Predictive uncertainty in deep learning-based MR image reconstruction using deep ensembles: Evaluation on the fastMRI data set.

PURPOSE: To estimate pixel-wise predictive uncertainty for deep learning-based MR image reconstruction and to examine the impact of domain shifts and architecture robustness. METHODS: Uncertainty prediction could provide a measure for robustness of deep learning (DL)-based MR image reconstruction from undersampled data. DL methods bear the risk of inducing reconstruction errors like in-painting of unrealistic structures or missing pathologies. These errors may be obscured by visual realism of DL reconstruction and thus remain undiscovered. Furthermore, most methods are task-agnostic and not well calibrated to domain shifts. We propose a strategy that estimates aleatoric (data) and epistemic (model) uncertainty, which entails training a deep ensemble (epistemic) with nonnegative log-likelihood (aleatoric) loss in addition to the conventional applied losses terms. The proposed procedure can be paired with any DL reconstruction, enabling investigations of their predictive uncertainties on a pixel level. Five different architectures were investigated on the fastMRI database. The impact on the examined uncertainty of in-distributional and out-of-distributional data with changes to undersampling pattern, imaging contrast, imaging orientation, anatomy, and pathology were explored. RESULTS: Predictive uncertainty could be captured and showed good correlation to normalized mean squared error. Uncertainty was primarily focused along the aliased anatomies and on hyperintense and hypointense regions. The proposed uncertainty measure was able to detect disease prevalence shifts. Distinct predictive uncertainty patterns were observed for changing network architectures. CONCLUSION: The proposed approach enables aleatoric and epistemic uncertainty prediction for DL-based MR reconstruction with an interpretable examination on a pixel level.

Reducing energy consumption in musculoskeletal MRI using shorter scan protocols, optimized magnet cooling patterns, and deep learning sequences.

OBJECTIVES: The unprecedented surge in energy costs in Europe, coupled with the significant energy consumption of MRI scanners in radiology departments, necessitates exploring strategies to optimize energy usage without compromising efficiency or image quality. This study investigates MR energy consumption and identifies strategies for improving energy efficiency, focusing on musculoskeletal MRI. We assess the potential savings achievable through (1) optimizing protocols, (2) incorporating deep learning (DL) accelerated acquisitions, and (3) optimizing the cooling system. MATERIALS AND METHODS: Energy consumption measurements were performed on two MRI scanners (1.5-T Aera, 1.5-T Sola) in practices in Munich, Germany, between December 2022 and March 2023. Three levels of energy reduction measures were implemented and compared to the baseline. Wilcoxon signed-rank test with Bonferroni correction was conducted to evaluate the impact of sequence scan times and energy consumption. RESULTS: Our findings showed significant energy savings by optimizing protocol settings and implementing DL technologies. Across all body regions, the average reduction in energy consumption was 72% with DL and 31% with economic protocols, accompanied by time reductions of 71% (DL) and 18% (economic protocols) compared to baseline. Optimizing the cooling system during the non-scanning time showed a 30% lower energy consumption. CONCLUSION: Implementing energy-saving strategies, including economic protocols, DL accelerated sequences, and optimized magnet cooling, can significantly reduce energy consumption in MRI scanners. Radiology departments and practices should consider adopting these strategies to improve energy efficiency and reduce costs. CLINICAL RELEVANCE STATEMENT: MRI scanner energy consumption can be substantially reduced by incorporating protocol optimization, DL accelerated acquisition, and optimized magnetic cooling into daily practice, thereby cutting costs and environmental impact. KEY POINTS: Optimization of protocol settings reduced energy consumption by 31% and imaging time by 18%. DL technologies led to a 72% reduction in energy consumption of and a 71% reduction in time, compared to the standard MRI protocol. During non-scanning times, activating Eco power mode (EPM) resulted in a 30% reduction in energy consumption, saving 4881 € ($5287) per scanner annually.

Applications of Artificial Intelligence for Pediatric Cancer Imaging.

Artificial intelligence (AI) is transforming the medical imaging of adult patients. However, its utilization in pediatric oncology imaging remains constrained, in part due to the inherent scarcity of data associated with childhood cancers. Pediatric cancers are rare, and imaging technologies are evolving rapidly, leading to insufficient data of a particular type to effectively train these algorithms. The small market size of pediatric patients compared with adult patients could also contribute to this challenge, as market size is a driver of commercialization. This review provides an overview of the current state of AI applications for pediatric cancer imaging, including applications for medical image acquisition, processing, reconstruction, segmentation, diagnosis, staging, and treatment response monitoring. Although current developments are promising, impediments due to the diverse anatomies of growing children and nonstandardized imaging protocols have led to limited clinical translation thus far. Opportunities include leveraging reconstruction algorithms to achieve accelerated low-dose imaging and automating the generation of metric-based staging and treatment monitoring scores. Transfer learning of adult-based AI models to pediatric cancers, multiinstitutional data sharing, and ethical data privacy practices for pediatric patients with rare cancers will be keys to unlocking the full potential of AI for clinical translation and improving outcomes for these young patients.

