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

Accuracy and Longitudinal Consistency of PET/MR Attenuation Correction in Amyloid PET Imaging amid Software and Hardware Upgrades

BACKGROUND AND PURPOSE

Integrated PET/MR allows the simultaneous acquisition of PET biomarkers and structural and functional MRI to study Alzheimer disease (AD). Attenuation correction (AC), crucial for PET quantification, can be performed by using a deep learning approach, DL-Dixon, based on standard Dixon images. Longitudinal amyloid PET imaging, which provides important information about disease progression or treatment responses in AD, is usually acquired over several years. Hardware and software upgrades often occur during a multiple-year study period, resulting in data variability. This study aims to harmonize PET/MR DL-Dixon AC amid software and head coil updates and evaluate its accuracy and longitudinal consistency.

MATERIALS AND METHODS

Tri-modality PET/MR and CT images were obtained from 329 participants, with a subset of 38 undergoing tri-modality scans twice within approximately 3 years. Transfer learning was used to fine-tune DL-Dixon models on images from 2 scanner software versions (VB20P and VE11P) and 2 head coils (16-channel and 32-channel coils). The accuracy and longitudinal consistency of the DL-Dixon AC were evaluated. Power analyses were performed to estimate the sample size needed to detect various levels of longitudinal changes in the PET standardized uptake value ratio (SUVR).

RESULTS

The DL-Dixon method demonstrated high accuracy across all data, irrespective of scanner software versions and head coils. More than 95.6% of brain voxels showed less than 10% PET relative absolute error in all participants. The median [interquartile range] PET mean relative absolute error was 1.10% [0.93%, 1.26%], 1.24% [1.03%, 1.54%], 0.99% [0.86%, 1.13%] in the cortical summary region, and 1.04% [0.83%, 1.36%], 1.08% [0.84%, 1.34%], 1.05% [0.72%, 1.32%] in cerebellum by using the DL-Dixon models for the VB20P 16-channel coil, VE11P 16-channel coil, and VE11P 32-channel coil data, respectively. The within-subject coefficient of variation and intraclass correlation coefficient of PET SUVR in the cortical regions were comparable between the DL-Dixon and CT AC. Power analysis indicated that similar numbers of participants would be needed to detect the same level of PET changes by using DL-Dixon and CT AC.

CONCLUSIONS

DL-Dixon exhibited excellent accuracy and longitudinal consistency across the 2 software versions and head coils, demonstrating its robustness for longitudinal PET/MR neuroimaging studies in AD.

CT-Free Attenuation Correction in Paediatric Long Axial Field-of-View Positron Emission Tomography Using Synthetic CT from Emission Data

Background/Objectives: Paediatric PET/CT imaging is crucial in oncology but poses significant radiation risks due to children's higher radiosensitivity and longer post-exposure life expectancy. This study aims to minimize radiation exposure by generating synthetic CT (sCT) images from emission PET data, eliminating the need for attenuation correction (AC) CT scans in paediatric patients. Methods: We utilized a cohort of 128 paediatric patients, resulting in 195 paired PET and CT images. Data were acquired using Siemens Biograph Vision 600 and Long Axial Field-of-View (LAFOV) Siemens Vision Quadra PET/CT scanners. A 3D parameter transferred conditional GAN (PT-cGAN) architecture, pre-trained on adult data, was adapted and trained on the paediatric cohort. The model's performance was evaluated qualitatively by a nuclear medicine specialist and quantitatively by comparing sCT-derived PET (sPET) with standard PET images. Results: The model demonstrated high qualitative and quantitative performance. Visual inspection showed no significant (19/23) or minor clinically insignificant (4/23) differences in image quality between PET and sPET. Quantitative analysis revealed a mean SUV relative difference of -2.6 ± 5.8% across organs, with a high agreement in lesion overlap (Dice coefficient of 0.92 ± 0.08). The model also performed robustly in low-count settings, maintaining performance with reduced acquisition times. Conclusions: The proposed method effectively reduces radiation exposure in paediatric PET/CT imaging by eliminating the need for AC CT scans. It maintains high diagnostic accuracy and minimises motion-induced artifacts, making it a valuable alternative for clinical application. Further testing in clinical settings is warranted to confirm these findings and enhance patient safety.

Prospective phase II trial of [68Ga]Ga-NOTA-AE105 uPAR-PET/MRI in patients with primary gliomas: Prognostic value and Implications for uPAR-targeted Radionuclide Therapy

BACKGROUND

Treatment of patients with low-grade and high-grade gliomas is highly variable due to the large difference in survival expectancy. New non-invasive tools are needed for risk stratification prior to treatment. The urokinase plasminogen activator receptor (uPAR) is expressed in several cancers, associated with poor prognosis and may be non-invasively imaged using uPAR-PET. We aimed to investigate the uptake of the uPAR-PET tracer [68Ga]Ga-NOTA-AE105 in primary gliomas and establish its prognostic value regarding overall survival (OS), and progression-free survival (PFS). Additionally, we analyzed the proportion of uPAR-PET positive tumors to estimate the potential number of candidates for future uPAR-PRRT.

METHODS

In a prospective phase II clinical trial, 24 patients suspected of primary glioma underwent a dynamic 60-min PET/MRI following the administration of approximately 200 MBq (range: 83-222 MBq) [68Ga]Ga-NOTA-AE105. Lesions were considered uPAR positive if the tumor-to-background ratio, calculated as the ratio of TumorSUVmax-to-Normal-BrainSUVmean tumor-SUVmax-to-background-SUVmean, was ≥ 2.0. The patients were followed over time to assess OS and PFS and stratified into high and low uPAR expression groups based on TumorSUVmax.

RESULTS

Of the 24 patients, 16 (67%) were diagnosed with WHO grade 4 gliomas, 6 (25%) with grade 3, and 2 (8%) with grade 2. Two-thirds of all patients (67%) presented with uPAR positive lesions and 94% grade 4 gliomas. At median follow up of 18.8 (2.1-45.6) months, 19 patients had disease progression and 14 had died. uPAR expression dichotomized into high and low, revealed significant worse prognosis for the high uPAR group for OS and PFS with HR of 14.3 (95% CI, 1.8-112.3; P = 0.011), and HR of 26.5 (95% CI, 3.3-214.0; P = 0.0021), respectively. uPAR expression as a continuous variable was associated with worse prognosis for OS and PFS with HR of 2.7 (95% CI, 1.5-4.8; P = 0.0012), and HR of 2.5 (95% CI, 1.5-4.2; P = 0.00073), respectively.

CONCLUSIONS

The majority of glioma patients and almost all with grade 4 gliomas displayed uPAR positive lesions underlining the feasibility of 68Ga-NOTA-AE105 PET/MRI in gliomas. High uPAR expression is significantly correlated with worse survival outcomes for patients. Additionally, the high proportion of uPAR positive gliomas underscores the potential of uPAR-targeted radionuclide therapy in these patients.

TRAIL REGISTRATION

EudraCT No: 2016-002417-21; the Scientific Ethics Committee: H-16,035,303; the Danish Data Protection Agency: 2012-58-0004; clinical trials registry: NCT02945826, 26Oct2016, URL: https://classic.

CLINICALTRIALS

gov/ct2/show/NCT02945826 .

