Dataset Information

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

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.

SUBMITTER: Kim S

PROVIDER: S-EPMC8192639 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:The amyloid cascade model of Alzheimer's disease posits the primacy of amyloid beta deposition preceding tau-mediated neurofibrillary tangle formation. The amyloid-tau-neurodegeneration biomarker-only diagnostic framework similarly requires the presence of amyloid beta for a diagnosis on the Alzheimer's continuum. However, medial temporal lobe tau pathology in the absence of amyloid beta is frequently observed at autopsy in cognitively normal individuals, a phenomenon that may reflect a consequence of aging and has been labelled 'primary age-related tauopathy'. Alternatively, others argue that this tauopathy reflects an early stage of the developmental continuum leading to Alzheimer's disease. We used positron emission tomography imaging to investigate amyloid beta and tau positivity and associations with cognition to better inform the conceptualization of biomarker changes in Alzheimer's pathogenesis. Five hundred twenty-three individuals from the Alzheimer's Disease Neuroimaging Initiative who had undergone flortaucipir positron emission tomography imaging were selected to derive positron emission tomography positivity thresholds using conditional inference decision tree regression. A subsample of 301 individuals without dementia (i.e. those with normal cognition or mild cognitive impairment) had also undergone florbetapir positron emission tomography imaging within 12 months and were categorized into one of the four groups based on cortical amyloid and Braak stage I/II tau positivity: A-/T-, A+/T-, A-/T+, or A+/T+. Tau positivity in the absence of amyloid beta positivity (i.e. A-/T+) comprised the largest group, representing 45% of the sample. In contrast, only 6% of the sample was identified as A+/T-, and the remainder of the sample fell into A-/T- (22%) or A+/T+ (27%) categories. A-/T- and A+/T- groups had the best cognitive performances across memory, language and executive function; the A-/T+ group showed small-to-moderate relative decreases in cognition; and the A+/T+ group had the worst cognitive performances. Furthermore, there were negative associations between Braak stage I/II tau values and all cognitive domains only in the A-/T+ and A+/T+ groups, with strongest associations for the A+/T+ group. Among our sample of older adults across the Alzheimer's pathological spectrum, 7-fold fewer individuals have positron emission tomography evidence of amyloid beta pathology in the absence of tau pathology than the converse, challenging prevailing models of amyloid beta's primacy in Alzheimer's pathogenesis. Given that cognitive performance in the A-/T+ group was poorer than in individuals without either pathology, our results suggest that medial temporal lobe tau without cortical amyloid beta may reflect an early stage on the Alzheimer's pathological continuum.

Project description:PurposeTo evaluate whether quantitative [18F]FDG-PET/CT assessment, including radiomic analysis of [18F]FDG-positive thyroid nodules, improved the preoperative differentiation of indeterminate thyroid nodules of non-Hürthle cell and Hürthle cell cytology.MethodsProspectively included patients with a Bethesda III or IV thyroid nodule underwent [18F]FDG-PET/CT imaging. Receiver operating characteristic (ROC) curve analysis was performed for standardised uptake values (SUV) and SUV-ratios, including assessment of SUV cut-offs at which a malignant/borderline neoplasm was reliably ruled out (≥ 95% sensitivity). [18F]FDG-positive scans were included in radiomic analysis. After segmentation at 50% of SUVpeak, 107 radiomic features were extracted from [18F]FDG-PET and low-dose CT images. Elastic net regression classifiers were trained in a 20-times repeated random split. Dimensionality reduction was incorporated into the splits. Predictive performance of radiomics was presented as mean area under the ROC curve (AUC) across the test sets.ResultsOf 123 included patients, 84 (68%) index nodules were visually [18F]FDG-positive. The malignant/borderline rate was 27% (33/123). SUV-metrices showed AUCs ranging from 0.705 (95% CI, 0.601-0.810) to 0.729 (0.633-0.824), 0.708 (0.580-0.835) to 0.757 (0.650-0.864), and 0.533 (0.320-0.747) to 0.700 (0.502-0.898) in all (n = 123), non-Hürthle (n = 94), and Hürthle cell (n = 29) nodules, respectively. At SUVmax, SUVpeak, SUVmax-ratio, and SUVpeak-ratio cut-offs of 2.1 g/mL, 1.6 g/mL, 1.2, and 0.9, respectively, sensitivity of [18F]FDG-PET/CT was 95.8% (95% CI, 78.9-99.9%) in non-Hürthle cell nodules. In Hürthle cell nodules, cut-offs of 5.2 g/mL, 4.7 g/mL, 3.4, and 2.8, respectively, resulted in 100% sensitivity (95% CI, 66.4-100%). Radiomic analysis of 84 (68%) [18F]FDG-positive nodules showed a mean test set AUC of 0.445 (95% CI, 0.290-0.600) for the PET model.ConclusionQuantitative [18F]FDG-PET/CT assessment ruled out malignancy in indeterminate thyroid nodules. Distinctive, higher SUV cut-offs should be applied in Hürthle cell nodules to optimize rule-out ability. Radiomic analysis did not contribute to the additional differentiation of [18F]FDG-positive nodules.Trial registration numberThis trial is registered with ClinicalTrials.gov: NCT02208544 (5 August 2014), https://clinicaltrials.gov/ct2/show/NCT02208544 .

