scholarly journals Deep learning-based amyloid PET positivity classification model in the Alzheimer’s disease continuum by using 2-[18F]FDG PET

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Suhong Kim ◽  
Peter Lee ◽  
Kyeong Taek Oh ◽  
Min Soo Byun ◽  
Dahyun Yi ◽  
...  
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Deep Learning ◽  
Fdg Pet ◽  
External Validation ◽  
Classification Model ◽  
Validation Dataset ◽  
Position Emission Tomography ◽  
Amyloid Pet ◽  
Deep Model

Abstract Background Considering the limited accessibility of amyloid position emission tomography (PET) in patients with dementia, we proposed a deep learning (DL)-based amyloid PET positivity classification model from PET images with 2-deoxy-2-[fluorine-18]fluoro-D-glucose (2-[18F]FDG). Methods We used 2-[18F]FDG PET datasets from the Alzheimer's Disease Neuroimaging Initiative and Korean Brain Aging Study for the Early diagnosis and prediction of Alzheimer’s disease for model development. Moreover, we used an independent dataset from another hospital. A 2.5-D deep learning architecture was constructed using 291 submodules and three axes images as the input. We conducted the voxel-wise analysis to assess the regions with substantial differences in glucose metabolism between the amyloid PET-positive and PET-negative participants. This facilitated an understanding of the deep model classification. In addition, we compared these regions with the classification probability from the submodules. Results There were 686 out of 1433 (47.9%) and 50 out of 100 (50%) amyloid PET-positive participants in the training and internal validation datasets and the external validation datasets, respectively. With 50 times iterations of model training and validation, the model achieved an AUC of 0.811 (95% confidence interval (CI) of 0.803–0.819) and 0.798 (95% CI, 0.789–0.807) on the internal and external validation datasets, respectively. The area under the curve (AUC) was 0.860 when tested with the model with the highest value (0.864) on the external validation dataset. Moreover, it had 75.0% accuracy, 76.0% sensitivity, 74.0% specificity, and 75.0% F1-score. We found an overlap between the regions within the default mode network, thus generating high classification values. Conclusion The proposed model based on the 2-[18F]FDG PET imaging data and a DL framework might successfully classify amyloid PET positivity in clinical practice, without performing amyloid PET, which have limited accessibility.

scholarly journals Deep Learning With 18F-Fluorodeoxyglucose-PET Gives Valid Diagnoses for the Uncertain Cases in Memory Impairment of Alzheimer’s Disease

2021 ◽  
Vol 13 ◽  
Author(s):  
Wei Zhang ◽  
Tianhao Zhang ◽  
Tingting Pan ◽  
Shilun Zhao ◽  
Binbin Nie ◽  
...  
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Deep Learning ◽  
Mental State ◽  
Fdg Pet ◽  
Neuropsychological Tests ◽  
Memory Impairment ◽  
Memory Function ◽  
Disease Assessment ◽  
18F Fluorodeoxyglucose

Objectives: Neuropsychological tests are an important basis for the memory impairment diagnosis in Alzheimer’s disease (AD). However, multiple memory tests might be conflicting within-subjects and lead to uncertain diagnoses in some cases. This study proposed a framework to diagnose the uncertain cases of memory impairment.Methods: We collected 2,386 samples including AD, mild cognitive impairment (MCI), and cognitive normal (CN) using 18F-fluorodeoxyglucose positron emission tomography (FDG-PET) and three different neuropsychological tests (Mini-Mental State Examination, Alzheimer’s Disease Assessment Scale-Cognitive Subscale, and Clinical Dementia Rating) from the Alzheimer’s Disease Neuroimaging Initiative (ADNI). A deep learning (DL) framework using FDG-PET was proposed to diagnose uncertain memory impairment cases that were conflicting between tests. Subsequent ANOVA, chi-squared, and t-test were used to explain the potential causes of uncertain cases.Results: For certain cases in the testing set, the proposed DL framework outperformed other methods with 95.65% accuracy. For the uncertain cases, its positive diagnoses had a significant (p < 0.001) worse decline in memory function than negative diagnoses in a longitudinal study of 40 months on average. In the memory-impaired group, uncertain cases were mainly explained by an AD metabolism pattern but mild in extent (p < 0.05). In the healthy group, uncertain cases were mainly explained by a non-energetic mental state (p < 0.001) measured using a global deterioration scale (GDS), with a significant depression-related metabolism pattern detected (p < 0.05).Conclusion: A DL framework for diagnosing uncertain cases of memory impairment is proposed. Proved by longitudinal tracing of its diagnoses, it showed clinical validity and had application potential. Its valid diagnoses also provided evidence and explanation of uncertain cases based on the neurodegeneration and depression mental state.

scholarly journals Correction to: Amyloid PET, FDG-PET or MRI? - the power of different imaging biomarkers to detect progression of early Alzheimer’s disease