SNMMI Procedure Standard/EANM Practice Guideline for Brain [18F]FDG PET Imaging, Version 2.0

PREAMBLEThe Society of Nuclear Medicine and Molecular Imaging (SNMMI) is an international scientific and professional organization founded in 1954 to promote the science, technology, and practical application of nuclear medicine. The European Association of Nuclear Medicine (EANM) is a professional nonprofit medical association that facilitates communication worldwide between individuals pursuing clinical and research excellence in nuclear medicine. The EANM was founded in 1985. The EANM was founded in 1985. SNMMI and EANM members are physicians, technologists, and scientists specializing in the research and practice of nuclear medicine.The SNMMI and EANM will periodically define new guidelines for nuclear medicine practice to help advance the science of nuclear medicine and to improve the quality of service to patients throughout the world. Existing practice guidelines will be reviewed for revision or renewal, as appropriate, on their fifth anniversary or sooner, if indicated.Each practice guideline, representing a policy statement by the SNMMI/EANM, has undergone a thorough consensus process in which it has been subjected to extensive review. The SNMMI and EANM recognize that the safe and effective use of diagnostic nuclear medicine imaging requires specific training, skills, and techniques, as described in each document. Reproduction or modification of the published practice guideline by those entities not providing these services is not authorized.These guidelines are an educational tool designed to assist practitioners in providing appropriate care for patients. They are not inflexible rules or requirements of practice and are not intended, nor should they be used, to establish a legal standard of care. For these reasons and those set forth below, both the SNMMI and the EANM caution against the use of these guidelines in litigation in which the clinical decisions of a practitioner are called into question.The ultimate judgment regarding the propriety of any specific procedure or course of action must be made by the physician or medical physicist in light of all the circumstances presented. Thus, there is no implication that an approach differing from the guidelines, standing alone, is below the standard of care. To the contrary, a conscientious practitioner may responsibly adopt a course of action different from that set forth in the guidelines when, in the reasonable judgment of the practitioner, such course of action is indicated by the condition of the patient, limitations of available resources, or advances in knowledge or technology subsequent to publication of the guidelines.The practice of medicine includes both the art and the science of the prevention, diagnosis, alleviation, and treatment of disease. The variety and complexity of human conditions make it impossible to always reach the most appropriate diagnosis or to predict with certainty a particular response to treatment.Therefore, it should be recognized that adherence to these guidelines will not ensure an accurate diagnosis or a successful outcome. All that should be expected is that the practitioner will follow a reasonable course of action based on current knowledge, available resources, and the needs of the patient to deliver effective and safe medical care. The sole purpose of these guidelines is to assist practitioners in achieving this objective.

Assessment of cerebral drug occupancy in humans using a single PET-scan: A [11C]UCB-J PET study

PURPOSE

Here, we evaluate a PET displacement model with a Single-step and Numerical solution in healthy individuals using the synaptic vesicle glycoprotein (SV2A) PET-tracer [11C]UCB-J and the anti-seizure medication levetiracetam (LEV). We aimed to (1) validate the displacement model by comparing the brain LEV-SV2A occupancy from a single PET scan with the occupancy derived from two PET scans and the Lassen plot and (2) determine the plasma LEV concentration-SV2A occupancy curve in healthy individuals.

METHODS

Eleven healthy individuals (five females, mean age 35.5 [range: 25-47] years) underwent two 120-min [11C]UCB-J PET scans where an LEV dose (5-30 mg/kg) was administered intravenously halfway through the first PET scan to partially displace radioligand binding to SV2A. Five individuals were scanned twice on the same day; the remaining six were scanned once on two separate days, receiving two identical LEV doses. Arterial blood samples were acquired to determine the arterial input function and plasma LEV concentrations. Using the displacement model, the SV2A-LEV target engagement was calculated and compared with the Lassen plot method. The resulting data were fitted with a single-site binding model.

RESULTS

SV2A occupancies and VND estimates derived from the displacement model were not significantly different from the Lassen plot (p = 0.55 and 0.13, respectively). The coefficient of variation was 14.6% vs. 17.3% for the Numerical and the Single-step solution in Bland-Altman comparisons with the Lassen plot. The average half maximal inhibitory concentration (IC50), as estimated from the area under the curve of the plasma LEV concentration, was 12.5 µg/mL (95% CI: 5-25) for the Single-Step solution, 11.8 µg/mL (95% CI: 4-25) for the Numerical solution, and 6.3 µg/mL (95% CI: 0.08-21) for the Lassen plot. Constraining Emax to 100% did not significantly improve model fits.

CONCLUSION

Plasma LEV concentration vs. SV2A occupancy can be determined in humans using a single PET scan displacement model. The average concentration of the three computed IC50 values ranges between 6.3 and 12.5 µg/mL. The next step is to use the displacement model to evaluate LEV occupancy and corresponding plasma concentrations in relation to treatment efficacy.

CLINICAL TRIAL REGISTRATION

NCT05450822. Retrospectively registered 5 July 2022 https://clinicaltrials.gov/ct2/results? term=NCT05450822&Search=Search.

Histomolecular Validation of [18F]-FACBC in Gliomas Using Image-Localized Biopsies

BACKGROUND

Gliomas have a heterogeneous nature, and identifying the most aggressive parts of the tumor and defining tumor borders are important for histomolecular diagnosis, surgical resection, and radiation therapy planning. This study evaluated [18F]-FACBC PET for glioma tissue classification.

METHODS

Pre-surgical [18F]-FACBC PET/MR images were used during surgery and image-localized biopsy sampling in patients with high- and low-grade glioma. TBR was compared to histomolecular results to determine optimal threshold values, sensitivity, specificity, and AUC values for the classification of tumor tissue. Additionally, PET volumes were determined in patients with glioblastoma based on the optimal threshold. [18F]-FACBC PET volumes and diagnostic accuracy were compared to ce-T1 MRI. In total, 48 biopsies from 17 patients were analyzed.

RESULTS

[18F]-FACBC had low uptake in non-glioblastoma tumors, but overall higher sensitivity and specificity for the classification of tumor tissue (0.63 and 0.57) than ce-T1 MRI (0.24 and 0.43). Additionally, [18F]-FACBC TBR was an excellent classifier for IDH1-wildtype tumor tissue (AUC: 0.83, 95% CI: 0.71-0.96). In glioblastoma patients, PET tumor volumes were on average eight times larger than ce-T1 MRI volumes and included 87.5% of tumor-positive biopsies compared to 31.5% for ce-T1 MRI.

CONCLUSION

The addition of [18F]-FACBC PET to conventional MRI could improve tumor classification and volume delineation.

The cingulate island sign in a mixed memory clinical cohort: Prevalence and diagnostic accuracy

INTRODUCTION

Visual rating of the cingulate island sign (CIS) on [18F]fluorodeoxyglucose ([18F]FDG) positron emission tomography (PET) has a high specificity for dementia with Lewy bodies (DLB) in selected cohorts such as DLB versus Alzheimer's disease (AD). In a mixed memory clinical population this study aimed to uncover the prevalence of CIS, the diagnostic accuracy for DLB, and the relationship between CIS and disease severity.

METHODS

CIS on [18F]FDG-PET was retrospectively assessed with the visual CIS rating scale (CISRs) in 1000 patients with a syndrome diagnosis of mild cognitive impairment (MCI) or dementia with no restrictions in etiological diagnosis.

RESULTS

In this cohort 24.3 % had a CISRs score ≥1 and 3.5 % had a CISRs score = 4. The prevalence of a CISRs score ≥1 was highest in DLB (74.0 %, n = 57). A CISRs score ≥1 was present in at least 9 % in other diagnostic groups. The prevalence of CIS across disease severities showed no statistically significant difference (p = 0.23). To differentiate DLB from non-DLB the optimal cut-off was a CISRs score ≥1 (balanced accuracy = 77.1 %) in MCI/mild dementia and a CISRs score ≥2 (balanced accuracy = 80.6 %) in moderate/severe dementia. The positive predictive value of a CISRs score = 4 for DLB was 57.7 % in MCI/mild dementia and 33.3 % in moderate/severe dementia.

