Automatic lesion detection and segmentation in 18F-flutemetamol positron emission tomography images using deep learning

BACKGROUND

Beta amyloid in the brain, which was originally confirmed by post-mortem examinations, can now be confirmed in living patients using amyloid positron emission tomography (PET) tracers, and the accuracy of diagnosis can be improved by beta amyloid plaque confirmation in patients. Amyloid deposition in the brain is often associated with the expression of dementia. Hence, it is important to identify the anatomically and functionally meaningful areas of the human brain cortex surface using PET to diagnose the possibility of developing dementia. In this study, we demonstrated the validity of automated ¹⁸F-flutemetamol PET lesion detection and segmentation based on a complete 2D U-Net convolutional neural network via masking treatment strategies.

METHODS

PET data were first normalized by volume and divided into five amyloid accumulation zones through axial, coronary, and thalamic slices. A single U-Net was trained using a divided dataset for one of these zones. Ground truth segmentations were obtained by manual delineation and thresholding (1.5 × background).

RESULTS

The following intersection over union values were obtained for the various slices in the verification dataset: frontal lobe axial/sagittal: 0.733/0.804; posterior cingulate cortex and precuneus coronal/sagittal: 0.661/0.726; lateral temporal lobe axial/coronal: 0.864/0.892; parietal lobe axial/coronal: 0.542/0.759; and striatum axial/sagittal: 0.679/0.752. The U-Net convolutional neural network architecture allowed fully automated 2D division of the ¹⁸F-flutemetamol PET brain images of Alzheimer's patients.

CONCLUSIONS

As dementia should be tested and evaluated in various ways, there is a need for artificial intelligence programs. This study can serve as a reference for future studies using auxiliary roles and research in Alzheimer's diagnosis.

Comparison of 11C-Pittsburgh Compound B and 18F-Flutemetamol White Matter Binding in PET

PET imaging with β-amyloid ligands is emerging as a molecular imaging technique targeting white matter integrity and demyelination. β-amyloid PET ligands such as 11C-Pittsburgh compound B (11C-PiB) have been considered for quantitative measurement of myelin content changes in multiple sclerosis, but 11C-PiB is not commercially available given its short half-life. A 18F PET ligand such as flutemetamol with a longer half-life may be an alternative, but its ability to differentiate white matter hyperintensities (WMH) from normal-appearing white matter (NAWM) and its relationship with age remains to be investigated. Methods: Cognitively unimpaired (CU) older and younger adults (n = 61) were recruited from the community responding to a study advertisement for β-amyloid PET. Participants prospectively underwent MRI, 11C-PiB, and 18F-flutemetamol PET scans. MRI fluid-attenuated inversion recovery images were segmented into WMH and NAWM and registered to the T1-weighted MRI. 11C-PiB and 18F-flutemetamol PET images were also registered to the T1-weighted MRI. 11C-PiB and 18F-flutemetamol SUV ratios (SUVrs) from the WMH and NAWM were calculated using cerebellar crus uptake as a reference for both 11C-PiB and 18F-flutemetamol. Results: The median age was 38 y (range, 30-48 y) in younger adults and 67 y (range, 61-83 y) in older adults. WMH and NAWM SUVrs were higher with 18F-flutemetamol than with 11C-PiB in both older (P < 0.001) and younger (P < 0.001) CU adults. 11C-PiB and 18F-flutemetamol SUVrs were higher in older than in younger CU adults in both WMH (P < 0.001) and NAWM (P < 0.001). 11C-PiB and 18F-flutemetamol SUVrs were higher in NAWM than WMH in both older (P < 0.001) and younger (P < 0.001) CU adults. There was no apparent difference between 11C-PiB and 18F-flutemetamol SUVrs in differentiating WMH from NAWM in older and in younger adults. Conclusion:11C-PiB and 18F-flutemetamol show a similar topographic pattern of uptake in white matter with a similar association with age in WMH and NAWM. 11C-PiB and 18F-flutemetamol can also effectively distinguish between WMH and NAWM. However, given its longer half-life, commercial availability, and higher binding potential, 18F-flutemetamol can be an alternative to 11C-PiB in molecular imaging studies specifically targeting multiple sclerosis to evaluate white matter integrity.