BMC Neurology ◽  
2020 ◽  
Vol 20 (1) ◽  
Author(s):  
Marion Ortner ◽  
René Drost ◽  
Dennis Hedderich ◽  
Oliver Goldhardt ◽  
Felix Müller-Sarnowski ◽  
...  
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Fdg Pet ◽  
Imaging Biomarkers ◽  
Amyloid Pet ◽  
Early Alzheimer’S Disease

A Japanese Multicenter Study on PET and Other Biomarkers for Subjects with Potential Preclinical and Prodromal Alzheimer’s Disease

2021 ◽  
pp. 1-8
Author(s):  
M. Senda ◽  
K. Ishii ◽  
K. Ito ◽  
T. Ikeuchi ◽  
H. Matsuda ◽  
...  
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Cognitive Impairment ◽  
Multicenter Study ◽  
Fdg Pet ◽  
Structural Mri ◽  
Amyloid Pet ◽  
Positron Emission ◽  
Prodromal Alzheimer’S Disease ◽  
T Tau

BACKGROUND: PET (positron emission tomography) and CSF (cerebrospinal fluid) provide the “ATN” (Amyloid, Tau, Neurodegeneration) classification and play an essential role in early and differential diagnosis of Alzheimer’s disease (AD). OBJECTIVE: Biomarkers were evaluated in a Japanese multicenter study on cognitively unimpaired subjects (CU) and early (E) and late (L) mild cognitive impairment (MCI) patients. MEASUREMENTS: A total of 38 (26 CU, 7 EMCI, 5 LMCI) subjects with the age of 65-84 were enrolled. Amyloid-PET and FDG-PET as well as structural MRI were acquired on all of them, with an additional tau-PET with 18F-flortaucipir on 15 and CSF measurement of Aβ1-42, P-tau, and T-tau on 18 subjects. Positivity of amyloid and tau was determined based on the positive result of either PET or CSF. RESULTS: The amyloid positivity was 13/38, with discordance between PET and CSF in 6/18. Cortical tau deposition quantified with PET was significantly correlated with CSF P-tau, in spite of discordance in the binary positivity between visual PET interpretation and CSF P-tau in 5/8 (PET-/CSF+). Tau was positive in 7/9 amyloid positive and 8/16 amyloid negative subjects who underwent tau measurement, respectively. Overall, a large number of subjects presented quantitative measures and/or visual read that are close to the borderline of binary positivity, which caused, at least partly, the discordance between PET and CSF in amyloid and/or tau. Nine subjects presented either tau or FDG-PET positive while amyloid was negative, suggesting the possibility of non-AD disorders. CONCLUSION: Positivity rate of amyloid and tau, together with their relationship, was consistent with previous reports. Multicenter study on subjects with very mild or no cognitive impairment may need refining the positivity criteria and cutoff level as well as strict quality control of the measurements.

scholarly journals Deep learning detection of informative features in tau PET for Alzheimer’s disease classification

2020 ◽  
Vol 21 (S21) ◽  
Author(s):  
Taeho Jo ◽  
◽  
Kwangsik Nho ◽  
Shannon L. Risacher ◽  
Andrew J. Saykin
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Clinical Trials ◽  
Deep Learning ◽  
Early Detection ◽  
Medial Temporal Lobe ◽  
Memory Loss ◽  
Disease Classification ◽  
Classification Model ◽  
Tau Pet

Abstract Background Alzheimer’s disease (AD) is the most common type of dementia, typically characterized by memory loss followed by progressive cognitive decline and functional impairment. Many clinical trials of potential therapies for AD have failed, and there is currently no approved disease-modifying treatment. Biomarkers for early detection and mechanistic understanding of disease course are critical for drug development and clinical trials. Amyloid has been the focus of most biomarker research. Here, we developed a deep learning-based framework to identify informative features for AD classification using tau positron emission tomography (PET) scans. Results The 3D convolutional neural network (CNN)-based classification model of AD from cognitively normal (CN) yielded an average accuracy of 90.8% based on five-fold cross-validation. The LRP model identified the brain regions in tau PET images that contributed most to the AD classification from CN. The top identified regions included the hippocampus, parahippocampus, thalamus, and fusiform. The layer-wise relevance propagation (LRP) results were consistent with those from the voxel-wise analysis in SPM12, showing significant focal AD associated regional tau deposition in the bilateral temporal lobes including the entorhinal cortex. The AD probability scores calculated by the classifier were correlated with brain tau deposition in the medial temporal lobe in MCI participants (r = 0.43 for early MCI and r = 0.49 for late MCI). Conclusion A deep learning framework combining 3D CNN and LRP algorithms can be used with tau PET images to identify informative features for AD classification and may have application for early detection during prodromal stages of AD.

scholarly journals The Clinical Use of Alzheimer’s Biomarkers in Patients With Mild Cognitive Impairment: A European Alzheimer’s Disease Consortium Survey