CONCLUSION

The CISRs is useful in differentiating DLB from other etiologies in a mixed memory clinical population. Balanced accuracy and positive predictive value may vary across disease severities in the population studied.

The use of PET/MRI in radiotherapy

Positron emission tomography/magnetic resonance imaging (PET/MRI) is a hybrid imaging technique that quantitatively combines the metabolic and functional data from positron emission tomography (PET) with anatomical and physiological information from MRI. As PET/MRI technology has advanced, its applications in cancer care have expanded. Recent studies have demonstrated that PET/MRI provides unique advantages in the field of radiotherapy and has become invaluable in guiding precision radiotherapy techniques. This review discusses the rationale and clinical evidence supporting the use of PET/MRI for radiation positioning, target delineation, efficacy evaluation, and patient surveillance.Critical relevance statement This article critically assesses the transformative role of PET/MRI in advancing precision radiotherapy, providing essential insights into improved radiation positioning, target delineation, efficacy evaluation, and patient surveillance in clinical radiology practice.Key points• The emergence of PET/MRI will be a key bridge for precise radiotherapy.• PET/MRI has unique advantages in the whole process of radiotherapy.• New tracers and nanoparticle probes will broaden the use of PET/MRI in radiation.• PET/MRI will be utilized more frequently for radiotherapy.

Strategies for deep learning-based attenuation and scatter correction of brain 18 F-FDG PET images in the image domain

BACKGROUND

Attenuation and scatter correction is crucial for quantitative positron emission tomography (PET) imaging. Direct attenuation correction (AC) in the image domain using deep learning approaches has been recently proposed for combined PET/MR and standalone PET modalities lacking transmission scanning devices or anatomical imaging.

PURPOSE

In this study, different input settings were considered in the model training to investigate deep learning-based AC in the image space.

METHODS

Three different deep learning methods were developed for direct AC in the image space: (i) use of non-attenuation-corrected PET images as input (NonAC-PET), (ii) use of attenuation-corrected PET images with a simple two-class AC map (composed of soft-tissue and background air) obtained from NonAC-PET images (PET segmentation-based AC [SegAC-PET]), and (iii) use of both NonAC-PET and SegAC-PET images in a Double-Channel fashion to predict ground truth attenuation corrected PET images with Computed Tomography images (CTAC-PET). Since a simple two-class AC map (generated from NonAC-PET images) can easily be generated, this work assessed the added value of incorporating SegAC-PET images into direct AC in the image space. A 4-fold cross-validation scheme was adopted to train and evaluate the different models based using 80 brain 18 F-Fluorodeoxyglucose PET/CT images. The voxel-wise and region-wise accuracy of the models were examined via measuring the standardized uptake value (SUV) quantification bias in different regions of the brain.

RESULTS

The overall root mean square error (RMSE) for the Double-Channel setting was 0.157 ± 0.08 SUV in the whole brain region, while RMSEs of 0.214 ± 0.07 and 0.189 ± 0.14 SUV were observed in NonAC-PET and SegAC-PET models, respectively. A mean SUV bias of 0.01 ± 0.26% was achieved by the Double-Channel model regarding the activity concentration in cerebellum region, as opposed to 0.08 ± 0.28% and 0.05 ± 0.28% SUV biases for the network that uniquely used NonAC-PET or SegAC-PET as input, respectively. SegAC-PET images with an SUV bias of -1.15 ± 0.54%, served as a benchmark for clinically accepted errors. In general, the Double-Channel network, relying on both SegAC-PET and NonAC-PET images, outperformed the other AC models.

CONCLUSION

Since the generation of two-class AC maps from non-AC PET images is straightforward, the current study investigated the potential added value of incorporating SegAC-PET images into a deep learning-based direct AC approach. Altogether, compared with models that use only NonAC-PET and SegAC-PET images, the Double-Channel deep learning network exhibited superior attenuation correction accuracy.

18F-FACBC and 18F-FDG PET/MRI in the evaluation of 3 patients with primary central nervous system lymphoma: a pilot study

BACKGROUND

This PET/MRI study compared contrast-enhanced MRI, 18F-FACBC-, and 18F-FDG-PET in the detection of primary central nervous system lymphomas (PCNSL) in patients before and after high-dose methotrexate chemotherapy. Three immunocompetent PCNSL patients with diffuse large B-cell lymphoma received dynamic 18F-FACBC- and 18F-FDG-PET/MRI at baseline and response assessment. Lesion detection was defined by clinical evaluation of contrast enhanced T1 MRI (ce-MRI) and visual PET tracer uptake. SUVs and tumor-to-background ratios (TBRs) (for 18F-FACBC and 18F-FDG) and time-activity curves (for 18F-FACBC) were assessed.

RESULTS

At baseline, seven ce-MRI detected lesions were also detected with 18F-FACBC with high SUVs and TBRs (SUVmax:mean, 4.73, TBRmax: mean, 9.32, SUVpeak: mean, 3.21, TBRpeak:mean: 6.30). High TBR values of 18F-FACBC detected lesions were attributed to low SUVbackground. Baseline 18F-FDG detected six lesions with high SUVs (SUVmax: mean, 13.88). In response scans, two lesions were detected with ce-MRI, while only one was detected with 18F-FACBC. The lesion not detected with 18F-FACBC was a small atypical MRI detected lesion, which may indicate no residual disease, as this patient was still in complete remission 12 months after initial diagnosis. No lesions were detected with 18F-FDG in the response scans.

CONCLUSIONS

18F-FACBC provided high tumor contrast, outperforming 18F-FDG in lesion detection at both baseline and in response assessment. 18F-FACBC may be a useful supplement to ce-MRI in PCNSL detection and response assessment, but further studies are required to validate these findings. Trial registration ClinicalTrials.gov. Registered 15th of June 2017 (Identifier: NCT03188354, https://clinicaltrials.gov/study/NCT03188354 ).

Diagnostic accuracy of anti-3-[18F]-FACBC PET/MRI in gliomas

PURPOSE

The primary aim was to evaluate whether anti-3-[18F]FACBC PET combined with conventional MRI correlated better with histomolecular diagnosis (reference standard) than MRI alone in glioma diagnostics. The ability of anti-3-[18F]FACBC to differentiate between molecular and histopathological entities in gliomas was also evaluated.

METHODS

In this prospective study, patients with suspected primary or recurrent gliomas were recruited from two sites in Norway and examined with PET/MRI prior to surgery. Anti-3-[18F]FACBC uptake (TBRpeak) was compared to histomolecular features in 36 patients. PET results were then added to clinical MRI readings (performed by two neuroradiologists, blinded for histomolecular results and PET data) to assess the predicted tumor characteristics with and without PET.

RESULTS

Histomolecular analyses revealed two CNS WHO grade 1, nine grade 2, eight grade 3, and 17 grade 4 gliomas. All tumors were visible on MRI FLAIR. The sensitivity of contrast-enhanced MRI and anti-3-[18F]FACBC PET was 61% (95%CI [45, 77]) and 72% (95%CI [58, 87]), respectively, in the detection of gliomas. Median TBRpeak was 7.1 (range: 1.4-19.2) for PET positive tumors. All CNS WHO grade 1 pilocytic astrocytomas/gangliogliomas, grade 3 oligodendrogliomas, and grade 4 glioblastomas/astrocytomas were PET positive, while 25% of grade 2-3 astrocytomas and 56% of grade 2-3 oligodendrogliomas were PET positive. Generally, TBRpeak increased with malignancy grade for diffuse gliomas. A significant difference in PET uptake between CNS WHO grade 2 and 4 gliomas (p < 0.001) and between grade 3 and 4 gliomas (p = 0.002) was observed. Diffuse IDH wildtype gliomas had significantly higher TBRpeak compared to IDH1/2 mutated gliomas (p < 0.001). Adding anti-3-[18F]FACBC PET to MRI improved the accuracy of predicted glioma grades, types, and IDH status, and yielded 13.9 and 16.7 percentage point improvement in the overall diagnoses for both readers, respectively.