Effect of different examination conditions on image quality and quantitative value of amyloid positron emission tomography using 18F-flutemetamol

OBJECTIVE

The recommended start time for ¹⁸F-flutemetamol amyloid positron emission tomography (PET) examination is 60-120 min after ¹⁸F-flutemetamol injection, while an acquisition time of 10-30 min is generally recommended. We aimed to elucidate the effects of different examination conditions on image quality, diagnostic ability, and quantitative value of amyloid PET using ¹⁸F-flutemetamol.

METHODS

We acquired data on a Discovery PET/computed tomography 710 scanner using Hoffman brain and pillar phantoms with 20 MBq of ¹⁸F for 30 min. The images were reconstructed into 10-, 20-, and 30-min periods. The ordered subset-expectation maximization algorithm was used for image reconstruction, which uses a 2- or 4-mm Gaussian filter and a combination of iteration and subset numbers. The percentage contrast and coefficient of variation (CV; as the image noise) were used as physical evaluation indices for reconstructed images, and images with superior contrast and low image noise were selected for clinical evaluation. The imaging data of 15 symptomatic patients (n = 7 and n = 8 for positive and negative diagnoses of Alzheimer's disease, respectively) were reconstructed under the phantom study conditions. Radiographers visually evaluated and ranked the clinical images based on the overall contrast and image noise, and nuclear medicine specialists diagnosed Alzheimer's disease. We compared the standardized uptake value ratio (SUVR) obtained with different acquisition conditions.

RESULTS

The basic study using the phantom revealed high convergence of contrast and image noise in five patterns of acquisition time and filter strengths. Regarding visual evaluation, the use of a 2-mm Gaussian filter caused difficulties in diagnosis because the brain parenchymal accumulation was mottled with high image noise. Differences in image quality and diagnostic ability due to different examination times were not significant. Differences in the SUVR were not significant in patients with a negative Alzheimer's disease diagnosis; in patients with a positive diagnosis, the SUVR showed significant fluctuation depending on the acquisition conditions.

CONCLUSION

The differences in image quality and diagnostic performance due to the differences in 10-min acquisition time were not significant; however, of note, SUVR showed significant fluctuation depending on the acquisition conditions in patients diagnosed with Alzheimer's disease.

Head-to-Head Comparison of 18F-Florbetaben and 18F-Flutemetamol in the Cortical and Striatal Regions

BACKGROUND

18F-florbetaben (FBB) and 18F-flutemetamol (FMM) amyloid PET have been developed and approved for clinical use. It is important to understand the distinct features of these ligands to compare and correctly interpret the results of different amyloid PET studies.

OBJECTIVE

We performed a head-to-head comparison of FBB and FMM to compare with regard to imaging characteristics, including dynamic range of retention, and differences in quantitative measurements between the two ligands in cortical, striatal, and white matter (WM) regions.

METHODS

Paired FBB and FMM PET images were acquired in 107 participants. Correlations of FBB and FMM amyloid deposition in the cortex, striatum, and WM were investigated and compared in different reference regions (cerebellar gray matter (CG), whole cerebellum (WC), WC with brainstem (WC + B), and pons).

RESULTS

The cortical SUVR (R2 = 0.97) and striatal SUVR (R2 = 0.95) demonstrated an excellent linear correlation between FBB and FMM using a WC as reference region. There was no difference in the cortical SUVR ratio between the two ligands (p = 0.90), but the striatal SUVR ratio was higher in FMM than in FBB (p < 0.001). Also, the effect size of differences in striatal SUVR seemed to be higher with FMM (2.61) than with FBB (2.34). These trends were similarly observed according to four different reference regions (CG, WC, WC + B, and pons).

CONCLUSION

Our findings suggest that FMM might be better than FBB to detect amyloid burden in the striatum, although both ligands are comparable for imaging AD pathology in vivo.

