Dataset Information

Independent attenuation correction of whole body [18F]FDG-PET using a deep learning approach with Generative Adversarial Networks.

ABSTRACT: BACKGROUND:Attenuation correction (AC) of PET data is usually performed using a second imaging for the generation of attenuation maps. In certain situations however-when CT- or MR-derived attenuation maps are corrupted or CT acquisition solely for the purpose of AC shall be avoided-it would be of value to have the possibility of obtaining attenuation maps only based on PET information. The purpose of this study was to thus develop, implement, and evaluate a deep learning-based method for whole body [18F]FDG-PET AC which is independent of other imaging modalities for acquiring the attenuation map. METHODS:The proposed method is investigated on whole body [18F]FDG-PET data using a Generative Adversarial Networks (GAN) deep learning framework. It is trained to generate pseudo CT images (CTGAN) based on paired training data of non-attenuation corrected PET data (PETNAC) and corresponding CT data. Generated pseudo CTs are then used for subsequent PET AC. One hundred data sets of whole body PETNAC and corresponding CT were used for training. Twenty-five PET/CT examinations were used as test data sets (not included in training). On these test data sets, AC of PET was performed using the acquired CT as well as CTGAN resulting in the corresponding PET data sets PETAC and PETGAN. CTGAN and PETGAN were evaluated qualitatively by visual inspection and by visual analysis of color-coded difference maps. Quantitative analysis was performed by comparison of organ and lesion SUVs between PETAC and PETGAN. RESULTS:Qualitative analysis revealed no major SUV deviations on PETGAN for most anatomic regions; visually detectable deviations were mainly observed along the diaphragm and the lung border. Quantitative analysis revealed mean percent deviations of SUVs on PETGAN of - 0.8 ± 8.6% over all organs (range [- 30.7%, + 27.1%]). Mean lesion SUVs showed a mean deviation of 0.9 ± 9.2% (range [- 19.6%, + 29.2%]). CONCLUSION:Independent AC of whole body [18F]FDG-PET is feasible using the proposed deep learning approach yielding satisfactory PET quantification accuracy. Further clinical validation is necessary prior to implementation in clinical routine applications.

SUBMITTER: Armanious K

PROVIDER: S-EPMC7246235 | biostudies-literature | 2020 May

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Independent attenuation correction of whole body [<sup>18</sup>F]FDG-PET using a deep learning approach with Generative Adversarial Networks.

Armanious Karim K Hepp Tobias T Küstner Thomas T Dittmann Helmut H Nikolaou Konstantin K La Fougère Christian C Yang Bin B Gatidis Sergios S

EJNMMI research 20200524 1

<h4>Background</h4>Attenuation correction (AC) of PET data is usually performed using a second imaging for the generation of attenuation maps. In certain situations however-when CT- or MR-derived attenuation maps are corrupted or CT acquisition solely for the purpose of AC shall be avoided-it would be of value to have the possibility of obtaining attenuation maps only based on PET information. The purpose of this study was to thus develop, implement, and evaluate a deep learning-based method for ...[more]

PMID: 32449036

Similar Datasets

Project description:PURPOSE:The aim of this study was to evaluate and quantify the effect of improved attenuation correction (AC) including bone segmentation and truncation correction on 18F-Fluordesoxyglucose cardiac positron emission tomography/magnetic resonance (PET/MR) imaging. METHODS:PET data of 32 cardiac PET/MR datasets were reconstructed with three different AC-maps (1. Dixon-VIBE only, 2. HUGE truncation correction and bone segmentation, 3. MLAA). The Dixon-VIBE AC-maps served as reference of reconstructed PET data. 17-segment short-axis polar plots of the left ventricle were analyzed regarding the impact of each of the three AC methods on PET quantification in cardiac PET/MR imaging. Non-AC PET images were segmented to specify the amount of truncation in the Dixon-VIBE AC-map serving as a reference. All AC-maps were evaluated for artifacts. RESULTS:Using HUGE + bone AC results in a homogeneous gain of ca. 6% and for MLAA 8% of PET signal distribution across the myocardium of the left ventricle over all patients compared to Dixon-VIBE AC only. Maximal relative differences up to 18% were observed in segment 17 (apex). The body volume truncation of -12.7 ± 7.1% compared to the segmented non-AC PET images using the Dixon-VIBE AC method was reduced to -1.9 ± 3.9% using HUGE and 7.8 ± 8.3% using MLAA. In each patient, a systematic overestimation in AC-map volume was observed when applying MLAA. Quantitative impact of artifacts showed regional differences up to 6% within single segments of the myocardium. CONCLUSIONS:Improved AC including bone segmentation and truncation correction in cardiac PET/MR imaging is important to ensure best possible diagnostic quality and PET quantification. The results exhibited an overestimation of AC-map volume using MLAA, while HUGE resulted in a more realistic body contouring. Incorporation of bone segmentation into the Dixon-VIBE AC-map resulted in homogeneous gain in PET signal distribution across the myocardium. The majority of observed AC-map artifacts did not significantly affect the quantitative assessment of the myocardium.