Low-count whole-body PET/MRI restoration: an evaluation of dose reduction spectrum and five state-of-the-art artificial intelligence models.

PURPOSE: To provide a holistic and complete comparison of the five most advanced AI models in the augmentation of low-dose 18F-FDG PET data over the entire dose reduction spectrum. METHODS: In this multicenter study, five AI models were investigated for restoring low-count whole-body PET/MRI, covering convolutional benchmarks - U-Net, enhanced deep super-resolution network (EDSR), generative adversarial network (GAN) - and the most cutting-edge image reconstruction transformer models in computer vision to date - Swin transformer image restoration network (SwinIR) and EDSR-ViT (vision transformer). The models were evaluated against six groups of count levels representing the simulated 75%, 50%, 25%, 12.5%, 6.25%, and 1% (extremely ultra-low-count) of the clinical standard 3 MBq/kg 18F-FDG dose. The comparisons were performed upon two independent cohorts - (1) a primary cohort from Stanford University and (2) a cross-continental external validation cohort from Tübingen University - in order to ensure the findings are generalizable. A total of 476 original count and simulated low-count whole-body PET/MRI scans were incorporated into this analysis. RESULTS: For low-count PET restoration on the primary cohort, the mean structural similarity index (SSIM) scores for dose 6.25% were 0.898 (95% CI, 0.887-0.910) for EDSR, 0.893 (0.881-0.905) for EDSR-ViT, 0.873 (0.859-0.887) for GAN, 0.885 (0.873-0.898) for U-Net, and 0.910 (0.900-0.920) for SwinIR. In continuation, SwinIR and U-Net's performances were also discreetly evaluated at each simulated radiotracer dose levels. Using the primary Stanford cohort, the mean diagnostic image quality (DIQ; 5-point Likert scale) scores of SwinIR restoration were 5 (SD, 0) for dose 75%, 4.50 (0.535) for dose 50%, 3.75 (0.463) for dose 25%, 3.25 (0.463) for dose 12.5%, 4 (0.926) for dose 6.25%, and 2.5 (0.534) for dose 1%. CONCLUSION: Compared to low-count PET images, with near-to or nondiagnostic images at higher dose reduction levels (up to 6.25%), both SwinIR and U-Net significantly improve the diagnostic quality of PET images. A radiotracer dose reduction to 1% of the current clinical standard radiotracer dose is out of scope for current AI techniques.

Noninvasive, longitudinal imaging-based analysis of body adipose tissue and water composition in a melanoma mouse model and in immune checkpoint inhibitor-treated metastatic melanoma patients.

BACKGROUND: As cancer cachexia (CC) is associated with cancer progression, early identification would be beneficial. The aim of this study was to establish a workflow for automated MRI-based segmentation of visceral (VAT) and subcutaneous adipose tissue (SCAT) and lean tissue water (LTW) in a B16 melanoma animal model, monitor diseases progression and transfer the protocol to human melanoma patients for therapy assessment. METHODS: For in vivo monitoring of CC B16 melanoma-bearing and healthy mice underwent longitudinal three-point DIXON MRI (days 3, 12, 17 after subcutaneous tumor inoculation). In a prospective clinical study, 18 metastatic melanoma patients underwent MRI before, 2 and 12 weeks after onset of checkpoint inhibitor therapy (CIT; n = 16). We employed an in-house MATLAB script for automated whole-body segmentation for detection of VAT, SCAT and LTW. RESULTS: B16 mice exhibited a CC phenotype and developed a reduced VAT volume compared to baseline (B16 - 249.8 µl, - 25%; controls + 85.3 µl, + 10%, p = 0.003) and to healthy controls. LTW was increased in controls compared to melanoma mice. Five melanoma patients responded to CIT, 7 progressed, and 6 displayed a mixed response. Responding patients exhibited a very limited variability in VAT and SCAT in contrast to others. Interestingly, the LTW was decreased in CIT responding patients (- 3.02% ± 2.67%; p = 0.0034) but increased in patients with progressive disease (+ 1.97% ± 2.19%) and mixed response (+ 4.59% ± 3.71%). CONCLUSION: MRI-based segmentation of fat and water contents adds essential additional information for monitoring the development of CC in mice and metastatic melanoma patients during CIT or other treatment approaches.

