PET/CT (D). In a separate phantom experiment a 2L plastic bottle was layered with approximately 12mm of Gypsum plaster to mimic skull bone. The phantom was imaged on PET/CT only and standard MR-AC was performed by replacing hyperdense CT attenuation values corresponding to bone (plaster) with attenuation values of water. PET image reconstruction was performed with CT-AC (D) and CT-AC using the modified CT images corresponding to MR-AC using DWFS (A). RESULTS: PET activity values in patients following MR-AC (A) showed a substantial radial dependency when compared to PET/CT. In all patients cortical PET activity was lower than the activity in the central region of the brain (10-15%). When adding bone attenuation values to standard MR-AC (B and C) the radial gradient of PET activity values was removed. Further evaluation of PET/MR activity following MR-AC (A) relative to MR-AC (C) using the full CT for attenuation correction showed an underestimation of 25% in the cortical regions and 5-10% in the central regions of the brain. Observations in patients were replicated by observations from the phantom study. CONCLUSION: Our phantom and patient data demonstrate a spatially varying bias of the PET activity in PET/MR images of the brain when bone tissue is not accounted for during attenuation correction. This has immediate implications for PET/MR imaging of the brain. Therefore, refinements to existing MR-AC methods or alternative strategies need to be found prior to adopting PET/MR imaging of the brain in clinical routine and research.