Quantitative Evaluation of 18F-Flutemetamol PET in Patients With Cognitive Impairment and Suspected Alzheimer's Disease: A Multicenter Study

Background: In clinical practice, equivocal findings are inevitable in visual interpretation of whether amyloid positron emission tomography (PET) is positive or negative. It is therefore necessary to establish a more objective quantitative evaluation method for determining the indication for disease-modifying drugs currently under development.

Aims: We aimed to determine cutoffs for positivity in quantitative analysis of ¹⁸F-flutemetamol PET in patients with cognitive impairment and suspected Alzheimer's disease (AD). We also evaluated the clinical efficacy of amyloid PET in the diagnosis of AD. This study was registered in the Japan Registry of Clinical Trials (jRCTs, 031180321).

Methods: Ninety-three patients suspected of having AD underwent ¹⁸F-flutemetamol PET in seven institutions. A PET image for each patient was visually assessed and dichotomously rated as either amyloid-positive or amyloid-negative by two board-certified nuclear medicine physicians. If the two readers obtained different interpretations, the visual rating was rerun until they reached consensus. The PET images were quantitatively analyzed using the standardized uptake value ratio (SUVR) and standardized Centiloid (CL) scale with the whole cerebellum as a reference area.

Results: Visual interpretation obtained 61 positive and 32 negative PET scans. Receiver operating characteristic analysis determined the best agreement of quantitative assessments and visual interpretation of PET scans to have an area under curve of 0.982 at an SUVR of 1.13 and a CL of 16. Using these cutoff values, there was high agreement between the two approaches (kappa = 0.88). Five discordant cases had SUVR and CL values ranging from 1.00 to 1.22 and from 1 to 26, respectively. In these discordant cases, either diffuse or mildly focal elevation of cortical activity confused visual interpretation. The amyloid PET outcome significantly altered the diagnosis of AD (χ² = 51.3, p < 0.0001). PET imaging elevated the proportions of the very high likelihood category from 20.4 to 46.2% and the very low likelihood category from 0 to 22.6%.

Conclusion: Quantitative analysis of amyloid PET using ¹⁸F-flutemetamol can objectively evaluate amyloid positivity using the determined cutoffs for SUVR and CL. Moreover, amyloid PET may have added value over the standard diagnostic workup in dementia patients with cognitive impairment and suspected AD.

Temporal and anatomical distribution of 18F-flutemetamol uptake in canine brain using positron emission tomography

BACKGROUND

Positron emission tomography (PET) is increasingly being used as an imaging modality for clinical and research applications in veterinary medicine. Amyloid PET has become a useful tool for diagnosing Alzheimer's disease (AD) in humans, by accurately identifying amyloid-beta (Aβ) plaques. Cognitive dysfunction syndrome in dogs shows cognitive and pathophysiologic characteristics similar to AD. Therefore, we assessed the physiologic characteristics of uptake of 18F-flutemetamol, an Aβ protein-binding PET tracer in clinical development, in normal dog brains, for distinguishing an abnormal state. Static and dynamic PET images of six adult healthy dogs were acquired after 18F-flutemetamol was administered intravenously at approximately 3.083 MBq/kg. For static images, PET data were acquired at 30, 60, and 90 min after injection. One week later, dynamic images were acquired for 120 min, from the time of tracer injection. PET data were reconstructed using an iterative technique, and corrections for attenuation and scatter were applied. Regions of interest were manually drawn over the frontal, parietal, temporal, occipital, anterior cingulate, posterior cingulate, and cerebellar cortices, cerebral white matter, midbrain, pons, and medulla oblongata. After calculating standardized uptake values with an established formula, standardized uptake value ratios (SUVRs) were obtained, using the cerebellar cortex as a reference region.

RESULTS

Among the six cerebral cortical regions, the cingulate cortices and frontal lobe showed the highest SUVRs. The lowest SUVR was observed in the occipital lobe. The average values of the cortical SUVRs were 1.25, 1.26, and 1.27 at 30, 60, and 90 min post-injection, respectively. Tracer uptake on dynamic scans was rapid, peaking within 4 min post-injection. After reaching this early maximum, cerebral cortical regions showed a curve with a steep descent, whereas cerebral white matter demonstrated a curve with a slow decline, resulting in a large gap between cerebral cortical regions and white matter.