Artificial intelligence enables whole-body positron emission tomography scans with minimal radiation exposure.

PURPOSE: To generate diagnostic 18F-FDG PET images of pediatric cancer patients from ultra-low-dose 18F-FDG PET input images, using a novel artificial intelligence (AI) algorithm. METHODS: We used whole-body 18F-FDG-PET/MRI scans of 33 children and young adults with lymphoma (3-30 years) to develop a convolutional neural network (CNN), which combines inputs from simulated 6.25% ultra-low-dose 18F-FDG PET scans and simultaneously acquired MRI scans to produce a standard-dose 18F-FDG PET scan. The image quality of ultra-low-dose PET scans, AI-augmented PET scans, and clinical standard PET scans was evaluated by traditional metrics in computer vision and by expert radiologists and nuclear medicine physicians, using Wilcoxon signed-rank tests and weighted kappa statistics. RESULTS: The peak signal-to-noise ratio and structural similarity index were significantly higher, and the normalized root-mean-square error was significantly lower on the AI-reconstructed PET images compared to simulated 6.25% dose images (p < 0.001). Compared to the ground-truth standard-dose PET, SUVmax values of tumors and reference tissues were significantly higher on the simulated 6.25% ultra-low-dose PET scans as a result of image noise. After the CNN augmentation, the SUVmax values were recovered to values similar to the standard-dose PET. Quantitative measures of the readers' diagnostic confidence demonstrated significantly higher agreement between standard clinical scans and AI-reconstructed PET scans (kappa = 0.942) than 6.25% dose scans (kappa = 0.650). CONCLUSIONS: Our CNN model could generate simulated clinical standard 18F-FDG PET images from ultra-low-dose inputs, while maintaining clinically relevant information in terms of diagnostic accuracy and quantitative SUV measurements.

Therapy Response Assessment of Pediatric Tumors with Whole-Body Diffusion-weighted MRI and FDG PET/MRI.

Background Whole-body diffusion-weighted (DW) MRI can help detect cancer with high sensitivity. However, the assessment of therapy response often requires information about tumor metabolism, which is measured with fluorine 18 fluorodeoxyglucose (FDG) PET. Purpose To compare tumor therapy response with whole-body DW MRI and FDG PET/MRI in children and young adults. Materials and Methods In this prospective, nonrandomized multicenter study, 56 children and young adults (31 male and 25 female participants; mean age, 15 years ± 4 [standard deviation]; age range, 6-22 years) with lymphoma or sarcoma underwent 112 simultaneous whole-body DW MRI and FDG PET/MRI between June 2015 and December 2018 before and after induction chemotherapy (ClinicalTrials.gov identifier: NCT01542879). The authors measured minimum tumor apparent diffusion coefficients (ADCs) and maximum standardized uptake value (SUV) of up to six target lesions and assessed therapy response after induction chemotherapy according to the Lugano classification or PET Response Criteria in Solid Tumors. The authors evaluated agreements between whole-body DW MRI- and FDG PET/MRI-based response classifications with Krippendorff α statistics. Differences in minimum ADC and maximum SUV between responders and nonresponders and comparison of timing for discordant and concordant response assessments after induction chemotherapy were evaluated with the Wilcoxon test. Results Good agreement existed between treatment response assessments after induction chemotherapy with whole-body DW MRI and FDG PET/MRI (α = 0.88). Clinical response prediction according to maximum SUV (area under the receiver operating characteristic curve = 100%; 95% confidence interval [CI]: 99%, 100%) and minimum ADC (area under the receiver operating characteristic curve = 98%; 95% CI: 94%, 100%) were similar (P = .37). Sensitivity and specificity were 96% (54 of 56 participants; 95% CI: 86%, 99%) and 100% (56 of 56 participants; 95% CI: 54%, 100%), respectively, for DW MRI and 100% (56 of 56 participants; 95% CI: 93%, 100%) and 100% (56 of 56 participants; 95% CI: 54%, 100%) for FDG PET/MRI. In eight of 56 patients who underwent imaging after induction chemotherapy in the early posttreatment phase, chemotherapy-induced changes in tumor metabolism preceded changes in proton diffusion (P = .002). Conclusion Whole-body diffusion-weighted MRI showed significant agreement with fluorine 18 fluorodeoxyglucose PET/MRI for treatment response assessment in children and young adults. © RSNA, 2020 Online supplemental material is available for this article.

PET/MRI and genetic intrapatient heterogeneity in head and neck cancers.