CONCLUSION

Anti-3-[18F]FACBC PET demonstrated high uptake in the majority of gliomas, especially in IDH wildtype gliomas, and improved the accuracy of preoperatively predicted glioma diagnoses.

CLINICAL TRIAL REGISTRATION

ClinicalTrials.gov ID: NCT04111588, URL: https://clinicaltrials.gov/study/NCT04111588.

Comparative Insight into Microglia/Macrophages-Associated Pathways in Glioblastoma and Alzheimer's Disease

Microglia and macrophages are pivotal to the brain's innate immune response and have garnered considerable attention in the context of glioblastoma (GBM) and Alzheimer's disease (AD) research. This review delineates the complex roles of these cells within the neuropathological landscape, focusing on a range of signaling pathways-namely, NF-κB, microRNAs (miRNAs), and TREM2-that regulate the behavior of tumor-associated macrophages (TAMs) in GBM and disease-associated microglia (DAMs) in AD. These pathways are critical to the processes of neuroinflammation, angiogenesis, and apoptosis, which are hallmarks of GBM and AD. We concentrate on the multifaceted regulation of TAMs by NF-κB signaling in GBM, the influence of TREM2 on DAMs' responses to amyloid-beta deposition, and the modulation of both TAMs and DAMs by GBM- and AD-related miRNAs. Incorporating recent advancements in molecular biology, immunology, and AI techniques, through a detailed exploration of these molecular mechanisms, we aim to shed light on their distinct and overlapping regulatory functions in GBM and AD. The review culminates with a discussion on how insights into NF-κB, miRNAs, and TREM2 signaling may inform novel therapeutic approaches targeting microglia and macrophages in these neurodegenerative and neoplastic conditions. This comparative analysis underscores the potential for new, targeted treatments, offering a roadmap for future research aimed at mitigating the progression of these complex diseases.

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.

An automatic pipeline for PET/MRI attenuation correction validation in the brain

PURPOSE

Challenges in PET/MRI quantitative accuracy for neurological uses arise from PET attenuation correction accuracy. We proposed and evaluated an automatic pipeline to assess the quantitative accuracy of four MRI-derived PET AC methods using analytically simulated PET brain lesions and ROIs as ground truth for PET activity.

METHODS

Our proposed pipeline, integrating a synthetic lesion insertion tool and the FreeSurfer neuroimaging framework, inserts simulated spherical and brain ROIs into PET projection space, reconstructing them via four PET MRAC techniques. Utilizing an 11-patient brain PET dataset, we compared the quantitative accuracy of four MRACs (DIXON, DIXONbone, UTE AC, and DL-DIXON) against the gold standard PET CTAC, evaluating MRAC to CTAC activity bias in spherical lesions and brain ROIs with and without background activity against original (lesion free) PET reconstructed images.

RESULTS

The proposed pipeline yielded accurate results for spherical lesions and brain ROIs, adhering to the MRAC to CTAC pattern of original brain PET images. Among the MRAC methods, DIXON AC exhibited the highest bias, followed by UTE, DIXONBone, and DL-DIXON showing the least. DIXON, DIXONbone, UTE, and DL-DIXON showed MRAC to CTAC biases of - 5.41%, - 1.85%, - 2.74%, and 0.08% respectively for ROIs inserted in background activity; - 7.02%, - 2.46%, - 3.56%, and - 0.05% for lesion ROIs without background; and - 6.82%, - 2.08%, - 2.29%, and 0.22% for the original brain PET images' 16 FreeSurfer brain ROIs.

CONCLUSION

The proposed pipeline delivers accurate results for synthetic spherical lesions and brain ROIs, with and without background activity consideration, enabling the evaluation of new attenuation correction approaches without utilizing measured PET emission data. Additionally, it offers a consistent method to generate realistic lesion ROIs, potentially applicable in assessing further PET correction techniques.

International EANM-SNMMI-ISMRM consensus recommendation for PET/MRI in oncology

PREAMBLE

The Society of Nuclear Medicine and Molecular Imaging (SNMMI) is an international scientific and professional organization founded in 1954 to promote the science, technology, and practical application of nuclear medicine. The European Association of Nuclear Medicine (EANM) is a professional non-profit medical association that facilitates communication worldwide between individuals pursuing clinical and research excellence in nuclear medicine. The EANM was founded in 1985. The merged International Society for Magnetic Resonance in Medicine (ISMRM) is an international, nonprofit, scientific association whose purpose is to promote communication, research, development, and applications in the field of magnetic resonance in medicine and biology and other related topics and to develop and provide channels and facilities for continuing education in the field.The ISMRM was founded in 1994 through the merger of the Society of Magnetic Resonance in Medicine and the Society of Magnetic Resonance Imaging. SNMMI, ISMRM, and EANM members are physicians, technologists, and scientists specializing in the research and practice of nuclear medicine and/or magnetic resonance imaging. The SNMMI, ISMRM, and EANM will periodically define new guidelines for nuclear medicine practice to help advance the science of nuclear medicine and/or magnetic resonance imaging and to improve the quality of service to patients throughout the world. Existing practice guidelines will be reviewed for revision or renewal, as appropriate, on their fifth anniversary or sooner, if indicated. Each practice guideline, representing a policy statement by the SNMMI/EANM/ISMRM, has undergone a thorough consensus process in which it has been subjected to extensive review. The SNMMI, ISMRM, and EANM recognize that the safe and effective use of diagnostic nuclear medicine imaging and magnetic resonance imaging requires specific training, skills, and techniques, as described in each document. Reproduction or modification of the published practice guideline by those entities not providing these services is not authorized. These guidelines are an educational tool designed to assist practitioners in providing appropriate care for patients. They are not inflexible rules or requirements of practice and are not intended, nor should they be used, to establish a legal standard of care. For these reasons and those set forth below, the SNMMI, the ISMRM, and the EANM caution against the use of these guidelines in litigation in which the clinical decisions of a practitioner are called into question. The ultimate judgment regarding the propriety of any specific procedure or course of action must be made by the physician or medical physicist in light of all the circumstances presented. Thus, there is no implication that an approach differing from the guidelines, standing alone, is below the standard of care. To the contrary, a conscientious practitioner may responsibly adopt a course of action different from that set forth in the guidelines when, in the reasonable judgment of the practitioner, such course of action is indicated by the condition of the patient, limitations of available resources, or advances in knowledge or technology subsequent to publication of the guidelines. The practice of medicine includes both the art and the science of the prevention, diagnosis, alleviation, and treatment of disease. The variety and complexity of human conditions make it impossible to always reach the most appropriate diagnosis or to predict with certainty a particular response to treatment. Therefore, it should be recognized that adherence to these guidelines will not ensure an accurate diagnosis or a successful outcome. All that should be expected is that the practitioner will follow a reasonable course of action based on current knowledge, available resources, and the needs of the patient to deliver effective and safe medical care. The sole purpose of these guidelines is to assist practitioners in achieving this objective.

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.