Project description:We propose a new deep learning-based approach to provide more accurate whole-body PET/MRI attenuation correction than is possible with the Dixon-based 4-segment method. We use activity and attenuation maps estimated using the maximum-likelihood reconstruction of activity and attenuation (MLAA) algorithm as inputs to a convolutional neural network (CNN) to learn a CT-derived attenuation map. Methods: The whole-body 18F-FDG PET/CT scan data of 100 cancer patients (38 men and 62 women; age, 57.3 ± 14.1 y) were retrospectively used for training and testing the CNN. A modified U-net was trained to predict a CT-derived μ-map (μ-CT) from the MLAA-generated activity distribution (λ-MLAA) and μ-map (μ-MLAA). We used 1.3 million patches derived from 60 patients' data for training the CNN, data of 20 others were used as a validation set to prevent overfitting, and the data of the other 20 were used as a test set for the CNN performance analysis. The attenuation maps generated using the proposed method (μ-CNN), μ-MLAA, and 4-segment method (μ-segment) were compared with the μ-CT, a ground truth. We also compared the voxelwise correlation between the activity images reconstructed using ordered-subset expectation maximization with the μ-maps, and the SUVs of primary and metastatic bone lesions obtained by drawing regions of interest on the activity images. Results: The CNN generates less noisy attenuation maps and achieves better bone identification than MLAA. The average Dice similarity coefficient for bone regions between μ-CNN and μ-CT was 0.77, which was significantly higher than that between μ-MLAA and μ-CT (0.36). Also, the CNN result showed the best pixel-by-pixel correlation with the CT-based results and remarkably reduced differences in activity maps in comparison to CT-based attenuation correction. Conclusion: The proposed deep neural network produced a more reliable attenuation map for 511-keV photons than the 4-segment method currently used in whole-body PET/MRI studies.

Project description: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 (PETsCT) and a vendor-provided atlas-based method (PETAtlas), with the CT-based reconstruction (PETCT) 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 PETCT and PETsCT (R2 = 0.98). The absolute percentage difference in PET quantification for the entire image was 6.1% for PETsCT and 11.2% for PETAtlas. The regional analysis showed that the average errors and the variability for PETsCT were lower than PETAtlas 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. Supplementary Information The online version contains supplementary material available at 10.1186/s40658-022-00486-8.