CONCLUSION

This study provides normal baseline data of 18F-flutemetamol PET that can facilitate an objective diagnosis of cognitive dysfunction syndrome in dogs in future.

Amyloid PET imaging in cardiac amyloidosis: a pilot study using 18F-flutemetamol positron emission tomography

OBJECTIVE

Cardiac amyloidosis is a rare disease characterized by amyloid heart deposits and is usually a part of systemic amyloidosis, in relation to systemic light chain (AL) and transthyretin (ATTR wild-type or genetic) amyloidosis. Several recent studies suggest a promising role of amyloid PET imaging to image cardiac amyloidosis, and several PET tracers are now available for in vivo detection of amyloid deposits. The aim of this study was to evaluate ¹⁸F-flutemetamol in diagnosing cardiac amyloidosis.

METHODS

We performed a pilot study using ¹⁸F-flutemetamol (Vizamyl™) in 12 patients, 3 control subjects without cardiac amyloidosis, and 9 subjects with documented cardiac amyloidosis. Mean standardized uptake value (SUV) in the left ventricular myocardium and blood pool was determined and semi-quantitative parameter as target to background ratio (TBR, myocardial/blood pool mean SUV ratio) between 10th and 30th minutes was calculated.

RESULTS

Uptake of ¹⁸F-flutemetamol in the left ventricular myocardium was noted in all patients with cardiac amyloidosis except one and none in control patient. The TBR was significantly higher in amyloidosis patients than in control subjects: 1.46, interquartile range (IQR) 1.32-2.06 versus 1.06, IQR 0.72-1.1 (p = 0.033). Only one patient in our study had light chain amyloidosis and showed higher TBR than patients with transthyretin amyloid: TBR 3.0 versus TBR median 1.44, IQR 1.33-1.69.

CONCLUSION

Amyloid PET tracers such as ¹⁸F-flutemetamol could be a promising tool in diagnosing and in therapy response assessment for patients with cardiac amyloidosis.

Assessment of brain beta-amyloid deposition in transgenic mouse models of Alzheimer's disease with PET imaging agents 18F-flutemetamol and 18F-florbetaben

BACKGROUND

Although amyloid beta (Aβ) imaging is widely used for diagnosing and monitoring Alzheimer's disease in clinical fields, paralleling comparison between 18F-flutemetamol and 18F-florbetaben was rarely attempted in AD mouse model. We performed a comparison of Aβ PET images between 18F-flutemetamol and 18F-florbetaben in a recently developed APPswe mouse model, C57BL/6-Tg (NSE-hAPPsw) Korl.

RESULTS

After an injection (0.23 mCi) of 18F-flutemetamol and 18F-florbetaben at a time interval of 2-3 days, we compared group difference of SUVR and kinetic parameters between the AD (n = 7) and control (n = 7) mice, as well as between 18F-flutemetamol and 18F-florbetaben image. In addition, bio-distribution and histopathology were conducted. With visual image and VOI-based SUVR analysis, the AD group presented more prominent uptake than did the control group in both the 18F-florbetaben and 18F-flutemetamol images. With kinetic analysis, the 18F-florbetaben images showed differences in K1 and k4 between the AD and control groups, although 18F-flutemetamol images did not show significant difference. 18F-florbetaben images showed more prominent cortical uptake and matched well to the thioflavin S staining images than did the 18F-flutemetamol image. In contrast, 18F-flutemetamol images presented higher K1, k4, K1/k2 values than those of 18F-florbetaben images. Also, 18F-flutemetamol images presented prominent uptake in the bowel and bladder, consistent with higher bio-distribution in kidney, lung, blood and heart.

CONCLUSIONS

Compared with 18F-flutemetamol images, 18F-florbetaben images showed prominent visual uptake intensity, SUVR, and higher correlations with the pathology. In contrast, 18F-flutemetamol was more actively metabolized than was 18F-florbetaben (Son et al. in J Nucl Med 58(Suppl 1):S278, 2017].