PURPOSE: The relation between functional imaging and intrapatient genetic heterogeneity remains poorly understood. The aim of our study was to investigate spatial sampling and functional imaging by FDG-PET/MRI to describe intrapatient tumour heterogeneity. METHODS: Six patients with oropharyngeal cancer were included in this pilot study. Two tumour samples per patient were taken and sequenced by next-generation sequencing covering 327 genes relevant in head and neck cancer. Corresponding regions were delineated on pretherapeutic FDG-PET/MRI images to extract apparent diffusion coefficients and standardized uptake values. RESULTS: Samples were collected within the primary tumour (n = 3), within the primary tumour and the involved lymph node (n = 2) as well as within two independent primary tumours (n = 1). Genetic heterogeneity of the primary tumours was limited and most driver gene mutations were found ubiquitously. Slightly increasing heterogeneity was found between primary tumours and lymph node metastases. One private predicted driver mutation within a primary tumour and one in a lymph node were found. However, the two independent primary tumours did not show any shared mutations in spite of a clinically suspected field cancerosis. No conclusive correlation between genetic heterogeneity and heterogeneity of PET/MRI-derived parameters was observed. CONCLUSION: Our limited data suggest that single sampling might be sufficient in some patients with oropharyngeal cancer. However, few driver mutations might be missed and, if feasible, spatial sampling should be considered. In two independent primary tumours, both lesions should be sequenced. Our data with a limited number of patients do not support the concept that multiparametric PET/MRI features are useful to guide biopsies for genetic tumour characterization.

Simultaneous whole-body PET/MRI with integrated multiparametric MRI for primary staging of high-risk prostate cancer.

PURPOSE: Whole-body positron emission tomography/magnetic resonance imaging (wbPET/MRI) is a promising diagnostic tool of recurrent prostate cancer (PC), but its role in primary staging of high-risk PC (hrPC) is not well defined. Thus, the aim was to compare the diagnostic accuracy for T-staging of PET-blinded reading (PBR) and PET/MRI. METHODS: In this prospective study, hrPC patients scheduled to radical prostatectomy (RPx) with extended lymphadenectomy (eLND) were staged with wbPET/MRI and either 68Ga-PSMA-11 or 11C-choline including simultaneous multiparametric MRI (mpMRI). Images were assessed in two sessions, first as PBR (mpMRI and wbMRI) and second as wbPET/MRI. Prostate Imaging Reporting and Data System criteria (PIRADS v2) were used for T-staging. Results were correlated with the exact anatomical localization and extension as defined by histopathology. Diagnostic accuracy of cTNM stage according to PBR was compared to pathological pTNM stage as reference standard. RESULTS: Thirty-four patients underwent wbPET/MRI of 68Ga-PSMA-11 (n = 17) or 11C-choline (n = 17). Twenty-four patients meeting the inclusion criteria of localized disease ± nodal disease based on imaging results underwent RPx and eLND, whereas ten patients were excluded from analysis due to metastatic disease. T-stage was best defined by mpMRI with underestimation of tumor lesion size by PET for both tracers. N-stage yielded a per patient sensitivity/specificity comparable to PBR. CONCLUSION: MpMRI is the primary modality for T-staging in hrPC as PET underestimated T-stage in direct comparison to final pathology. In this selected study, cohort MRI shows no inferiority compared to wbPET/MRI considering N-staging.

Impact of PET/CT on clinical management in patients with cancer of unknown primary-a PET/CT registry study.

OBJECTIVE: To evaluate the impact of PET/CT on clinical management in patients with cancer of unknown primary (CUP). METHODS: A cohort of patients with CUP undergoing PET/CT was prospectively enrolled in a local PET/CT registry study between April 2013 and June 2018. Questionnaire data from referring physicians on intended patient management prior and after PET/CT were recorded including items on the intended treatment concept and intended additional diagnostics. Changes in management after PET/CT were recorded. Patient outcome of different cohorts was analyzed for overall survival drawn from patient records. RESULTS: One hundred fifty-five patients (53 female; 63.4 ± 12.1 years) were included. Intended therapeutic management was revised in 45.8% of patients after PET/CT, including major changes affecting the intended treatment goal in 26.5% of patients and minor changes (therapy adjustments) in 19.3% of patients. Invasive and additional diagnostic procedures were intended in 25.8% and 63.2% prior PET/CT and 13.5% and 6.5% after PET/CT. PET/CT-based curative therapy concepts were associated with significantly longer patient survival (4.7 ± 0.3 years) than palliative therapy concepts (1.8 ± 0.5 years, p = .0001). Patients with cervical CUP showed a significantly longer survival (4.3 ± 0.3 years) than patients with extracervical CUP (3.5 ± 0.5 years, p = .01). The identification of the primary did not significantly affect survival. CONCLUSION: This registry study confirms previous studies reporting that PET/CT significantly influences clinical management in patients with CUP, helping physicians to select a more individualized treatment and to avoid additional diagnostics. Furthermore, we could confirm that tumor localization and extent as shown by PET/CT have a significant impact on patient prognosis. KEY POINTS: • PET/CT significantly influences intended clinical management in patients with CUP, helping physicians to select a more individualized treatment and to avoid additional diagnostics. • Tumor localization and extent as shown by PET/CT have a significant impact on patient prognosis. • The identification of the primary tumor has no significant impact on overall patient survival.