Clinical validation of the cingulate island sign visual rating scale in dementia with Lewy bodies

INTRODUCTION

The cingulate island sign (CIS) is a metabolic pattern on [¹⁸F]fluorodeoxyglucose ([¹⁸F]FDG) positron emission tomography (PET) associated with dementia with Lewy bodies (DLB). The aim of this study was to validate the visual CIS rating scale (CISRs) for the diagnosis of DLB and to explore the clinical correlates.

METHODS

This single-center study included 166 DLB patients and 161 patients with Alzheimer's disease (AD). The CIS on [¹⁸F]FDG-PET scans was rated using the CISRs independently by three blinded raters.

RESULTS

The optimal cut-off to differentiate DLB from AD was a CISRs score ≥ 1 (sensitivity = 66%, specificity = 84%) whereas a CISRs score ≥ 2 (sensitivity = 58%, specificity = 92%) was optimal to differentiate amyloid positive DLB (n = 43 (82.7%)) and AD. To identify DLB with abnormal (n = 53 (72.6%)) versus normal (n = 20 (27.4%)) dopamine transporter imaging, a CISRs cut-off of 4 had a specificity of 95%. DLB with a CISRs score of 4 performed significantly better in tests on free verbal recall and picture based cued recall, but worse on processing speed compared to DLB with a CISRs score of 0.

CONCLUSION

This study confirms the CISRs as a valid marker for the diagnosis of DLB with a high specificity and a lower, but acceptable, sensitivity. Concomitant AD pathology does not influence diagnostic accuracy of the CISRs. In DLB patients, presence of CIS is associated with relative preserved memory function and impaired processing speed.

An automatic pipeline for PET/MRI attenuation correction validation in the brain

Purpose

PET/MRI quantitative accuracy for neurological applications is challenging due to accuracy of the PET attenuation correction. In this work, we proposed and evaluated an automatic pipeline for assessing the quantitative accuracy of four different MRI = based attenuation correction (PET MRAC) approaches.

Methods

The proposed pipeline consists of a synthetic lesion insertion tool and the FreeSurfer neuroimaging analysis framework. The synthetic lesion insertion tool is used to insert simulated spherical, and brain regions of interest (ROI) into the PET projection space and reconstructed with four different PET MRAC techniques, while FreeSurfer is used to generate brain ROIs from T1 weighted MRI image. Using a cohort of 11 patients' brain PET dataset, the quantitative accuracy of four MRAC(s), which are: DIXON AC, DIXONbone AC, UTE AC, and Deep learning trained with DIXON AC, named DL-DIXON AC, were compared to the PET-based CT attenuation correction (PET CTAC). MRAC to CTAC activity bias in spherical lesions and brain ROIs were reconstructed with and without background activity and compared to the original PET images.

Results

The proposed pipeline provides accurate and consistent results for inserted spherical lesions and brain ROIs inserted with and without considering the background activity and following the same MRAC to CTAC pattern as the original brain PET images. As expected, the DIXON AC showed the highest bias; the second was for the UTE, then the DIXONBone, and the DL-DIXON with the lowest bias. For simulated ROIs inserted in the background activity, DIXON showed a -4.65% MRAC to CTAC bias, 0.06% for the DIXONbone, -1.70% for the UTE, and - 0.23% for the DL-DIXON. For lesion ROIs inserted without background activity, DIXON showed a -5.21%, -1% for the DIXONbone, -2.55% for the UTE, and - 0.52 for the DL-DIXON. For MRAC to CTAC bias calculated using the same 16 FreeSurfer brain ROIs in the original brain PET reconstructed images, a 6.87% was observed for the DIXON, -1.83% for DIXON bone, -3.01% for the UTE, and - 0.17% for the DL-DIXON.

Conclusion

The proposed pipeline provides accurate and consistent results for synthetic spherical lesions and brain ROIs inserted with and without considering the background activity; hence a new attenuation correction approach can be evaluated without using measured PET emission data.

The performance of machine learning approaches for attenuation correction of PET in neuroimaging: A meta-analysis

PURPOSE

This systematic review provides a consensus on the clinical feasibility of machine learning (ML) methods for brain PET attenuation correction (AC). Performance of ML-AC were compared to clinical standards.

METHODS

Two hundred and eighty studies were identified through electronic searches of brain PET studies published between January 1, 2008, and August 1, 2022. Reported outcomes for image quality, tissue classification performance, regional and global bias were extracted to evaluate ML-AC performance. Methodological quality of included studies and the quality of evidence of analysed outcomes were assessed using QUADAS-2 and GRADE, respectively.

RESULTS

A total of 19 studies (2371 participants) met the inclusion criteria. Overall, the global bias of ML methods was 0.76 ± 1.2%. For image quality, the relative mean square error (RMSE) was 0.20 ± 0.4 while for tissues classification, the Dice similarity coefficient (DSC) for bone/soft tissue/air were 0.82 ± 0.1 / 0.95 ± 0.03 / 0.85 ± 0.14.

CONCLUSIONS

In general, ML-AC performance is within acceptable limits for clinical PET imaging. The sparse information on ML-AC robustness and its limited qualitative clinical evaluation may hinder clinical implementation in neuroimaging, especially for PET/MRI or emerging brain PET systems where standard AC approaches are not readily available.

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.

Diagnostic Value of 18 F-FACBC PET/MRI in Brain Metastases

PURPOSE

The study aims to evaluate whether combined 18 F-FACBC PET/MRI could provide additional diagnostic information compared with MRI alone in brain metastases.

PATIENTS AND METHODS

Eighteen patients with newly diagnosed or suspected recurrence of brain metastases received dynamic 18 F-FACBC PET/MRI. Lesion detection was evaluated on PET and MRI scans in 2 groups depending on prior stereotactic radiosurgery (SRS group) or not (no-SRS group). SUVs, time-activity curves, and volumetric analyses of the lesions were performed.

RESULTS

In the no-SRS group, 29/29 brain lesions were defined as "MRI positive." With PET, 19/29 lesions were detected and had high tumor-to-background ratios (TBRs) (D max MR , ≥7 mm; SUV max , 1.2-8.4; TBR, 3.9-25.9), whereas 10/29 lesions were undetected (D max MR , ≤8 mm; SUV max , 0.3-1.2; TBR, 1.0-2.7). In the SRS group, 4/6 lesions were defined as "MRI positive," whereas 2/6 lesions were defined as "MRI negative" indicative of radiation necrosis. All 6 lesions were detected with PET (D max MR , ≥15 mm; SUV max , 1.4-4.2; TBR, 3.6-12.6). PET volumes correlated and were comparable in size with contrast-enhanced MRI volumes but were only partially congruent (mean DSC, 0.66). All time-activity curves had an early peak, followed by a plateau or a decreasing slope.

CONCLUSIONS

18 F-FACBC PET demonstrated uptake in brain metastases from cancer of different origins (lung, gastrointestinal tract, breast, thyroid, and malignant melanoma). However, 18 F-FACBC PET/MRI did not improve detection of brain metastases compared with MRI but might detect tumor tissue beyond contrast enhancement on MRI. 18 F-FACBC PET should be further evaluated in recurrent brain metastases.

A zero-dose synthetic baseline for the personalized analysis of 2-Deoxy-2-[18F]fluoroglucose: 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 synthesized pseudo-CT for MR high-resolution pediatric cranial bone imaging (MR-HiPCB)

PURPOSE

CT is routinely used to detect cranial abnormalities in pediatric patients with head trauma or craniosynostosis. This study aimed to develop a deep learning method to synthesize pseudo-CT (pCT) images for MR high-resolution pediatric cranial bone imaging to eliminating ionizing radiation from CT.