Patients with Amyloid-Negative Mild Cognitive Impairment have Cortical Hypometabolism but the Hippocampus is Preserved

BACKGROUND

Patients with mild cognitive impairment (MCI) are at risk for Alzheimer's dementia but the presence of amyloid (Aβ) strongly increases this risk. In clinical settings, when Aβ status is not available, different neurodegenerative markers are used to characterize MCI. The accuracy of these markers to discriminate between Aβ-and Aβ+ MCI is not yet determined.

OBJECTIVE

To compare different markers of neurodegeneration in Aβ-and Aβ+ MCI, with an Aβ-elderly control (EC) group.

METHODS

Patients with MCI (n = 39) and EC (n = 28) underwent MRI, 18F-FDG PET, and Aβ PET (18F-flutemetamol). We compared FDG and MRI biomarker values in cortical and hippocampal regions of interest, and using voxel-wise surface maps. We computed ROC curves discriminating between the three groups for each biomarker.

RESULTS

All biomarker values were reduced in Aβ+ MCI compared to EC (p < 0.001). Aβ-MCI had low cortical metabolism (p = 0.002), but hippocampal volume, cortical thickness, and hippocampal metabolism were not significantly different between Aβ-MCI and EC (p > 0.40). Cortical metabolism best discriminated between MCI and EC (AUC = 0.92/0.86, Aβ+/Aβ-) while hippocampal volume best discriminated between Aβ-MCI and Aβ+ MCI (AUC = 0.79).

CONCLUSIONS

Cortical hypometabolism was observed in both Aβ-MCI and Aβ+ MCI whereas hippocampal atrophy was mostly found in Aβ+ MCI. For MCI patients without available Aβ information, hippocampal atrophy is thus more informative about Aβ status than cortical hypometabolism.

Functional Changes in the Language Network in Response to Increased Amyloid β Deposition in Cognitively Intact Older Adults

Word finding symptoms are frequent early in the course of Alzheimer's disease and relate principally to functional changes in left posterior temporal cortex. In cognitively intact older adults, we examined whether amyloid load affects the network for language and associative-semantic processing. Fifty-six community-recruited subjects (52-74 years), stratified for apolipoprotein E and brain-derived neurotrophic factor genotype, received a neurolinguistic assessment, (18)F-flutemetamol positron emission tomography, and a functional MRI of the associative-semantic system. The primary measure of amyloid load was the cerebral-to-cerebellar gray matter standardized uptake value ratio in a composite cortical volume of interest (SUVR(comp)). The primary outcome analysis consisted of a whole-brain voxelwise linear regression between SUVR(comp) and fMRI response during associative-semantic versus visuoperceptual processing. Higher activity in one region, the posterior left middle temporal gyrus, correlated positively with increased amyloid load. The correlation remained significant when only the word conditions were contrasted but not for pictures. According to a stepwise linear regression analysis, offline naming reaction times correlated positively with SUVR(comp). A binary classification into amyloid-positive and amyloid-negative cases confirmed our findings. The left posterior temporal activity increase may reflect higher demands for semantic control in the presence of a higher amyloid burden.

Automated quantification of 18F-flutemetamol PET activity for categorizing scans as negative or positive for brain amyloid: concordance with visual image reads

Clinical trials of the PET amyloid imaging agent (18)F-flutemetamol have used visual assessment to classify PET scans as negative or positive for brain amyloid. However, quantification provides additional information about regional and global tracer uptake and may have utility for image assessment over time and across different centers. Using postmortem brain neuritic plaque density data as a truth standard to derive a standardized uptake value ratio (SUVR) threshold, we assessed a fully automated quantification method comparing visual and quantitative scan categorizations. We also compared the histopathology-derived SUVR threshold with one derived from healthy controls.

