11
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Attenuation correction using 3D deep convolutional neural network for brain 18F-FDG PET/MR: Comparison with Atlas, ZTE and CT based attenuation correction

      research-article

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          One of the main technical challenges of PET/MRI is to achieve an accurate PET attenuation correction (AC) estimation. In current systems, AC is accomplished by generating an MRI-based surrogate computed tomography (CT) from which AC-maps are derived. Nevertheless, all techniques currently implemented in clinical routine suffer from bias. We present here a convolutional neural network (CNN) that generated AC-maps from Zero Echo Time (ZTE) MR images. Seventy patients referred to our institution for 18FDG-PET/MR exam (SIGNA PET/MR, GE Healthcare) as part of the investigation of suspected dementia, were included. 23 patients were added to the training set of the manufacturer and 47 were used for validation. Brain computed tomography (CT) scan, two-point LAVA-flex MRI (for atlas-based AC) and ZTE-MRI were available in all patients. Three AC methods were evaluated and compared to CT-based AC (CTAC): one based on a single head-atlas, one based on ZTE-segmentation and one CNN with a 3D U-net architecture to generate AC maps from ZTE MR images. Impact on brain metabolism was evaluated combining voxel and regions-of-interest based analyses with CTAC set as reference. The U-net AC method yielded the lowest bias, the lowest inter-individual and inter-regional variability compared to PET images reconstructed with ZTE and Atlas methods. The impact on brain metabolism was negligible with average errors of -0.2% in most cortical regions. These results suggest that the U-net AC is more reliable for correcting photon attenuation in brain FDG-PET/MR than atlas-AC and ZTE-AC methods.

          Related collections

          Most cited references21

          • Record: found
          • Abstract: found
          • Article: not found

          Deep Learning MR Imaging–based Attenuation Correction for PET/MR Imaging

          Purpose To develop and evaluate the feasibility of deep learning approaches for magnetic resonance (MR) imaging-based attenuation correction (AC) (termed deep MRAC) in brain positron emission tomography (PET)/MR imaging. Materials and Methods A PET/MR imaging AC pipeline was built by using a deep learning approach to generate pseudo computed tomographic (CT) scans from MR images. A deep convolutional auto-encoder network was trained to identify air, bone, and soft tissue in volumetric head MR images coregistered to CT data for training. A set of 30 retrospective three-dimensional T1-weighted head images was used to train the model, which was then evaluated in 10 patients by comparing the generated pseudo CT scan to an acquired CT scan. A prospective study was carried out for utilizing simultaneous PET/MR imaging for five subjects by using the proposed approach. Analysis of covariance and paired-sample t tests were used for statistical analysis to compare PET reconstruction error with deep MRAC and two existing MR imaging-based AC approaches with CT-based AC. Results Deep MRAC provides an accurate pseudo CT scan with a mean Dice coefficient of 0.971 ± 0.005 for air, 0.936 ± 0.011 for soft tissue, and 0.803 ± 0.021 for bone. Furthermore, deep MRAC provides good PET results, with average errors of less than 1% in most brain regions. Significantly lower PET reconstruction errors were realized with deep MRAC (-0.7% ± 1.1) compared with Dixon-based soft-tissue and air segmentation (-5.8% ± 3.1) and anatomic CT-based template registration (-4.8% ± 2.2). Conclusion The authors developed an automated approach that allows generation of discrete-valued pseudo CT scans (soft tissue, bone, and air) from a single high-spatial-resolution diagnostic-quality three-dimensional MR image and evaluated it in brain PET/MR imaging. This deep learning approach for MR imaging-based AC provided reduced PET reconstruction error relative to a CT-based standard within the brain compared with current MR imaging-based AC approaches. © RSNA, 2017 Online supplemental material is available for this article.
            Bookmark
            • Record: found
            • Abstract: found
            • Article: found
            Is Open Access

            A multi-centre evaluation of eleven clinically feasible brain PET/MRI attenuation correction techniques using a large cohort of patients