METHODS

3D golden-angle stack-of-stars MRI were obtained from 44 pediatric participants. Two patch-based residual UNets were trained using paired MR and CT patches randomly selected from the whole head (NetWH) or in the vicinity of bone, fractures/sutures, or air (NetBA) to synthesize pCT. A third residual UNet was trained to generate a binary brain mask using only MRI. The pCT images from NetWH (pCTNetWH ) in the brain area and NetBA (pCTNetBA ) in the nonbrain area were combined to generate pCTCom . A manual processing method using inverted MR images was also employed for comparison.

RESULTS

pCTCom (68.01 ± 14.83 HU) had significantly smaller mean absolute errors (MAEs) than pCTNetWH (82.58 ± 16.98 HU, P < 0.0001) and pCTNetBA (91.32 ± 17.2 HU, P < 0.0001) in the whole head. Within cranial bone, the MAE of pCTCom (227.92 ± 46.88 HU) was significantly lower than pCTNetWH (287.85 ± 59.46 HU, P < 0.0001) but similar to pCTNetBA (230.20 ± 46.17 HU). Dice similarity coefficient of the segmented bone was significantly higher in pCTCom (0.90 ± 0.02) than in pCTNetWH (0.86 ± 0.04, P < 0.0001), pCTNetBA (0.88 ± 0.03, P < 0.0001), and inverted MR (0.71 ± 0.09, P < 0.0001). Dice similarity coefficient from pCTCom demonstrated significantly reduced age dependence than inverted MRI. Furthermore, pCTCom provided excellent suture and fracture visibility comparable to CT.

CONCLUSION

MR high-resolution pediatric cranial bone imaging may facilitate the clinical translation of a radiation-free MR cranial bone imaging method for pediatric patients.

A deep learning-based whole-body solution for PET/MRI attenuation correction

BACKGROUND

Deep convolutional neural networks have demonstrated robust and reliable PET attenuation correction (AC) as an alternative to conventional AC methods in integrated PET/MRI systems. However, its whole-body implementation is still challenging due to anatomical variations and the limited MRI field of view. The aim of this study is to investigate a deep learning (DL) method to generate voxel-based synthetic CT (sCT) from Dixon MRI and use it as a whole-body solution for PET AC in a PET/MRI system.

MATERIALS AND METHODS

Fifteen patients underwent PET/CT followed by PET/MRI with whole-body coverage from skull to feet. We performed MRI truncation correction and employed co-registered MRI and CT images for training and leave-one-out cross-validation. The network was pretrained with region-specific images. The accuracy of the AC maps and reconstructed PET images were assessed by performing a voxel-wise analysis and calculating the quantification error in SUV obtained using DL-based sCT (PET_sCT) and a vendor-provided atlas-based method (PET_Atlas), with the CT-based reconstruction (PET_CT) serving as the reference. In addition, region-specific analysis was performed to compare the performances of the methods in brain, lung, liver, spine, pelvic bone, and aorta.

RESULTS

Our DL-based method resulted in better estimates of AC maps with a mean absolute error of 62 HU, compared to 109 HU for the atlas-based method. We found an excellent voxel-by-voxel correlation between PET_CT and PET_sCT (R² = 0.98). The absolute percentage difference in PET quantification for the entire image was 6.1% for PET_sCT and 11.2% for PET_Atlas. The regional analysis showed that the average errors and the variability for PET_sCT were lower than PET_Atlas in all regions. The largest errors were observed in the lung, while the smallest biases were observed in the brain and liver.

CONCLUSIONS

Experimental results demonstrated that a DL approach for whole-body PET AC in PET/MRI is feasible and allows for more accurate results compared with conventional methods. Further evaluation using a larger training cohort is required for more accurate and robust performance.

Simultaneous PET/MRI: The future gold standard for characterizing motor neuron disease-A clinico-radiological and neuroscientific perspective

Neuroimaging assessment of motor neuron disease has turned into a cornerstone of its clinical workup. Amyotrophic lateral sclerosis (ALS), as a paradigmatic motor neuron disease, has been extensively studied by advanced neuroimaging methods, including molecular imaging by MRI and PET, furthering finer and more specific details of the cascade of ALS neurodegeneration and symptoms, facilitated by multicentric studies implementing novel methodologies. With an increase in multimodal neuroimaging data on ALS and an exponential improvement in neuroimaging technology, the need for harmonization of protocols and integration of their respective findings into a consistent model becomes mandatory. Integration of multimodal data into a model of a continuing cascade of functional loss also calls for the best attempt to correlate the different molecular imaging measurements as performed at the shortest inter-modality time intervals possible. As outlined in this perspective article, simultaneous PET/MRI, nowadays available at many neuroimaging research sites, offers the perspective of a one-stop shop for reproducible imaging biomarkers on neuronal damage and has the potential to become the new gold standard for characterizing motor neuron disease from the clinico-radiological and neuroscientific perspectives.

Attenuation Coefficient Estimation for PET/MRI With Bayesian Deep Learning Pseudo-CT and Maximum-Likelihood Estimation of Activity and Attenuation

A major remaining challenge for magnetic resonance-based attenuation correction methods (MRAC) is their susceptibility to sources of magnetic resonance imaging (MRI) artifacts (e.g., implants and motion) and uncertainties due to the limitations of MRI contrast (e.g., accurate bone delineation and density, and separation of air/bone). We propose using a Bayesian deep convolutional neural network that in addition to generating an initial pseudo-CT from MR data, it also produces uncertainty estimates of the pseudo-CT to quantify the limitations of the MR data. These outputs are combined with the maximum-likelihood estimation of activity and attenuation (MLAA) reconstruction that uses the PET emission data to improve the attenuation maps. With the proposed approach uncertainty estimation and pseudo-CT prior for robust MLAA (UpCT-MLAA), we demonstrate accurate estimation of PET uptake in pelvic lesions and show recovery of metal implants. In patients without implants, UpCT-MLAA had acceptable but slightly higher root-mean-squared-error (RMSE) than Zero-echotime and Dixon Deep pseudo-CT when compared to CTAC. In patients with metal implants, MLAA recovered the metal implant; however, anatomy outside the implant region was obscured by noise and crosstalk artifacts. Attenuation coefficients from the pseudo-CT from Dixon MRI were accurate in normal anatomy; however, the metal implant region was estimated to have attenuation coefficients of air. UpCT-MLAA estimated attenuation coefficients of metal implants alongside accurate anatomic depiction outside of implant regions.

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.

Monte Carlo Characterization of the Trimage Brain PET System

The TRIMAGE project aims to develop a brain-dedicated PET/MR/EEG (Positron Emission Tomography/Magnetic Resonance/Electroencephalogram) system that is able to perform simultaneous PET, MR and EEG acquisitions. The PET component consists of a full ring with 18 sectors. Each sector includes three square detector modules based on dual sstaggered LYSO:Ce matrices read out by SiPMs. Using Monte Carlo simulations and following NEMA (National Electrical Manufacturers Association) guidelines, image quality procedures have been applied to evaluate the performance of the PET component of the system. The performance are reported in terms of spatial resolution, uniformity, recovery coefficient, spill over ratio, noise equivalent count rate (NECR) and scatter fraction. The results show that the TRIMAGE system is at the top of the current brain PET technologies.