New severity assessment in cystic fibrosis: signal intensity and lung volume compared to LCI and FEV1: preliminary results.

OBJECTIVES: Magnetic resonance imaging (MRI) aids diagnosis in cystic fibrosis (CF) but its use in quantitative severity assessment is under research. This study aims to assess changes in signal intensity (SI) and lung volumes (Vol) during functional MRI and their use as a severity assessment tool in CF patients. METHODS: The CF intra-hospital standard chest 1.5 T MRI protocol comprises of very short echo-time sequences in submaximal in- and expiration for functional information. Quantitative measurements (Vol/SI at in- and expiration, relative differences (Vol_delta/SI_delta), and cumulative histograms for normalized SI values across the expiratory lung volume) were assessed for correlation to pulmonary function: lung clearance index (LCI) and forced expiratory volume in 1 s (FEV1). RESULTS: In 49 patients (26 male, mean age 17 ± 7 years) significant correlation of Vol_delta and SI_delta (R = 0.86; p < 0.0001) during respiration was observed. Individual cumulated histograms enabled severity disease differentiation (mild, severe) to be visualized (defined by functional parameter: LCI > 10). The expiratory volume at a relative SI of 100% correlated significantly to LCI (R = 0.676 and 0.627; p < 0.0001) and FEV1 (R = - 0.847 and - 0.807; p < 0.0001). Clustering patients according to Vol_SI_100 showed that an amount of ≤ 4% was related to normal, while an amount of > 4% was associated with pathological pulmonary function values. CONCLUSION: Functional pulmonary MRI provides a radiation-free severity assessment tool and can contribute to early detection of lung impairment in CF. Lung volume with SI below 100% of the inspiratory volume represents overinflated tissue; an amount of 4% of the expiratory lung volume was a relevant turning point. KEY POINTS: • Signal intensity and lung volumes are used as potential metric parameters for lung impairment. • Quantification of trapped air impacts on therapy management. • Functional pulmonary MRI can contribute to early detection of lung impairment.

Retrospective correction of motion-affected MR images using deep learning frameworks.

PURPOSE: Motion is 1 extrinsic source for imaging artifacts in MRI that can strongly deteriorate image quality and, thus, impair diagnostic accuracy. In addition to involuntary physiological motion such as respiration and cardiac motion, intended and accidental patient movements can occur. Any impairment by motion artifacts can reduce the reliability and precision of the diagnosis and a motion-free reacquisition can become time- and cost-intensive. Numerous motion correction strategies have been proposed to reduce or prevent motion artifacts. These methods have in common that they need to be applied during the actual measurement procedure with a-priori knowledge about the expected motion type and appearance. For retrospective motion correction and without the existence of any a-priori knowledge, this problem is still challenging. METHODS: We propose the use of deep learning frameworks to perform retrospective motion correction in a reference-free setting by learning from pairs of motion-free and motion-affected images. For this image-to-image translation problem, we propose and compare a variational auto encoder and generative adversarial network. Feasibility and influences of motion type and optimal architecture are investigated by blinded subjective image quality assessment and by quantitative image similarity metrics. RESULTS: We observed that generative adversarial network-based motion correction is feasible producing near-realistic motion-free images as confirmed by blinded subjective image quality assessment. Generative adversarial network-based motion correction accordingly resulted in images with high evaluation metrics (normalized root mean squared error <0.08, structural similarity index >0.8, normalized mutual information >0.9). CONCLUSION: Deep learning-based retrospective restoration of motion artifacts is feasible resulting in near-realistic motion-free images. However, the image translation task can alter or hide anatomical features and, therefore, the clinical applicability of this technique has to be evaluated in future studies.

Comprehensive anatomical and functional imaging in patients with type I neurofibromatosis using simultaneous FDG-PET/MRI.

