• Biomedical Science Letters
• /
• v.25 no.1
• /
• pp.7-14
• /
• 2019

Alzheimer's disease (AD) is highly prevalent in dementia, with no specifically effective treatment having yet been discovered. Amyloid plaques are one of the key hallmarks of AD. Transgenic mouse models exhibiting Alzheimer's disease-like pathology have been widely used to study the pathophysiology of Alzheimer's disease. In this study, we showed an age-dependent correlation between cognitive function, pathological findings, and [F-18] Florbetaben (FBB) PET images. Nineteen transgenic mice (12 with AD, 7 with controls) were used for this study. We observed an increase in ${\beta}$-Amyloid deposition ($A{\beta}$) in brain tissue and [F-18] FBB amyloid PET imaging in the AD group. The [F-18] FBB data showed a mildly negative trend with cognitive function. Pathological findings were negatively correlated with cognitive functions. These finding suggests that amyloid beta deposition can be well-monitored with [F-18] FBB PET and a decline in cognitive function is related to the increase in amyloid plaque burden.

• Biomedical Science Letters
• /
• v.25 no.1
• /
• pp.99-106
• /
• 2019

Amyloid positron emission tomography (PET) allows early and accurate diagnosis in suspected cases of Alzheimer's disease (AD) and contributes to future treatment plans. In the present study, a method of implementing a diagnostic system to distinguish ${\beta}$-Amyloid ($A{\beta}$) positive from $A{\beta}$ negative with objectiveness and accuracy was proposed using a machine learning approach, such as the Principal Component Analysis (PCA) and Support Vector Machine (SVM). $^{18}F$-Florbetaben (FBB) brain PET images were arranged in control and patients (total n = 176) with mild cognitive impairment and AD. An SVM was used to classify the slices of registered PET image using PET template, and a system was created to diagnose patients comprehensively from the output of the trained model. To compare the per-slice classification, the PCA-SVM model observing the whole brain (WB) region showed the highest performance (accuracy 92.38, specificity 92.87, sensitivity 92.87), followed by SVM with gray matter masking (GMM) (accuracy 92.22, specificity 92.13, sensitivity 92.28) for $A{\beta}$ positivity. To compare according to per-subject classification, the PCA-SVM with WB also showed the highest performance (accuracy 89.21, specificity 71.67, sensitivity 98.28), followed by PCA-SVM with GMM (accuracy 85.80, specificity 61.67, sensitivity 98.28) for $A{\beta}$ positivity. When comparing the area under curve (AUC), PCA-SVM with WB was the highest for per-slice classifiers (0.992), and the models except for SVM with WM were highest for the per-subject classifier (1.000). We can classify $^{18}F$-Florbetaben amyloid brain PET image for $A{\beta}$ positivity using PCA-SVM model, with no additional effects on GMM.

• Biomedical Science Letters
• /
• v.24 no.4
• /
• pp.418-425
• /
• 2018

Amyloid brain positron emission tomography (PET) images are visually and subjectively analyzed by the physician with a lot of time and effort to determine the ${\beta}$-Amyloid ($A{\beta}$) deposition. We designed a convolutional neural network (CNN) model that predicts the $A{\beta}$-positive and $A{\beta}$-negative status. We performed 18F-florbetaben (FBB) brain PET on controls and patients (n=176) with mild cognitive impairment and Alzheimer's Disease (AD). We classified brain PET images visually as per the on the brain amyloid plaque load score. We designed the visual geometry group (VGG16) model for the visual assessment of slice-based samples. To evaluate only the gray matter and not the white matter, gray matter masking (GMM) was applied to the slice-based standard samples. All the performance metrics were higher with GMM than without GMM (accuracy 92.39 vs. 89.60, sensitivity 87.93 vs. 85.76, and specificity 98.94 vs. 95.32). For the patient-based standard, all the performance metrics were almost the same (accuracy 89.78 vs. 89.21), lower (sensitivity 93.97 vs. 99.14), and higher (specificity 81.67 vs. 70.00). The area under curve with the VGG16 model that observed the gray matter region only was slightly higher than the model that observed the whole brain for both slice-based and patient-based decision processes. Amyloid brain PET images can be appropriately analyzed using the CNN model for predicting the $A{\beta}$-positive and $A{\beta}$-negative status.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.26 no.1
• /
• pp.33-37
• /
• 2022

Purpose ¹⁸F-Florbetaben (FBB) Readings are made by visually comparing the signal strengths of gray matter and white matter. We intend to evaluate the usefulness of image analysis by comparing quantified image analysis with readout. Materials and Methods Based on the reading results, 100 patients were divided into a negative scan and a positive scan, and 300 MBq of FBB was injected, and images were taken 90 minutes later for 20 minutes. The equipment was a Discovery 600 (GE Healthcare, MI, USA). Four regions of interest (lateral temporal lobes, frontal lobes, posterior cingulate & precuneus, and parietal lobes) were established based on the amyloid reading standard provided by the manufacturer. For image analysis, SUVratio (SUVr) was calculated by dividing each SUVmean by the cerebellum, and the average SUVr in the entire area was performed. Statistical analysis analyzed the cutoff derivation through ROC Curve, the difference between groups in Independent sample t-test, and the degree of agreement with the reading result through Kappa test. Results The average SUVr cutoff in the entire area was 1.23. Concordance with the read results using cutoff was 95/100 (95%) for negative and 92/100 (92%) for positive. As a result of the t-test, there was a statistically significant difference between the groups (P < 0.05), and the Kappa statistical result showed a high degree of agreement with 0.867 (P < 0.05). Conclusion The results of image analysis were statistically significant and showed a high degree of agreement with the reading results. In addition, FBB image analysis can be viewed by 3D mapping the area where amyloid is accumulated, location estimation is possible, and quantitative analysis results can be viewed in detail. If quantified FBB image analysis is used as an auxiliary indicator, it is thought to be helpful in reading.