Application of artificial intelligence in brain molecular imaging

Initial development of artificial Intelligence (AI) and machine learning (ML) dates back to the mid-twentieth century. A growing awareness of the potential for AI, as well as increases in computational resources, research, and investment are rapidly advancing AI applications to medical imaging and, specifically, brain molecular imaging. AI/ML can improve imaging operations and decision making, and potentially perform tasks that are not readily possible by physicians, such as predicting disease prognosis, and identifying latent relationships from multi-modal clinical information. The number of applications of image-based AI algorithms, such as convolutional neural network (CNN), is increasing rapidly. The applications for brain molecular imaging (MI) include image denoising, PET and PET/MRI attenuation correction, image segmentation and lesion detection, parametric image formation, and the detection/diagnosis of Alzheimer's disease and other brain disorders. When effectively used, AI will likely improve the quality of patient care, instead of replacing radiologists. A regulatory framework is being developed to facilitate AI adaptation for medical imaging.

EANM procedure guidelines for brain PET imaging using [18F]FDG, version 3

The present procedural guidelines summarize the current views of the EANM Neuro-Imaging Committee (NIC). The purpose of these guidelines is to assist nuclear medicine practitioners in making recommendations, performing, interpreting, and reporting results of [¹⁸F]FDG-PET imaging of the brain. The aim is to help achieve a high-quality standard of [¹⁸F]FDG brain imaging and to further increase the diagnostic impact of this technique in neurological, neurosurgical, and psychiatric practice. The present document replaces a former version of the guidelines that have been published in 2009. These new guidelines include an update in the light of advances in PET technology such as the introduction of digital PET and hybrid PET/MR systems, advances in individual PET semiquantitative analysis, and current broadening clinical indications (e.g., for encephalitis and brain lymphoma). Further insight has also become available about hyperglycemia effects in patients who undergo brain [¹⁸F]FDG-PET. Accordingly, the patient preparation procedure has been updated. Finally, most typical brain patterns of metabolic changes are summarized for neurodegenerative diseases. The present guidelines are specifically intended to present information related to the European practice. The information provided should be taken in the context of local conditions and regulations.

Deep-learning-based attenuation correction in dynamic [15O]H2O studies using PET/MRI in healthy volunteers

Quantitative [¹⁵O]H₂O positron emission tomography (PET) is the accepted reference method for regional cerebral blood flow (rCBF) quantification. To perform reliable quantitative [¹⁵O]H₂O-PET studies in PET/MRI scanners, MRI-based attenuation-correction (MRAC) is required. Our aim was to compare two MRAC methods (RESOLUTE and DeepUTE) based on ultrashort echo-time with computed tomography-based reference standard AC (CTAC) in dynamic and static [¹⁵O]H₂O-PET. We compared rCBF from quantitative perfusion maps and activity concentration distribution from static images between AC methods in 25 resting [¹⁵O]H₂O-PET scans from 14 healthy men at whole-brain, regions of interest and voxel-wise levels. Average whole-brain CBF was 39.9 ± 6.0, 39.0 ± 5.8 and 40.0 ± 5.6 ml/100 g/min for CTAC, RESOLUTE and DeepUTE corrected studies respectively. RESOLUTE underestimated whole-brain CBF by 2.1 ± 1.50% and rCBF in all regions of interest (range -2.4%- -1%) compared to CTAC. DeepUTE showed significant rCBF overestimation only in the occipital lobe (0.6 ± 1.1%). Both MRAC methods showed excellent correlation on rCBF and activity concentration with CTAC, with slopes of linear regression lines between 0.97 and 1.01 and R² over 0.99. In conclusion, RESOLUTE and DeepUTE provide AC information comparable to CTAC in dynamic [¹⁵O]H₂O-PET but RESOLUTE is associated with a small but systematic underestimation.

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.

CERMEP-IDB-MRXFDG: a database of 37 normal adult human brain [18F]FDG PET, T1 and FLAIR MRI, and CT images available for research

We present a database of cerebral PET FDG and anatomical MRI for 37 normal adult human subjects (CERMEP-IDB-MRXFDG). Thirty-nine participants underwent static [18F]FDG PET/CT and MRI, resulting in [18F]FDG PET, T1 MPRAGE MRI, FLAIR MRI, and CT images. Two participants were excluded after visual quality control. We describe the acquisition parameters, the image processing pipeline and provide participants' individual demographics (mean age 38 ± 11.5 years, range 23-65, 20 women). Volumetric analysis of the 37 T1 MRIs showed results in line with the literature. A leave-one-out assessment of the 37 FDG images using Statistical Parametric Mapping (SPM) yielded a low number of false positives after exclusion of artefacts. The database is stored in three different formats, following the BIDS common specification: (1) DICOM (data not processed), (2) NIFTI (multimodal images coregistered to PET subject space), (3) NIFTI normalized (images normalized to MNI space). Bona fide researchers can request access to the database via a short form.

Feasibility of Deep Learning-Guided Attenuation and Scatter Correction of Whole-Body 68Ga-PSMA PET Studies in the Image Domain

OBJECTIVE

This study evaluates the feasibility of direct scatter and attenuation correction of whole-body 68Ga-PSMA PET images in the image domain using deep learning.

METHODS

Whole-body 68Ga-PSMA PET images of 399 subjects were used to train a residual deep learning model, taking PET non-attenuation-corrected images (PET-nonAC) as input and CT-based attenuation-corrected PET images (PET-CTAC) as target (reference). Forty-six whole-body 68Ga-PSMA PET images were used as an independent validation dataset. For validation, synthetic deep learning-based attenuation-corrected PET images were assessed considering the corresponding PET-CTAC images as reference. The evaluation metrics included the mean absolute error (MAE) of the SUV, peak signal-to-noise ratio, and structural similarity index (SSIM) in the whole body, as well as in different regions of the body, namely, head and neck, chest, and abdomen and pelvis.

RESULTS

The deep learning-guided direct attenuation and scatter correction produced images of comparable visual quality to PET-CTAC images. It achieved an MAE, relative error (RE%), SSIM, and peak signal-to-noise ratio of 0.91 ± 0.29 (SUV), -2.46% ± 10.10%, 0.973 ± 0.034, and 48.171 ± 2.964, respectively, within whole-body images of the independent external validation dataset. The largest RE% was observed in the head and neck region (-5.62% ± 11.73%), although this region exhibited the highest value of SSIM metric (0.982 ± 0.024). The MAE (SUV) and RE% within the different regions of the body were less than 2.0% and 6%, respectively, indicating acceptable performance of the deep learning model.

CONCLUSIONS

This work demonstrated the feasibility of direct attenuation and scatter correction of whole-body 68Ga-PSMA PET images in the image domain using deep learning with clinically tolerable errors. The technique has the potential of performing attenuation correction on stand-alone PET or PET/MRI systems.

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.

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.

Pitfalls on PET/MRI

A decade of PET/MRI clinical imaging has passed and many of the pitfalls are similar to those on earlier studies. However, techniques to overcome them have emerged and continue to develop. Although clinically significant lung nodules are demonstrable, smaller nodules may be detected using ultrashort/zero echo-time (TE) lung MRI. Fast reconstruction ultrashort TE sequences have also been used to achieve high-resolution lung MRI even with free-breathing. The introduction and improvement of time-of-flight scanners and increasing the axial length of the PET detector arrays have more than doubled the sensitivity of the PET part of the system. MRI for attenuation correction has provided many potential pitfalls, including misclassification of tissue classes based on MRI information for attenuation correction. Although the use of short echo times have helped to address these pitfalls, one of the most exciting developments has been the use of deep learning algorithms and computational neural networks to rapidly provide soft tissue, fat, bone and air information for the attenuation correction as a supplement to the attenuation correction information from fat-water imaging. Challenges with motion correction, particularly respiratory and cardiac remain but are being addressed with respiratory monitors and using PET data. In order to address truncation artefacts, the system manufacturers have developed methods to extend the MR field-of-view for the purpose of the attenuation and scatter corrections. General pitfalls like stitching of body sections for individual studies, optimum delivery of images for viewing and reporting, and resource implications for the sheer volume of data generated remain Methods to overcome these pitfalls serve as a strong foundation for the future of PET/MRI. Advances in the underlying technology with significant evolution in hard-ware and software and the exiting developments in use of deep learning algorithms and computational neural networks will drive the next decade of PET/MRI imaging.