2021 ◽  
Author(s):  
Camilla Caprioglio ◽  
Valentina Garibotto ◽  
Frank Jessen ◽  
Lutz Frölich ◽  
Gilles Allali ◽  
...  
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Cognitive Impairment ◽  
Mild Cognitive Impairment ◽  
Fdg Pet ◽  
Diagnostic Process ◽  
Amyloid Pet ◽  
Clinical Use ◽  
Tau Pet ◽  
T Tau

Abstract Background. This study aims to investigate the clinical use of the main Alzheimer’s disease (AD) biomarkers in patients with mild cognitive impairment (MCI) by examining the beliefs and preferences of clinicians and biomarker experts of the European Alzheimer’s Disease Consortium (EADC).Methods. Out of 306 contacted EADC professionals, 150 (101 clinicians, 43 biomarker experts, and 6 falling into other categories) filled in an online survey from May to September 2020. The investigated biomarkers were: medial temporal lobe atrophy score (MTA) on structural MRI, typical AD (i.e. temporoparietal and posterior cingulate) hypometabolism on FDG-PET, CSF (Aβ42, p-tau, t-tau), amyloid-PET and tau-PET.Results. Despite the abnormal accumulation of amyloid rather than tau was deemed by the majority of responders as the initial cause of AD, responders did not show a clear preference for amyloid-PET. The most widely used biomarker is MTA (77% of responders reported to use it at least frequently), followed by Aβ42, p-tau, t-tau levels in CSF (45%), typical AD hypometabolism on FDG-PET (32%), amyloid-PET (8%), and tau-PET (2%). Imaging and CSF biomarkers were found to be widely used to support the etiological diagnostic process in MCI, while APOE genotyping was performed only in a minority of patients. CSF is considered the most valuable biomarker in terms of additional diagnostic value, followed by amyloid-PET, tau-PET, and typical AD hypometabolism on FDG-PET. The combination of amyloidosis and neuronal injury biomarkers is associated with the highest diagnostic confidence in an etiological diagnosis of AD in MCI, while MTA alone was perceived as the less reliable biomarker.Conclusions. Biomarkers are widely used across Europe for the diagnosis of MCI. Overall, we observed that CSF is currently considered as the most useful biomarker, followed by amyloid-PET. Moreover, the use of molecular imaging (i.e. amyloid-PET and tau-PET) in the diagnostic work-up of MCI patients is increasing over time.

scholarly journals Deep learning detection of informative features in tau PET for Alzheimer’s disease classification

2020 ◽  
Author(s):  
Taeho Jo ◽  
Kwangsik Nho ◽  
Shannon L. Risacher ◽  
Andrew J. Saykin ◽  
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Clinical Trials ◽  
Deep Learning ◽  
Early Detection ◽  
Group Analysis ◽  
Statistical Parametric Mapping ◽  
Classification Model ◽  
Tau Pet ◽  
3D Cnn

AbstractBackgroundAlzheimer’s disease (AD) is the most common type of dementia, typically characterized by memory loss followed by progressive cognitive decline and functional impairment. Many clinical trials of potential therapies for AD have failed, and there is currently no approved disease-modifying treatment. Biomarkers for early detection and mechanistic understanding of disease course are critical for drug development and clinical trials. Amyloid has been the focus of most biomarker research. Here, we developed a deep learning-based framework to identify informative features for AD classification using tau positron emission tomography (PET) scans.MethodsWe analysed [18F]flortaucipir PET image data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) cohort. We first developed an image classifier to distinguish AD from cognitively normal (CN) older adults by training a 3D convolutional neural network (CNN)-based deep learning model on tau PET images (N=132; 66 CN and 66 AD), then applied the classifier to images from individuals with mild cognitive impairment (MCI; N=168). In addition, we applied a layer-wise relevance propagation (LRP)-based model to identify informative features and to visualize classification results. We compared these results with those from whole brain voxel-wise between-group analysis using conventional Statistical Parametric Mapping (SPM12).ResultsThe 3D CNN-based classification model of AD from CN yielded an average accuracy of 90.8% based on five-fold cross-validation. The LRP model identified the brain regions in tau PET images that contributed most to the AD classification from CN. The top identified regions included the hippocampus, parahippocampus, thalamus, and fusiform. The LRP results were consistent with those from the voxel-wise analysis in SPM12, showing significant focal AD associated regional tau deposition in the bilateral temporal lobes including the entorhinal cortex. The AD probability scores calculated by the classifier were correlated with brain tau deposition in the medial temporal lobe in MCI participants (r=0.43 for early MCI and r=0.49 for late MCI).ConclusionA deep learning framework combining 3D CNN and LRP algorithms can be used with tau PET images to identify informative features for AD classification and may have application for early detection during prodromal stages of AD.

Sign in / Sign up

Export Citation Format

Share Document