Project description:Knowledge of the within-subject variability of 18F-FDG PET/MRI measurements is necessary for proper interpretation of quantitative PET or MRI metrics in the context of therapeutic efficacy assessments with integrated PET/MRI scanners. The goal of this study was to determine the test-retest repeatability of these metrics on PET/MRI, with comparison to similar metrics acquired by PET/CT. Methods: This prospective study enrolled subjects with pathology-proven pelvic malignancies. Baseline imaging consisted of PET/CT immediately followed by PET/MRI, using a single 370-MBq 18F-FDG dose. Repeat imaging was performed within 7 d using an identical imaging protocol, with no oncologic therapy between sessions. PET imaging on both scanners consisted of a list-mode acquisition at a single pelvic station. The MRI consisted of 2-point Dixon imaging for attenuation correction, standard sequences for anatomic correlation, and diffusion-weighted imaging. PET data were statically reconstructed using various frame durations and minimizing uptake time differences between sessions. SUV metrics were extracted for both PET/CT and PET/MRI in each imaging session. Apparent diffusion coefficient (ADC) metrics were extracted for both PET/MRI sessions. Results: The study cohort consisted of 14 subjects (13 female, 1 male) with various pelvic cancers (11 cervical, 2 rectal, 1 endometrial). For SUVmax, the within-subject coefficient of variation (wCV) appeared higher for PET/CT (8.5%-12.8%) than PET/MRI (6.6%-8.7%) across all PET reconstructions, though with no significant repeatability differences (all P values ≥ 0.08) between modalities. For lean body mass-adjusted SUVpeak, the wCVs appeared similar for PET/CT (9.9%-11.5%) and PET/MRI (9.2%-11.3%) across all PET reconstructions, again with no significant repeatability differences (all P values ≥ 0.14) between modalities. For PET/MRI, the wCV for ADCmedian of 3.5% appeared lower than the wCVs for SUVmax (6.6%-8.7%) and SULpeak (9.2%-11.3%), though without significant repeatability differences (all P values ≥ 0.23). Conclusion: For solid tumors of the pelvis, the repeatability of the evaluated SUV and ADC metrics on 18F-FDG PET/MRI is both acceptably high and similar to previously published values for 18F-FDG PET/CT and MRI, supporting the use of 18F-FDG PET/MRI for quantitative oncologic treatment response assessments.

Project description:Objectives: Alzheimer's disease (AD) is the most prevalent neurodegenerative disorder and the most common form of dementia in the older people. Some types of mild cognitive impairment (MCI) are the clinical precursors of AD, while other MCI forms tend to remain stable over time and do not progress to AD. To discriminate MCI patients at risk of AD from stable MCI, we propose a novel deep-learning radiomics (DLR) model based on 18F-fluorodeoxyglucose positron emission tomography (18F-FDG PET) images and combine DLR features with clinical parameters (DLR+C) to improve diagnostic performance. Methods: 18F-fluorodeoxyglucose positron emission tomography (PET) data from the Alzheimer's disease Neuroimaging Initiative database (ADNI) were collected, including 168 patients with MCI who converted to AD within 3 years and 187 patients with MCI without conversion within 3 years. These subjects were randomly partitioned into 90 % for the training/validation group and 10 % for the independent test group. The proposed DLR approach consists of three steps: base DL model pre-training, network features extraction, and integration of DLR+C, where a convolution network serves as a feature encoder, and a support vector machine (SVM) operated as the classifier. In comparative experiments, we compared our DLR+C method with four other methods: the standard uptake value ratio (SUVR) method, Radiomics-ROI method, Clinical method, and SUVR + Clinical method. To guarantee the robustness, 10-fold cross-validation was processed 100 times. Results: Under the DLR model, our proposed DLR+C was advantageous and yielded the best classification performance in the diagnosis of conversion with the accuracy, sensitivity, and specificity of 90.62 ± 1.16, 87.50 ± 0.00, and 93.39 ± 2.19%, respectively. In contrast, the respective accuracy of the other four methods reached 68.38 ± 1.27, 73.31 ± 6.93, 81.09 ± 1.97, and 85.35 ± 0.72 %. These results suggested the DLR approach could be used successfully in the prediction of conversion to AD, and that our proposed DLR-combined clinical information was effective. Conclusions: This study showed DLR+C could provide a novel and valuable method for the computer-assisted diagnosis of conversion to AD from MCI. This DLR+C method provided a quantitative biomarker which could predict conversion to AD in MCI patients.

Dataset Information

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

Background

Methods

Results

Conclusion

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets

Dataset Information

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

Background

Methods

Results

Conclusion

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets

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