            Aim: To accurately quantify the radioactivity concentration measured by PET, emission data need to be corrected for photon attenuation; however, the MRI signal cannot easily be converted into attenuation values, making attenuation correction (AC) in PET/MRI challenging. In order to further improve the current vendor-implemented MR-AC methods for absolute quantification, a number of prototype methods have been proposed in the literature. These can be categorized into three types: template/atlas-based, segmentation-based, and reconstruction-based. These proposed methods in general demonstrated improvements compared to vendor-implemented AC, and many studies report deviations in PET uptake after AC of only a few percent from a gold standard CT-AC. Using a unified quantitative evaluation with identical metrics, subject cohort, and common CT-based reference, the aims of this study were to evaluate a selection of novel methods proposed in the literature, and identify the ones suitable for clinical use. Methods: In total, 11 AC methods were evaluated: two vendor-implemented (MR-ACDIXON and MR-ACUTE), five based on template/atlas information (MR-ACSEGBONE (Koesters et al., 2016), MR-ACONTARIO (Anazodo et al., 2014), MR-ACBOSTON (Izquierdo-Garcia et al., 2014), MR-ACUCL (Burgos et al., 2014), and MR-ACMAXPROB (Merida et al., 2015)), one based on simultaneous reconstruction of attenuation and emission (MR-ACMLAA (Benoit et al., 2015)), and three based on image-segmentation (MR-ACMUNICH (Cabello et al., 2015), MR-ACCAR-RiDR (Juttukonda et al., 2015), and MR-ACRESOLUTE (Ladefoged et al., 2015)). We selected 359 subjects who were scanned using one of the following radiotracers: [18F]FDG (210), [11C]PiB (51), and [18F] florbetapir (98). The comparison to AC with a gold standard CT was performed both globally and regionally, with a special focus on robustness and outlier analysis. Results: The average performance in PET tracer uptake was within ± 5% of CT for all of the proposed methods, with the average ± SD global percentage bias in PET FDG uptake for each method being: MR-ACDIXON (−11.3 ± 3.5)%, MR-ACUTE (−5.7 ± 2.0)%, MR-ACONTARIO (−4.3 ± 3.6)%, MR-ACMUNICH (3.7 ± 2.1)%, MR-ACMLAA (−1.9 ± 2.6)%, MR-ACSEGBONE (−1.7 ± 3.6)%, MR-ACUCL (0.8 ± 1.2)%, MR-ACCAR-RiDR (−0.4 ± 1.9)%, MR-ACMAXPROB (−0.4 ± 1.6)%, MR-ACBOSTON (−0.3 ± 1.8)%, and MR-ACRESOLUTE (0.3 ± 1.7)%, ordered by average bias. The overall best performing methods (MR-ACBOSTON, MR-ACMAXPROB, MR-ACRESOLUTE and MR-ACUCL, ordered alphabetically) showed regional average errors within ± 3% of PET with CT-AC in all regions of the brain with FDG, and the same four methods, as well as MR-ACCAR-RiDR, showed that for 95% of the patients, 95% of brain voxels had an uptake that deviated by less than 15% from the reference. Comparable performance was obtained with PiB and florbetapir. Conclusions: All of the proposed novel methods have an average global performance within likely acceptable limits ( ± 5% of CT-based reference), and the main difference among the methods was found in the robustness, outlier analysis, and clinical feasibility. Overall, the best performing methods were MR-ACBOSTON, MR-ACMAXPROB, MR-ACRESOLUTE and MR-ACUCL, ordered alphabetically. These methods all minimized the number of outliers, standard deviation, and average global and local error. The methods MR-ACMUNICH and MR-ACCAR-RiDR were both within acceptable quantitative limits, so these methods should be considered if processing time is a factor. The method MR-ACSEGBONE also demonstrates promising results, and performs well within the likely acceptable quantitative limits. For clinical routine scans where processing time can be a key factor, this vendor-provided solution currently outperforms most methods. With the performance of the methods presented here, it may be concluded that the challenge of improving the accuracy of MR-AC in adult brains with normal anatomy has been solved to a quantitatively acceptable degree, which is smaller than the quantification reproducibility in PET imaging.
              Bookmark
              • Record: found
              • Abstract: found
              • Article: not found

              Brain fluorodeoxyglucose (FDG) PET in dementia.

              The purpose of this article is to present a selective and concise summary of fluorodeoxyglucose (FDG) positron emission tomography (PET) in dementia imaging. FDG PET is used to visualize a downstream topographical marker that indicates the distribution of neural injury or synaptic dysfunction, and can identify distinct phenotypes of dementia due to Alzheimer's disease (AD), Lewy bodies, and frontotemporal lobar degeneration. AD dementia shows hypometabolism in the parietotemporal association area, posterior cingulate, and precuneus. Hypometabolism in the inferior parietal lobe and posterior cingulate/precuneus is a predictor of cognitive decline from mild cognitive impairment (MCI) to AD dementia. FDG PET may also predict conversion of cognitively normal individuals to those with MCI. Age-related hypometabolism is observed mainly in the anterior cingulate and anterior temporal lobe, along with regional atrophy. Voxel-based statistical analyses, such as statistical parametric mapping or three-dimensional stereotactic surface projection, improve the diagnostic performance of imaging of dementias. The potential of FDG PET in future clinical and methodological studies should be exploited further.
                Bookmark

