Regional SUV quantification in hybrid PET/MR, a comparison of two atlas-based automatic brain segmentation methods

Identification of Parkinson's disease and multiple system atrophy using multimodal PET/MRI radiomics

OBJECTIVES

To construct a machine learning model for differentiating Parkinson's disease (PD) and multiple system atrophy (MSA) by using multimodal PET/MRI radiomics and clinical characteristics.

METHODS

One hundred and nineteen patients (81 with PD and 38 with MSA) underwent brain PET/CT and MRI to obtain metabolic images ([18F]FDG, [11C]CFT PET) and structural MRI (T1WI, T2WI, and T2-FLAIR). Image analysis included automatic segmentation on MRI, co-registration of PET images onto the corresponding MRI. Radiomics features were then extracted from the putamina and caudate nuclei and selected to construct predictive models. Moreover, based on PET/MRI radiomics and clinical characteristics, we developed a nomogram. Receiver operating characteristic (ROC) curves were performed to evaluate the performance of the models. Decision curve analysis (DCA) was employed to access the clinical usefulness of the models.

RESULTS

The combined PET/MRI radiomics model of five sequences outperformed monomodal radiomics models alone. Further, PET/MRI radiomics-clinical combined model could perfectly distinguish PD from MSA (AUC = 0.993), which outperformed the clinical model (AUC = 0.923, p = 0.028) in training set, with no significant difference in test set (AUC = 0.860 vs 0.917, p = 0.390). However, no significant difference was found between PET/MRI radiomics-clinical model and PET/MRI radiomics model in training (AUC = 0.988, p = 0.276) and test sets (AUC = 0.860 vs 0.845, p = 0.632). DCA demonstrated the highest clinical benefit of PET/MRI radiomics-clinical model.

CONCLUSIONS

Our study indicates that multimodal PET/MRI radiomics could achieve promising performance to differentiate between PD and MSA in clinics.

CLINICAL RELEVANCE STATEMENT

This study developed an optimal radiomics signature and construct model to distinguish PD from MSA by multimodal PET/MRI imaging methods in clinics for parkinsonian syndromes, which achieved an excellent performance.

KEY POINTS

•Multimodal PET/MRI radiomics from putamina and caudate nuclei increase the diagnostic efficiency for distinguishing PD from MSA. •The radiomics-based nomogram was developed to differentiate between PD and MSA. •Combining PET/MRI radiomics-clinical model achieved promising performance to identify PD and MSA.

Deep learning segmentation results in precise delineation of the putamen in multiple system atrophy

OBJECTIVES

The precise segmentation of atrophic structures remains challenging in neurodegenerative diseases. We determined the performance of a Deep Neural Patchwork (DNP) in comparison to established segmentation algorithms regarding the ability to delineate the putamen in multiple system atrophy (MSA), Parkinson's disease (PD), and healthy controls.

METHODS

We retrospectively included patients with MSA and PD as well as healthy controls. A DNP was trained on manual segmentations of the putamen as ground truth. For this, the cohort was randomly split into a training (N = 131) and test set (N = 120). The DNP's performance was compared with putaminal segmentations as derived by Automatic Anatomic Labelling, Freesurfer and Fastsurfer. For validation, we assessed the diagnostic accuracy of the resulting segmentations in the delineation of MSA vs. PD and healthy controls.

RESULTS

A total of 251 subjects (61 patients with MSA, 158 patients with PD, and 32 healthy controls; mean age of 61.5 ± 8.8 years) were included. Compared to the dice-coefficient of the DNP (0.96), we noted significantly weaker performance for AAL3 (0.72; p < .001), Freesurfer (0.82; p < .001), and Fastsurfer (0.84, p < .001). This was corroborated by the superior diagnostic performance of MSA vs. PD and HC of the DNP (AUC 0.93) versus the AUC of 0.88 for AAL3 (p = 0.02), 0.86 for Freesurfer (p = 0.048), and 0.85 for Fastsurfer (p = 0.04).

CONCLUSION

By utilization of a DNP, accurate segmentations of the putamen can be obtained even if substantial atrophy is present. This allows for more precise extraction of imaging parameters or shape features from the putamen in relevant patient cohorts.

CLINICAL RELEVANCE STATEMENT

Deep learning-based segmentation of the putamen was superior to currently available algorithms and is beneficial for the diagnosis of multiple system atrophy.

KEY POINTS

• A Deep Neural Patchwork precisely delineates the putamen and performs equal to human labeling in multiple system atrophy, even when pronounced putaminal volume loss is present. • The Deep Neural Patchwork-based segmentation was more capable to differentiate between multiple system atrophy and Parkinson's disease than the AAL3 atlas, Freesurfer, or Fastsurfer.

Characterizing Early-Onset Alzheimer Disease Using Multiprobe PET/MRI: An AT(N) Framework-Based Study

PURPOSE

Early-onset Alzheimer disease (EOAD) is rare, highly heterogeneous, and associated with poor prognosis. This AT(N) Framework-based study aimed to compare multiprobe PET/MRI findings between EOAD and late-onset Alzheimer disease (LOAD) patients and explore potential imaging biomarkers for characterizing EOAD.