METHODS

Data from 345 consenting subjects enrolled in 8 prior clinical trials of (18)F-flutemetamol injection were used. We grouped subjects into 3 cohorts: an autopsy cohort (n = 68) comprising terminally ill patients with postmortem confirmation of brain amyloid status; a test cohort (n = 172) comprising 33 patients with clinically probable Alzheimer disease, 80 patients with mild cognitive impairment, and 59 healthy volunteers; and a healthy cohort of 105 volunteers, used to define a reference range for SUVR. Visual image categorizations for comparison were from a previous study. A fully automated PET-only quantification method was used to compute regional neocortical SUVRs that were combined into a single composite SUVR. An SUVR threshold for classifying scans as positive or negative was derived by ranking the PET scans from the autopsy cohort based on their composite SUVR and comparing data with the standard of truth based on postmortem brain amyloid status for subjects in the autopsy cohort. The derived threshold was used to categorize the 172 scans in the test cohort as negative or positive, and results were compared with categorization using visual assessment. Different reference and composite region definitions were assessed. Threshold levels were also compared with corresponding thresholds derived from the healthy group.

RESULTS

Automated quantification (using pons as the reference region) demonstrated 91% sensitivity and 88% specificity and gave 3 false-positive and 4 false-negative scans. All 3 false-positive cases were either borderline-normal by standard of truth or had moderate to heavy cortical diffuse plaque burden. In the test cohort, the concordance between quantitative and visual read categorization ranged from 97.1% to 99.4% depending on the selection of reference and composite regions. The threshold derived from the healthy group was close to the histopathology-derived threshold.

CONCLUSION

Categorization of (18)F-flutemetamol amyloid imaging data using an automated PET-only quantification method showed good agreement with histopathologic classification of neuritic plaque density and a strong concordance with visual read results.

Implementation and validation of an adaptive template registration method for 18F-flutemetamol imaging data

The spatial normalization of PET amyloid imaging data is challenging because different white and gray matter patterns of negative (Aβ-) and positive (Aβ+) uptake could lead to systematic bias if a standard method is used. In this study, we propose the use of an adaptive template registration method to overcome this problem.

METHODS

Data from a phase II study (n = 72) were used to model amyloid deposition with the investigational PET imaging agent (18)F-flutemetamol. Linear regression of voxel intensities on the standardized uptake value ratio (SUVR) in a neocortical composite region for all scans gave an intercept image and a slope image. We devised a method where an adaptive template image spanning the uptake range (the most Aβ- to the most Aβ+ image) can be generated through a linear combination of these 2 images and where the optimal template is selected as part of the registration process. We applied the method to the (18)F-flutemetamol phase II data using a fixed volume of interest atlas to compute SUVRs. Validation was performed in several steps. The PET-only adaptive template registration method and the MR imaging-based method used in statistical parametric mapping were applied to spatially normalize PET and MR scans, respectively. Resulting transformations were applied to coregistered gray matter probability maps, and the quality of the registrations was assessed visually and quantitatively. For comparison of quantification results with an independent patient-space method, FreeSurfer was used to segment each subject's MR scan and the parcellations were applied to the coregistered PET scans. We then correlated SUVRs for a composite neocortical region obtained with both methods. Furthermore, to investigate whether the (18)F-flutemetamol model could be generalized to (11)C-Pittsburgh compound B ((11)C-PIB), we applied the method to Australian Imaging, Biomarkers and Lifestyle (AIBL) (11)C-PIB scans (n = 285) and compared the PET-only neocortical composite score with the corresponding score obtained with a semimanual method that made use of the subject's MR images for the positioning of regions.

RESULTS

Spatial normalization was successful on all scans. Visual and quantitative comparison of the new PET-only method with the MR imaging-based method of statistical parametric mapping indicated that performance was similar in the cortical regions although the new PET-only method showed better registration in the cerebellum and pons reference region area. For the (18)F-flutemetamol quantification, there was a strong correlation between the PET-only and FreeSurfer SUVRs (Pearson r = 0.96). We obtained a similar correlation for the AIBL (11)C-PIB data (Pearson r = 0.94).

CONCLUSION

The derived adaptive template registration method allows for robust, accurate, and fully automated quantification of uptake for (18)F-flutemetamol and (11)C-PIB scans without the use of MR imaging data.