PURPOSE: To demonstrate the clinical use of FDG-PET/MRI for monitoring enlargement and metabolism of plexiform neurofibromas (PNF) in patients with neurofibromatosis type 1 (NF1), in whom the development of a malignant peripheral nerve sheath tumor (MPNST) is often a life limiting event. METHODS: NF1 patients who underwent a simultaneous FDG-PET/MRI examination in our institution from September 2012 to February 2018 were included. Indication was suspicion of malignant transformation of a PNF to MPNST. A maximum of six peripheral nerve lesions per patient were defined as targets. Standardized uptake values (SUV) and apparent diffusion coefficients (ADC) were measured. The presence of target sign and contrast-medium enhancement was visually recorded. Growth rates were estimated comparing prior or follow-up examinations and correlated with FDG uptake and ADC values. The presence of CNS lesions in cerebral T2 weighted images was recorded. RESULTS: In 28 NF1 patients a total number of 83 peripheral nerve tumors, 75 benign PNFs and eight MPNSTs, were selected as target lesions. The SUVs of MPNSTs were significantly higher than the SUVs of PNF (3.84 ± 3.98 [SUVmean MPNSTs] vs. 1.85 ± 1.03 [SUVmean PNF], P < .01). Similarly, lesion SUVmean-to-liver SUVmean ratios significantly differed between MPNSTs and PNF (3.20 ± 2.70 [MPNSTs] vs. 1.23 ± 0.61 [PNF]; P < .01). For differentiation between still benign PNF and MPNSTs, we defined SUVmax ≥ 2.78 as a significant cut-off value. Growth rate of PNF correlated significantly positively with SUVmean (rs = .41; P = .003). MRI parameters like ADCmean (1.87 ± 0.24 × 10-3 mm2/s [PNF] vs. 1.76 ± 0.11 × 10-3 mm2/s [MPNSTs]; P > .05], contrast medium enhancement (P = .50) and target sign (P = .86) did not differ between groups. CONCLUSION: Simultaneous FDG-PET/MRI is a comprehensive imaging modality for monitoring PNF in NF1 patients. The combined acquisition of both morphologic information in MRI and metabolic information in PET enables the correlation of lesion growth rates with metabolic activity and to define SUV thresholds of significance to identify malignant transformation, which is of utmost clinical significance.

Practice-based evidence for the clinical benefit of PET/CT-results of the first oncologic PET/CT registry in Germany.

PURPOSE: The purpose of this study was to evaluate the impact of PET/CT on clinical management of cancer patients based on a prospective data registry. The study was developed to inform consultations with public health insurances on PET/CT coverage. METHODS: We evaluated a prospective patient cohort having a clinically indicated PET/CT at a single German University Center from April 2013 to August 2016. The registry collected questionnaire data from requesting physicians on intended patient management before and after PET/CT. A total of 4,504 patients with 5,939 PET/CT examinations were enrolled in the registry, resulting in evaluable data from 3,724 patients receiving 4,754 scans. The impact of PET/CT on patient management was assessed across 22 tumor types, for different indications (diagnosis, staging, suspected recurrence) and different categories of management including treatment (curative or palliative) and non-treatment (watchful waiting, additional imaging, invasive tests). RESULTS: The most frequent PET/CT indication was tumor staging (59.7%). Melanoma, lung cancer, lymphoma, neuroendocrine tumor and prostate cancer accounted for 70% of cases. Overall, the use of PET/CT resulted in a 37.1% change of clinical management (95% CI, 35.7-38.5), most frequently (30.6%) from an intended non-treatment strategy before PET/CT to active treatment after PET/CT. The frequency of changes ranged from 28.3% for head and neck cancers up to 46.0% for melanomas. The impact of PET/CT was greatest in reducing demands for additional imaging which decreased from 66.1% before PET/CT to 6.1% after PET/CT. Pre-PET/CT planned invasive tests could be avoided in 72.7% of cases. The treatment goal changed after PET/CT in 21.7% of cases, in twice as many cases from curative to palliative therapy than vice versa. CONCLUSIONS: The data of this large prospective registry confirm that physicians often change their intended management on the basis of PET/CT by initiating treatment and reducing additional imaging as well as invasive tests. This applies to various cancer types and indications.

Comprehensive metabolic and morphologic disease characterization in systemic sclerosis: initial results using combined positron emission tomography and magnetic resonance imaging.