• Dementia and Neurocognitive Disorders
• /
• v.22 no.2
• /
• pp.61-68
• /
• 2023

Background and Purpose: Analyzing brain amyloid positron emission tomography (PET) images to access the occurrence of β-amyloid (Aβ) deposition in Alzheimer's patients requires much time and effort from physicians, while the variation of each interpreter may differ. For these reasons, a machine learning model was developed using a convolutional neural network (CNN) as an objective decision to classify the Aβ positive and Aβ negative status from brain amyloid PET images. Methods: A total of 7,344 PET images of 144 subjects were used in this study. The 18F-florbetaben PET was administered to all participants, and the criteria for differentiating Aβ positive and Aβ negative state was based on brain amyloid plaque load score (BAPL) that depended on the visual assessment of PET images by the physicians. We applied the CNN algorithm trained in batches of 51 PET images per subject directory from 2 classes: Aβ positive and Aβ negative states, based on the BAPL scores. Results: The binary classification of the model average performance matrices was evaluated after 40 epochs of three trials based on test datasets. The model accuracy for classifying Aβ positivity and Aβ negativity was (95.00±0.02) in the test dataset. The sensitivity and specificity were (96.00±0.02) and (94.00±0.02), respectively, with an area under the curve of (87.00±0.03). Conclusions: Based on this study, the designed CNN model has the potential to be used clinically to screen amyloid PET images.

• Dementia and Neurocognitive Disorders
• /
• v.21 no.4
• /
• pp.126-137
• /
• 2022

Background and Purpose: Early detection of subjective cognitive decline (SCD) due to Alzheimer's disease (AD) is important for clinical research and effective prevention and management. This study examined if quantitative electroencephalography (qEEG) could be used for early detection of AD in SCD. Methods: Participants with SCD from 6 dementia clinics in Korea were enrolled. ¹⁸F-florbetaben brain amyloid positron emission tomography (PET) was conducted for all the participants. qEEG was performed to measure power spectrum and source cortical activity. Results: The present study included 95 participants aged over 65 years, including 26 amyloid PET (+) and 69 amyloid PET (-). In participants with amyloid PET (+), relative power at delta band was higher in frontal (p=0.025), parietal (p=0.005), and occipital (p=0.022) areas even after adjusting for age, sex, and education. Source activities of alpha 1 band were significantly decreased in the bilateral fusiform and inferior temporal areas, whereas those of delta band were increased in the bilateral cuneus, pericalcarine, lingual, lateral occipital, precuneus, posterior cingulate, and isthmus areas. There were increased connections between bilateral precuneus areas but decreased connections between left rostral middle frontal area and bilateral frontal poles at delta band in participants with amyloid PET (+) showed. At alpha 1 band, there were decreased connections between bilateral entorhinal areas after adjusting for covariates. Conclusions: SCD participants with amyloid PET (+) showed increased delta and decreased alpha 1 activity. qEEG is a potential means for predicting amyloid pathology in SCD. Further longitudinal studies are needed to confirm these findings.

• Sleep Medicine and Psychophysiology
• /
• v.28 no.2
• /
• pp.78-85
• /
• 2021

Objectives: When elderly patients show depressive symptoms, discrimination between depressive disorder and prodromal phase of Alzheimer's disease is important. We tested whether a quantitative electroencephalogram (qEEG) marker was associated with cerebral amyloid-β (Aβ) deposition in older adults with depression. Methods: Non-demented older individuals (≥ 55years) diagnosed with depression were included in the analyses (n = 63; 76.2% female; mean age ± standard deviation 73.7 ± 6.87 years). The participants were divided into Aβ+ (n = 32) and Aβ- (n = 31) groups based on amyloid PET assessment. EEG was recorded during the 7min eye-closed (EC) phase and 3min eye-open (EO) phase, and all EEG data were analyzed using Fourier transform spectral analysis. We tested interaction effects among Aβ positivity, condition (EC vs. EO), laterality (left, midline, or right), and polarity (frontal, central, or posterior) for EEG alpha band power. Then, the EC-to-EO alpha reactivity index (ARI) was examined as a neurophysiological marker for predicting Aβ+ in depressed older adults. Results: The mean power spectral density of the alpha band in EO phase showed a significant difference between the Aβ+ and Aβ- groups (F = 6.258, p = 0.015). A significant 3-way interaction was observed among Aβ positivity, condition, and laterality on alpha-band power after adjusting for age, sex, educational years, global cognitive function, medication use, and white matter hyperintensities on MRI (F = 3.720, p = 0.030). However, post-hoc analyses showed no significant difference in ARI according to Aβ status in any regions of interest. Conclusion: Among older adults with depression, increased power in EO phase alpha band was associated with Aβ positivity. However, EC-to-EO ARI was not confirmed as a predictor for Aβ+ in depressed older individuals. Future studies with larger samples are needed to confirm our results.