Project description:The 2-deoxy-d-[18F]fluoro-D-glucose (FDG) positron emission tomography/computed tomography (PET/CT) is widely utilized to assess the vascular and articular inflammatory burden of patients with a suspected diagnosis of rheumatic disease. We aimed to elucidate the impact of [18F]FDG PET/CT on change in initially suspected diagnosis in patients at the time of the scan. Thirty-four patients, who had undergone [18F]FDG PET/CT, were enrolled and the initially suspected diagnosis prior to [18F]FDG PET/CT was compared to the final diagnosis. In addition, a semi-quantitative analysis including vessel wall-to-liver (VLR) and joint-to-liver (JLR) ratios was also conducted. Prior to [18F]FDG PET/CT, 22/34 (64.7%) of patients did not have an established diagnosis, whereas in 7/34 (20.6%), polymyalgia rheumatica (PMR) was suspected, and in 5/34 (14.7%), giant cell arteritis (GCA) was suspected by the referring rheumatologists. After [18F]FDG PET/CT, the diagnosis was GCA in 19/34 (55.9%), combined GCA and PMR (GCA + PMR) in 9/34 (26.5%) and PMR in the remaining 6/34 (17.6%). As such, [18F]FDG PET/CT altered suspected diagnosis in 28/34 (82.4%), including in all unclear cases. VLR of patients whose final diagnosis was GCA tended to be significantly higher when compared to VLR in PMR (GCA, 1.01 ± 0.08 (95%CI, 0.95-1.1) vs. PMR, 0.92 ± 0.1 (95%CI, 0.85-0.99), p = 0.07), but not when compared to PMR + GCA (1.04 ± 0.14 (95%CI, 0.95-1.13), p = 1). JLR of individuals finally diagnosed with PMR (0.94 ± 0.16, (95%CI, 0.83-1.06)), however, was significantly increased relative to JLR in GCA (0.58 ± 0.04 (95%CI, 0.55-0.61)) and GCA + PMR (0.64 ± 0.09 (95%CI, 0.57-0.71); p < 0.0001, respectively). In individuals with a suspected diagnosis of rheumatic disease, an inflammatory-directed [18F]FDG PET/CT can alter diagnosis in the majority of the cases, particularly in subjects who were referred because of diagnostic uncertainty. Semi-quantitative assessment may be helpful in establishing a final diagnosis of PMR, supporting the notion that a quantitative whole-body read-out may be useful in unclear cases.

Project description:Dedicated brain positron emission tomography (PET) devices can provide higher-resolution images with much lower doses compared to conventional whole-body PET systems, which is important to support PET neuroimaging and particularly useful for the diagnosis of neurodegenerative diseases. However, when a dedicated brain PET scanner does not come with a combined CT or transmission source, there is no direct solution for accurate attenuation and scatter correction, both of which are critical for quantitative PET. To address this problem, we propose joint attenuation and scatter correction (ASC) in image space for non-corrected PET (PETNC) using deep convolutional neural networks (DCNNs). This approach is a one-step process, distinct from conventional methods that rely on generating attenuation maps first that are then applied to iterative scatter simulation in sinogram space. For training and validation, time-of-flight PET/MR scans and additional helical CTs were performed for 35 subjects (25/10 split for training and test dataset). A DCNN model was proposed and trained to convert PETNC to DCNN-based ASC PET (PETDCNN) directly in image space. For quantitative evaluation, uptake differences between PETDCNN and reference CT-based ASC PET (PETCT-ASC) were computed for 116 automated anatomical labels (AALs) across 10 test subjects (1160 regions in total). MR-based ASC PET (PETMR-ASC), a current clinical protocol in PET/MR imaging, was another reference for comparison. Statistical significance was assessed using a paired t test. The performance of PETDCNN was comparable to that of PETMR-ASC, in comparison to reference PETCT-ASC. The mean SUV differences (mean ± SD) from PETCT-ASC were 4.0% ± 15.4% (P < 0.001) and -4.2% ± 4.3% (P < 0.001) for PETDCNN and PETMR-ASC, respectively. The overall larger variation of PETDCNN (15.4%) was prone to the subject with the highest mean difference (48.5% ± 10.4%). The mean difference of PETDCNN excluding the subject was substantially improved to -0.8% ± 5.2% (P < 0.001), which was lower than that of PETMR-ASC (-5.07% ± 3.60%, P < 0.001). In conclusion, we demonstrated the feasibility of directly producing PET images corrected for attenuation and scatter using a DCNN (PETDCNN) from PETNC in image space without requiring conventional attenuation map generation and time-consuming scatter correction. Additionally, our DCNN-based method provides a possible alternative to MR-ASC for simultaneous PET/MRI.