BACKGROUND: The aim of this study was to evaluate the role of metabolic and morphologic parameters derived from simultaneous hybrid PET/MRI in correlation to clinical criteria for an image-based characterization of musculoskeletal, esophagus and lymph node involvement in systemic sclerosis (SSc). METHODS: Between November 2013 and May 2015, simultaneous whole-body hybrid PET/MRI was performed in 13 prospectively recruited patients with SSc. A mean dose of 241.3 MBq 2-deoxy-2-[18F]fluoro-D-glucose (FDG) was injected. SUVmean and SUVmax values were measured in the spinal bone marrow, spleen, joints, muscles, fasciae, mediastinal lymph nodes and esophagus. MRI abnormalities were scored as 0 (absent), 1 (moderate) and 2 (marked). In addition, organ and skin involvement were graded with clinical sum score (CSS) and modified Rodnan skin score (mRSS), respectively. RESULTS: Results indicate positive correlations between mRSS and fascial FDG-uptake values (fascia summed SUVmax ρ=0.67; fascia summed SUVmean ρ=0.66) that performed better than the MRI sum score (ρ=0.50). Fascial FDG-uptake is also useful in the differentiation between diffuse and limited SSc. Additionally, FDG-PET detected patients with active mediastinal lymphadenopathy and MRI proved to be useful for the delineation of esophagus involvement. CONCLUSIONS: Fascial FDG-uptake has a strong correlation with mRSS and can discriminate between limited and diffuse SSc. These results and the detection of active lymphadenopathy and esophagus involvement can identify patients with advanced scleroderma. Combined PET/MRI therefore provides complementary information on the complex pathophysiology and may integrate several imaging procedures in one.

Independent brain 18F-FDG PET attenuation correction using a deep learning approach with Generative Adversarial Networks.

OBJECTIVE: Attenuation correction (AC) of positron emission tomography (PET) data poses a challenge when no transmission data or computed tomography (CT) data are available, e.g. in stand alone PET scanners or PET/magnetic resonance imaging (MRI). In these cases, external imaging data or morphological imaging data are normally used for the generation of attenuation maps. Newly introduced machine learning methods however may allow for direct estimation of attenuation maps from non attenuation-corrected PET data (PETNAC). Our purpose was thus to establish and evaluate a method for independent AC of brain fluorine-18-fluorodeoxyglucose (18F-FDG) PET images only based on PETNAC using Generative Adversarial Networks (GAN). SUBJECTS AND METHODS: After training of the deep learning GAN framework on a paired training dataset of PETNAC and the corresponding CT images of the head from 50 patients, pseudo-CT images were generated from PETNAC of 40 validation patients, of which 20 were used for technical validation and 20 stemming from patients with CNS disorders were used for clinical validation. Pseudo-CT was used for subsequent AC of these validation data sets resulting in independently attenuation-corrected PET data. RESULTS: Visual inspection revealed a high degree of resemblance of generated pseudo-CT images compared to the acquired CT images in all validation data sets, with minor differences in individual anatomical details. Quantitative analyses revealed minimal underestimation below 5% of standardized uptake value (SUV) in all brain regions in independently attenuation-corrected PET data compared to the reference PET images. Color-coded error maps showed no regional bias and only minimal average errors around ±0%. Using independently attenuation-corrected PET data, no differences in image-based diagnoses were observed in 20 patients with neurological disorders compared to the reference PET images. CONCLUSION: Independent AC of brain 18F-FDG PET is feasible with high accuracy using the proposed, easy to implement deep learning framework. Further evaluation in clinical cohorts will be necessary to assess the clinical performance of this method.

Voxel-wise correlation of functional imaging parameters in HNSCC patients receiving PET/MRI in an irradiation setup.

PURPOSE: The purpose of this study was to demonstrate the feasibility of voxel-wise multiparametric characterization of head and neck squamous cell carcinomas (HNSCC) using hybrid multiparametric magnetic resonance imaging and positron emission tomography with [18F]-fluorodesoxyglucose (FDG-PET/MRI) in a radiation treatment planning setup. METHODS: Ten patients with locally advanced HNSCC were examined with a combined FDG-PET/MRI in an irradiation planning setup. The multiparametric imaging protocol consisted of FDG-PET, T2-weighted transverse short tau inversion recovery sequence (STIR) and diffusion-weighted MRI (DWI). Primary tumours were manually segmented and quantitative imaging parameters were extracted. PET standardized uptake values (SUV) and DWI apparent diffusion coefficients (ADC) were correlated on a voxel-wise level. RESULTS: Images acquired in this specialised radiotherapy planning setup achieved good diagnostic quality. Median tumour volume was 4.9 [1.1-42.1] ml. Mean PET SUV and ADC of the primary tumours were 5 ± 2.5 and 1.2 ± 0.3 10-3 mm2/s, respectively. In voxel-wise correlation between ADC values and corresponding FDG SUV of the tumours, a significant negative correlation was observed (r = -0.31 ± 0.27, p < 0.05). CONCLUSION: Multiparametric voxel-wise characterization of HNSCC is feasible using combined PET/MRI in a radiation planning setup. This technique may provide novel insights into tumour biology with regard to radiation therapy in the future.