METHODS

Patients with AD who underwent PET/MRI in our PET center were retrospectively reviewed and grouped according to the age at disease onset: EOAD, younger than 60 years; and LOAD, 60 years or older. Clinical characteristics were recorded. All study patients had positive β-amyloid PET imaging; some patients also underwent 18 F-FDG and 18 F-florzolotau PET. Imaging of the EOAD and LOAD groups was compared using region-of-interest and voxel-based analysis. Correlation of onset age and regional SUV ratios were also evaluated.

RESULTS

One hundred thirty-three patients were analyzed (75 EOAD and 58 LOAD patients). Sex ( P = 0.515) and education ( P = 0.412) did not significantly differ between groups. Mini-Mental State Examination score was significantly lower in the EOAD group (14.32 ± 6.74 vs 18.67 ± 7.20, P = 0.004). β-Amyloid deposition did not significantly differ between groups. Glucose metabolism in the frontal, parietal, precuneus, temporal, occipital lobe, and supramarginal and angular gyri was significantly lower in the EOAD group (n = 49) than in the LOAD group (n = 44). In voxel-based morphometry analysis, right posterior cingulate/precuneus atrophy was more obvious in the EOAD ( P < 0.001), although no voxel survived family-wise error correction. Tau deposition in the precuneus, parietal lobe, and angular, supramarginal, and right middle frontal gyri was significantly higher in the EOAD group (n = 18) than in the LOAD group (n = 13).

CONCLUSIONS

Multiprobe PET/MRI showed that tau burden and neuronal damage are more severe in EOAD than in LOAD. Multiprobe PET/MRI may be useful to assess the pathologic characteristics of EOAD.

Segmentation of Infant Brain Using Nonnegative Matrix Factorization

This study develops an atlas-based automated framework for segmenting infants’ brains from magnetic resonance imaging (MRI). For the accurate segmentation of different structures of an infant’s brain at the isointense age (6–12 months), our framework integrates features of diffusion tensor imaging (DTI) (e.g., the fractional anisotropy (FA)). A brain diffusion tensor (DT) image and its region map are considered samples of a Markov–Gibbs random field (MGRF) that jointly models visual appearance, shape, and spatial homogeneity of a goal structure. The visual appearance is modeled with an empirical distribution of the probability of the DTI features, fused by their nonnegative matrix factorization (NMF) and allocation to data clusters. Projecting an initial high-dimensional feature space onto a low-dimensional space of the significant fused features with the NMF allows for better separation of the goal structure and its background. The cluster centers in the latter space are determined at the training stage by the K-means clustering. In order to adapt to large infant brain inhomogeneities and segment the brain images more accurately, appearance descriptors of both the first-order and second-order are taken into account in the fused NMF feature space. Additionally, a second-order MGRF model is used to describe the appearance based on the voxel intensities and their pairwise spatial dependencies. An adaptive shape prior that is spatially variant is constructed from a training set of co-aligned images, forming an atlas database. Moreover, the spatial homogeneity of the shape is described with a spatially uniform 3D MGRF of the second-order for region labels. In vivo experiments on nine infant datasets showed promising results in terms of the accuracy, which was computed using three metrics: the 95-percentile modified Hausdorff distance (MHD), the Dice similarity coefficient (DSC), and the absolute volume difference (AVD). Both the quantitative and visual assessments confirm that integrating the proposed NMF-fused DTI feature and intensity MGRF models of visual appearance, the adaptive shape prior, and the shape homogeneity MGRF model is promising in segmenting the infant brain DTI.

Machine Learning Quantitative Analysis of FDG PET Images of Medial Temporal Lobe Epilepsy Patients

PURPOSE

18F-FDG PET is widely used in epilepsy surgery. We established a robust quantitative algorithm for the lateralization of epileptogenic foci and examined the value of machine learning of 18F-FDG PET data in medial temporal lobe epilepsy (MTLE) patients.

PATIENTS AND METHODS

We retrospectively reviewed patients who underwent surgery for MTLE. Three clinicians identified the side of MTLE epileptogenesis by visual inspection. The surgical side was set as the epileptogenic side. Two parcellation paradigms and corresponding atlases (Automated Anatomical Labeling and FreeSurfer aparc + aseg) were used to extract the normalized PET uptake of the regions of interest (ROIs). The lateralization index of the MTLE-associated regions in either hemisphere was calculated. The lateralization indices of each ROI were subjected for machine learning to establish the model for classifying the side of MTLE epileptogenesis.

RESULT

Ninety-three patients were enrolled for training and validation, and another 11 patients were used for testing. The hit rate of lateralization by visual analysis was 75.3%. Among the 23 patients whose MTLE side of epileptogenesis was incorrectly determined or for whom no conclusion was reached by visual analysis, the Automated Anatomical Labeling and aparc + aseg parcellated the associated ROIs on the correctly lateralized MTLE side in 100.0% and 82.6%. In the testing set, lateralization accuracy was 100% in the 2 paradigms.