                Author and article information

                Contributors
                Role: ConceptualizationRole: Data curationRole: MethodologyRole: Project administrationRole: ResourcesRole: ValidationRole: VisualizationRole: Writing – original draftRole: Writing – review & editing
                Role: ConceptualizationRole: Data curationRole: MethodologyRole: SupervisionRole: Writing – review & editing
                Role: Data curation
                Role: Formal analysisRole: Software
                Role: Resources
                Role: Writing – review & editing
                Role: Writing – review & editing
                Role: MethodologyRole: Writing – review & editing
                Role: Writing – review & editing
                Role: ConceptualizationRole: Data curationRole: InvestigationRole: MethodologyRole: Project administrationRole: SupervisionRole: ValidationRole: Writing – original draftRole: Writing – review & editing
                Role: Editor
                Journal
                PLoS One
                PLoS ONE
                plos
                plosone
                PLoS ONE
                Public Library of Science (San Francisco, CA USA )
                1932-6203
                2019
                7 October 2019
                : 14
                : 10
                : e0223141
                Affiliations
                [1 ] Nuclear Medicine Department, Groupe Hospitalier Pitié-Salpêtrière C. Foix, APHP, Paris, France
                [2 ] Centre de Neuroimagerie de Recherche (CENIR), Institut du Cerveau et de la Moëlle, Paris, France
                [3 ] GE Healthcare, Bangalore, India
                [4 ] Gordon Center for Medical Imaging, Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, United States of America
                [5 ] Laboratoire d’Imagerie Biomédicale, Sorbonne Université, Paris, France
                [6 ] GE Healthcare, Munich, Germany
                Nathan S Kline Institute, UNITED STATES
                Author notes

                Competing Interests: MK received a research grant from GE Healthcare. SK and FW are GE Healthcare employees. Only non-GE employees had control of inclusion of data and information that might present a conflict of interest for authors who are employees of GE Healthcare. No other potential conflict of interest relevant to this article was reported. AK received honoraria for lectures from GE Healthcare and Piramal. MOH received honoraria for lectures from Lilly. This does not alter our adherence to PLOS ONE policies on sharing data and materials. The other authors do not present any conflict of interest.

                Author information
                http://orcid.org/0000-0003-1197-2879
                Article
                PONE-D-19-16876
                10.1371/journal.pone.0223141
                6779234
                31589623
                9889725e-de41-4352-b6ab-b146e2aa4a7e
                © 2019 Blanc-Durand et al

                This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

                History
                : 24 June 2019
                : 13 September 2019
                Page count
                Figures: 4, Tables: 1, Pages: 12
                Funding
                The funder provided support in the form of salaries for authors [MK, SK, FW], but did not have any additional role in the study design, data collection and analysis, decision to publish. The specific roles of these authors are articulated in the ‘author contributions’ section.
                Categories
                Research Article
                Medicine and Health Sciences
                Diagnostic Medicine
                Diagnostic Radiology
                Magnetic Resonance Imaging
                Research and Analysis Methods
                Imaging Techniques
                Diagnostic Radiology
                Magnetic Resonance Imaging
                Medicine and Health Sciences
                Radiology and Imaging
                Diagnostic Radiology
                Magnetic Resonance Imaging
                Research and Analysis Methods
                Imaging Techniques
                Neuroimaging
                Positron Emission Tomography
                Biology and Life Sciences
                Neuroscience
                Neuroimaging
                Positron Emission Tomography
                Medicine and Health Sciences
                Diagnostic Medicine
                Diagnostic Radiology
                Tomography
                Positron Emission Tomography
                Research and Analysis Methods
                Imaging Techniques
                Diagnostic Radiology
                Tomography
                Positron Emission Tomography
                Medicine and Health Sciences
                Radiology and Imaging
                Diagnostic Radiology
                Tomography
                Positron Emission Tomography
                Research and Analysis Methods
                Imaging Techniques
                Neuroimaging
                Computed Axial Tomography
                Biology and Life Sciences
                Neuroscience
                Neuroimaging
                Computed Axial Tomography
                Medicine and Health Sciences
                Diagnostic Medicine
                Diagnostic Radiology
                Tomography
                Computed Axial Tomography
                Research and Analysis Methods
                Imaging Techniques
                Diagnostic Radiology
                Tomography
                Computed Axial Tomography
                Medicine and Health Sciences
                Radiology and Imaging
                Diagnostic Radiology
                Tomography
                Computed Axial Tomography
                Research and Analysis Methods
                Imaging Techniques
                Neuroimaging
                Biology and Life Sciences
                Neuroscience
                Neuroimaging
                Research and Analysis Methods
                Imaging Techniques
                Biology and Life Sciences
                Anatomy
                Brain
                Cerebral Cortex
                Cerebellum
                Medicine and Health Sciences
                Anatomy
                Brain
                Cerebral Cortex
                Cerebellum
                Computer and Information Sciences
                Neural Networks
                Biology and Life Sciences
                Neuroscience
                Neural Networks
                Biology and Life Sciences
                Anatomy
                Musculoskeletal System
                Skeleton
                Skull
                Mastoid Process
                Medicine and Health Sciences
                Anatomy
                Musculoskeletal System
                Skeleton
                Skull
                Mastoid Process
                Custom metadata
                All relevant data are within the manuscript and its Supporting Information files.

                Uncategorized
                Uncategorized

                Comments

                Comment on this article