A semiquantitative MRI-Score can predict loss of lung function in patients with cystic fibrosis: Preliminary results.

OBJECTIVES: To evaluate the applicability of a semiquantitative MRI scoring system (MR-CF-S) as a prognostic marker for clinical course of cystic fibrosis (CF) lung disease. METHODS: This observational study of a single-centre CF cohort included a group of 61 patients (mean age 12.9 ± 4.7 years) receiving morphological and functional pulmonary MRI, pulmonary function testing (PFT) and follow-up of 2 years. MRI was analysed by three raters using MR-CF-S. The inter-rater agreement, correlation of score categories with forced expiratory volume in 1 s (FEV1) at baseline, and the predictive value of clinical parameters, and score categories was assessed for the whole cohort and a subgroup of 40 patients with moderately impaired lung function. RESULTS: The inter-rater agreement of MR-CF-S was sufficient (mean intraclass correlation coefficient 0.92). MR-CF-S (-0.62; p < 0.05) and most of the categories significantly correlated with FEV1. Differences between patients with relevant loss of FEV1 (>3%/year) and normal course were only significant for MR-CF-S (p < 0.05) but not for clinical parameters. Centrilobular opacity (CO) was the most promising score category for prediction of a decline of FEV1 (area under curve: whole cohort 0.69; subgroup 0.86). CONCLUSIONS: MR-CF-S is promising to predict a loss of lung function. CO seems to be a particular finding in CF patients with an abnormal course. KEY POINTS: • Lung imaging is essential in the diagnostic work-up of CF patients • MRI serves as a powerful, radiation-free modality in paediatric CF patients • Observational single-centre study showed significant correlation of MR-CF score and FEV 1 • MR-CF score is promising in predicting a loss of lung function.

Automated reference-free detection of motion artifacts in magnetic resonance images.

OBJECTIVES: Our objectives were to provide an automated method for spatially resolved detection and quantification of motion artifacts in MR images of the head and abdomen as well as a quality control of the trained architecture. MATERIALS AND METHODS: T1-weighted MR images of the head and the upper abdomen were acquired in 16 healthy volunteers under rest and under motion. Images were divided into overlapping patches of different sizes achieving spatial separation. Using these patches as input data, a convolutional neural network (CNN) was trained to derive probability maps for the presence of motion artifacts. A deep visualization offers a human-interpretable quality control of the trained CNN. Results were visually assessed on probability maps and as classification accuracy on a per-patch, per-slice and per-volunteer basis. RESULTS: On visual assessment, a clear difference of probability maps was observed between data sets with and without motion. The overall accuracy of motion detection on a per-patch/per-volunteer basis reached 97%/100% in the head and 75%/100% in the abdomen, respectively. CONCLUSION: Automated detection of motion artifacts in MRI is feasible with good accuracy in the head and abdomen. The proposed method provides quantification and localization of artifacts as well as a visualization of the learned content. It may be extended to other anatomic areas and used for quality assurance of MR images.

Self-navigated 4D cartesian imaging of periodic motion in the body trunk using partial k-space compressed sensing.

PURPOSE: To enable fast and flexible high-resolution four-dimensional (4D) MRI of periodic thoracic/abdominal motion for motion visualization or motion-corrected imaging. METHODS: We proposed a Cartesian three-dimensional k-space sampling scheme that acquires a random combination of k-space lines in the ky/kz plane. A partial Fourier-like constraint compacts the sampling space to one half of k-space. The central k-space line is periodically acquired to allow an extraction of a self-navigated respiration signal used to populate a k-space of multiple breathing positions. The randomness of the acquisition (induced by periodic breathing pattern) yields a subsampled k-space that is reconstructed using compressed sensing. Local image evaluations (coefficient of variation and slope steepness through organs) reveal information about motion resolvability. Image quality is inspected by a blinded reading. Sequence and reconstruction method are made publicly available. RESULTS: The method is able to capture and reconstruct 4D images with high image quality and motion resolution within a short scan time of less than 2 min. These findings are supported by restricted-isometry-property analysis, local image evaluation, and blinded reading. CONCLUSION: The proposed method provides a clinical feasible setup to capture periodic respiratory motion with a fast acquisition protocol and can be extended by further surrogate signals to capture additional periodic motions. Retrospective parametrization allows for flexible tuning toward the targeted applications. Magn Reson Med 78:632-644, 2017. © 2016 International Society for Magnetic Resonance in Medicine.