CONCLUSIONS

Visual analysis of 18F-FDG PET to lateralize MTLE epileptogenesis showed a lower hit rate compared with machine-assisted interpretation. While reviewing 18F-FDG PET images of MTLE patients, considering the regions associated with MTLE resulted in better performance than limiting analysis to hippocampal regions.

18F-APN-1607 Tau Positron Emission Tomography Imaging for Evaluating Disease Progression in Alzheimer’s Disease

Purpose

¹⁸F-APN-1607 is a novel tau positron emission tomography (PET) tracer characterized with high binding affinity for 3− and 4-repeat tau deposits. The aim was to analyze the spatial distribution of ¹⁸F-APN-1607 PET imaging in Alzheimer’s disease (AD) subjects with different stages and to investigate the relationship between the change of tau deposition and overall disease progression.

Methods

We retrospectively analyzed the ¹⁸F-APN-1607 PET imaging of 31 subjects with clinically and imaging defined as AD. According to the Mini-Mental State Examination (MMSE) score, patients were divided into three groups, namely, mild (≥21, n = 7), moderate (10–20, n = 16), and severe (≤9, n = 8). PET imaging was segmented to 70 regions of interest (ROIs) and extracted the standard uptake value (SUV) of each ROI. SUV ratio (SUVR) was calculated from the ratio of SUV in different brain regions to the cerebellar cortex. The regions were defined as positive and negative with unsupervised cluster analysis according to SUVR. The SUVRs of each region were compared among groups with the one-way ANOVA or Kruskal–Wallis H test. Furthermore, the correlations between MMSE score and regional SUVR were calculated with Pearson or Spearman correlation analysis.

Results

There were no significant differences among groups in gender (χ² = 3.814, P = 0.161), age of onset (P = 0.170), age (P = 0.109), and education level (P = 0.065). With the disease progression, the ¹⁸F-APN-1607 PET imaging showed the spread of tau deposition from the hippocampus, posterior cingulate gyrus (PCG), and lateral temporal cortex (LTC) to the parietal and occipital lobes, and finally to the frontal lobe. Between the mild and moderate groups, the main brain areas with significant differences in ¹⁸F-APN-1607 uptake were supplementary motor area (SMA), cuneus, precuneus, occipital lobule, paracentral lobule, right angular gyrus, and parietal, which could be used for early disease progression assessment (P < 0.05). There were significant differences in the frontal lobe, right temporal lobe, and fusiform gyrus between the moderate and severe groups, which might be suitable for the late-stage disease progression assessment (P < 0.05).

Conclusion

¹⁸F-APN-1607 PET may serve as an effective imaging marker for visualizing the change pattern of tau protein deposition in AD patients, and its uptake level in certain brain regions is closely related to the severity of cognitive impairment. These indicate the potential of ¹⁸F-APN-1607 PET for the in vivo evaluation of the progression of AD.

A Baboon Brain Atlas for Magnetic Resonance Imaging and Positron Emission Tomography Image Analysis

The olive baboon (Papio anubis) is phylogenetically proximal to humans. Investigation into the baboon brain has shed light on the function and organization of the human brain, as well as on the mechanistic insights of neurological disorders such as Alzheimer's and Parkinson's. Non-invasive brain imaging, including positron emission tomography (PET) and magnetic resonance imaging (MRI), are the primary outcome measures frequently used in baboon studies. PET functional imaging has long been used to study cerebral metabolic processes, though it lacks clear and reliable anatomical information. In contrast, MRI provides a clear definition of soft tissue with high resolution and contrast to distinguish brain pathology and anatomy, but lacks specific markers of neuroreceptors and/or neurometabolites. There is a need to create a brain atlas that combines the anatomical and functional/neurochemical data independently available from MRI and PET. For this purpose, a three-dimensional atlas of the olive baboon brain was developed to enable multimodal imaging analysis. The atlas was created on a population-representative template encompassing 89 baboon brains. The atlas defines 24 brain regions, including the thalamus, cerebral cortex, putamen, corpus callosum, and insula. The atlas was evaluated with four MRI images and 20 PET images employing the radiotracers for [11C]benzamide, [11C]metergoline, [18F]FAHA, and [11C]rolipram, with and without structural aids like [18F]flurodeoxyglycose images. The atlas-based analysis pipeline includes automated segmentation, registration, quantification of region volume, the volume of distribution, and standardized uptake value. Results showed that, in comparison to PET analysis utilizing the "gold standard" manual quantification by neuroscientists, the performance of the atlas-based analysis was at >80 and >70% agreement for MRI and PET, respectively. The atlas can serve as a foundation for further refinement, and incorporation into a high-throughput workflow of baboon PET and MRI data. The new atlas is freely available on the Figshare online repository (https://doi.org/10.6084/m9.figshare.16663339), and the template images are available from neuroImaging tools & resources collaboratory (NITRC) (https://www.nitrc.org/projects/haiko89/).