Franken-CT: Head and Neck MR-Based Pseudo-CT Synthesis Using Diverse Anatomical Overlapping MR-CT Scans

Typically, pseudo-Computerized Tomography (CT) synthesis schemes proposed in the literature rely on complete atlases acquired with the same field of view (FOV) as the input volume. However, clinical CTs are usually acquired in a reduced FOV to decrease patient ionization. In this work, we present the Franken-CT approach, showing how the use of a non-parametric atlas composed of diverse anatomical overlapping Magnetic Resonance (MR)-CT scans and deep learning methods based on the U-net architecture enable synthesizing extended head and neck pseudo-CTs. Visual inspection of the results shows the high quality of the pseudo-CT and the robustness of the method, which is able to capture the details of the bone contours despite synthesizing the resulting image from knowledge obtained from images acquired with a completely different FOV. The experimental Zero-Normalized Cross-Correlation (ZNCC) reports 0.9367 ± 0.0138 (mean ± SD) and 95% confidence interval (0.9221, 0.9512); the experimental Mean Absolute Error (MAE) reports 73.9149 ± 9.2101 HU and 95% confidence interval (66.3383, 81.4915); the Structural Similarity Index Measure (SSIM) reports 0.9943 ± 0.0009 and 95% confidence interval (0.9935, 0.9951); and the experimental Dice coefficient for bone tissue reports 0.7051 ± 0.1126 and 95% confidence interval (0.6125, 0.7977). The voxel-by-voxel correlation plot shows an excellent correlation between pseudo-CT and ground-truth CT Hounsfield Units (m = 0.87; adjusted R2 = 0.91; p < 0.001). The Bland–Altman plot shows that the average of the differences is low (−38.6471 ± 199.6100; 95% CI (−429.8827, 352.5884)). This work serves as a proof of concept to demonstrate the great potential of deep learning methods for pseudo-CT synthesis and their great potential using real clinical datasets.

18F-FACBC PET/MRI in the evaluation of human brain metastases: a case report

Background

Patients with metastatic cancer to the brain have a poor prognosis. In clinical practice, MRI is used to delineate, diagnose and plan treatment of brain metastases. However, MRI alone is limited in detecting micro-metastases, delineating lesions and discriminating progression from pseudo-progression. Combined PET/MRI utilises superior soft tissue images from MRI and metabolic data from PET to evaluate tumour structure and function. The amino acid PET tracer ¹⁸F-FACBC has shown promising results in discriminating high- and low-grade gliomas, but there are currently no reports on its use on brain metastases. This is the first study to evaluate the use of ¹⁸F-FACBC on brain metastases.

Case presentation

A middle-aged female patient with brain metastases was evaluated using hybrid PET/MRI with ¹⁸F-FACBC before and after stereotactic radiotherapy, and at suspicion of recurrence. Static/dynamic PET and contrast-enhanced T1 MRI data were acquired and analysed. This case report includes the analysis of four ¹⁸F-FACBC PET/MRI examinations, investigating their utility in evaluating functional and structural metastasis properties.

Conclusion

Analysis showed high tumour-to-background ratios in brain metastases compared to other amino acid PET tracers, including high uptake in a very small cerebellar metastasis, suggesting that ¹⁸F-FACBC PET can provide early detection of otherwise overlooked metastases. Further studies to determine a threshold for ¹⁸F-FACBC brain tumour boundaries and explore its utility in clinical practice should be performed.

Quantitative Molecular Positron Emission Tomography Imaging Using Advanced Deep Learning Techniques

The widespread availability of high-performance computing and the popularity of artificial intelligence (AI) with machine learning and deep learning (ML/DL) algorithms at the helm have stimulated the development of many applications involving the use of AI-based techniques in molecular imaging research. Applications reported in the literature encompass various areas, including innovative design concepts in positron emission tomography (PET) instrumentation, quantitative image reconstruction and analysis techniques, computer-aided detection and diagnosis, as well as modeling and prediction of outcomes. This review reflects the tremendous interest in quantitative molecular imaging using ML/DL techniques during the past decade, ranging from the basic principles of ML/DL techniques to the various steps required for obtaining quantitatively accurate PET data, including algorithms used to denoise or correct for physical degrading factors as well as to quantify tracer uptake and metabolic tumor volume for treatment monitoring or radiation therapy treatment planning and response prediction.This review also addresses future opportunities and current challenges facing the adoption of ML/DL approaches and their role in multimodality imaging.

Transfer Learning in Magnetic Resonance Brain Imaging: A Systematic Review

(1) Background: Transfer learning refers to machine learning techniques that focus on acquiring knowledge from related tasks to improve generalization in the tasks of interest. In magnetic resonance imaging (MRI), transfer learning is important for developing strategies that address the variation in MR images from different imaging protocols or scanners. Additionally, transfer learning is beneficial for reutilizing machine learning models that were trained to solve different (but related) tasks to the task of interest. The aim of this review is to identify research directions, gaps in knowledge, applications, and widely used strategies among the transfer learning approaches applied in MR brain imaging; (2) Methods: We performed a systematic literature search for articles that applied transfer learning to MR brain imaging tasks. We screened 433 studies for their relevance, and we categorized and extracted relevant information, including task type, application, availability of labels, and machine learning methods. Furthermore, we closely examined brain MRI-specific transfer learning approaches and other methods that tackled issues relevant to medical imaging, including privacy, unseen target domains, and unlabeled data; (3) Results: We found 129 articles that applied transfer learning to MR brain imaging tasks. The most frequent applications were dementia-related classification tasks and brain tumor segmentation. The majority of articles utilized transfer learning techniques based on convolutional neural networks (CNNs). Only a few approaches utilized clearly brain MRI-specific methodology, and considered privacy issues, unseen target domains, or unlabeled data. We proposed a new categorization to group specific, widely-used approaches such as pretraining and fine-tuning CNNs; (4) Discussion: There is increasing interest in transfer learning for brain MRI. Well-known public datasets have clearly contributed to the popularity of Alzheimer's diagnostics/prognostics and tumor segmentation as applications. Likewise, the availability of pretrained CNNs has promoted their utilization. Finally, the majority of the surveyed studies did not examine in detail the interpretation of their strategies after applying transfer learning, and did not compare their approach with other transfer learning approaches.

Artificial intelligence techniques support nuclear medicine modalities to improve the diagnosis of Parkinson’s disease and Parkinsonian syndromes

Purpose

The aim of this review is to discuss the most significant contributions about the role of Artificial Intelligence (AI) techniques to support the diagnosis of movement disorders through nuclear medicine modalities.

Methods

The work is based on a selection of papers available on PubMed, Scopus and Web of Sciences. Articles not written in English were not considered in this study.

Results

Many papers are available concerning the increasing contribution of machine learning techniques to classify Parkinson’s disease (PD), Parkinsonian syndromes and Essential Tremor (ET) using data derived from brain SPECT with dopamine transporter radiopharmaceuticals. Other papers investigate by AI techniques data obtained by 123I-MIBG myocardial scintigraphy to differentially diagnose PD and other Parkinsonian syndromes.

Conclusion

The recent literature provides strong evidence that AI techniques can play a fundamental role in the diagnosis of movement disorders by means of nuclear medicine modalities, therefore paving the way towards personalized medicine.