Project description:PurposeTo demonstrate the feasibility of CT-less attenuation and scatter correction (ASC) in the image space using deep learning for whole-body PET, with a focus on the potential benefits and pitfalls.Materials and methodsIn this retrospective study, 110 whole-body fluorodeoxyglucose (FDG) PET/CT studies acquired in 107 patients (mean age ± standard deviation, 58 years ± 18; age range, 11-92 years; 72 females) from February 2016 through January 2018 were randomly collected. A total of 37.3% (41 of 110) of the studies showed metastases, with diverse FDG PET findings throughout the whole body. A U-Net-based network was developed for directly transforming noncorrected PET (PETNC) into attenuation- and scatter-corrected PET (PETASC). Deep learning-corrected PET (PETDL) images were quantitatively evaluated by using the standardized uptake value (SUV) of the normalized root mean square error, the peak signal-to-noise ratio, and the structural similarity index, in addition to a joint histogram for statistical analysis. Qualitative reviews by radiologists revealed the potential benefits and pitfalls of this correction method.ResultsThe normalized root mean square error (0.21 ± 0.05 [mean SUV ± standard deviation]), mean peak signal-to-noise ratio (36.3 ± 3.0), mean structural similarity index (0.98 ± 0.01), and voxelwise correlation (97.62%) of PETDL demonstrated quantitatively high similarity with PETASC. Radiologist reviews revealed the overall quality of PETDL. The potential benefits of PETDL include a radiation dose reduction on follow-up scans and artifact removal in the regions with attenuation correction- and scatter correction-based artifacts. The pitfalls involve potential false-negative results due to blurring or missing lesions or false-positive results due to pseudo-low-uptake patterns.ConclusionDeep learning-based direct ASC at whole-body PET is feasible and potentially can be used to overcome the current limitations of CT-based approaches, benefiting patients who are sensitive to radiation from CT.Supplemental material is available for this article.© RSNA, 2020.

Project description:Combined whole-body dual-tracer ((18)F-FDG and (11)C-acetate) PET/CT is increasingly used for staging hepatocellular carcinoma, with only limited studies investigating the radiation dosimetry data of these scans. The aim of the study was to characterize the radiation dosimetry of combined whole-body dual-tracer PET/CT protocols.Consecutive adult patients with hepatocellular carcinoma who underwent whole-body dual-tracer PET/CT scans were retrospectively reviewed with institutional review board approval. OLINDA/EXM 1.1 was used to estimate patient-specific internal dose exposure in each organ. Biokinetic models for (18)F-FDG and (11)C-acetate as provided by ICRP (International Commission on Radiological Protection) publication 106 were used. Standard reference phantoms were modified to more closely represent patient-specific organ mass. With patient-specific parameters, organ equivalent doses from each CT series were estimated using VirtualDose. Dosimetry capabilities for tube current modulation protocols were applied by integrating with the latest anatomic realistic models. Effective dose was calculated using ICRP publication 103 tissue-weighting coefficients for adult male and female, respectively.Fourteen scans were evaluated (12 men, 2 women; mean age ± SD, 60 ± 19.48 y). The patient-specific effective dose from (18)F-FDG and (11)C-acetate was 6.08 ± 1.49 and 1.56 ± 0.47 mSv, respectively, for male patients and 6.62 ± 1.38 and 1.79 ± 0.12 mSV, respectively, for female patients. The patient-specific effective dose of the CT component, which comprised 2 noncontrast whole-body scans, to male and female patients was 21.20 ± 8.94 and 14.79 ± 3.35 mSv, respectively. Thus, the total effective doses of the combined whole-body dual-tracer PET/CT studies for male and female patients were 28.84 ± 10.18 and 23.19 ± 4.61 mSv, respectively.Patient-specific parameters allow for more accurate estimation of organ equivalent doses. Considering the substantial radiation dose incurred, judicious medical justification is required with every whole-body dual-tracer PET/CT referral. Although radiation risks may have less impact for the population with cancer because of their reduced life expectancy, the information is of interest and relevant for both justification, to evaluate risk/benefit, and protocol optimization.

Dataset Information

Independent attenuation correction of whole body [18F]FDG-PET using a deep learning approach with Generative Adversarial Networks.

Publications

Independent attenuation correction of whole body [<sup>18</sup>F]FDG-PET using a deep learning approach with Generative Adversarial Networks.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets