Dataset Information

Deep learning prediction of mild cognitive impairment conversion to Alzheimer's disease at 3 years after diagnosis using longitudinal and whole-brain 3D MRI.

ABSTRACT:

Background

While there is no cure for Alzheimer's disease (AD), early diagnosis and accurate prognosis of AD may enable or encourage lifestyle changes, neurocognitive enrichment, and interventions to slow the rate of cognitive decline. The goal of our study was to develop and evaluate a novel deep learning algorithm to predict mild cognitive impairment (MCI) to AD conversion at three years after diagnosis using longitudinal and whole-brain 3D MRI.

Methods

This retrospective study consisted of 320 normal cognition (NC), 554 MCI, and 237 AD patients. Longitudinal data include T1-weighted 3D MRI obtained at initial presentation with diagnosis of MCI and at 12-month follow up. Whole-brain 3D MRI volumes were used without a priori segmentation of regional structural volumes or cortical thicknesses. MRIs of the AD and NC cohort were used to train a deep learning classification model to obtain weights to be applied via transfer learning for prediction of MCI patient conversion to AD at three years post-diagnosis. Two (zero-shot and fine tuning) transfer learning methods were evaluated. Three different convolutional neural network (CNN) architectures (sequential, residual bottleneck, and wide residual) were compared. Data were split into 75% and 25% for training and testing, respectively, with 4-fold cross validation. Prediction accuracy was evaluated using balanced accuracy. Heatmaps were generated.

Results

The sequential convolutional approach yielded slightly better performance than the residual-based architecture, the zero-shot transfer learning approach yielded better performance than fine tuning, and CNN using longitudinal data performed better than CNN using a single timepoint MRI in predicting MCI conversion to AD. The best CNN model for predicting MCI conversion to AD at three years after diagnosis yielded a balanced accuracy of 0.793. Heatmaps of the prediction model showed regions most relevant to the network including the lateral ventricles, periventricular white matter and cortical gray matter.

Conclusions

This is the first convolutional neural network model using longitudinal and whole-brain 3D MRIs without extracting regional brain volumes or cortical thicknesses to predict future MCI to AD conversion at 3 years after diagnosis. This approach could lead to early prediction of patients who are likely to progress to AD and thus may lead to better management of the disease.

SUBMITTER: Ocasio E

PROVIDER: S-EPMC8176545 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Multiple biomarkers can capture different facets of Alzheimer's disease. However, statistical models of biomarkers to predict outcomes in Alzheimer's rarely model nonlinear interactions between these measures. Here, we used Gaussian Processes to address this, modelling nonlinear interactions to predict progression from mild cognitive impairment (MCI) to Alzheimer's over 3 years, using Alzheimer's Disease Neuroimaging Initiative (ADNI) data. Measures included: demographics, APOE4 genotype, CSF (amyloid-β42, total tau, phosphorylated tau), [18F ]florbetapir, hippocampal volume and brain-age. We examined: (a) the independent value of each biomarker; and (b) whether modelling nonlinear interactions between biomarkers improved predictions. Each measured added complementary information when predicting conversion to Alzheimer's. A linear model classifying stable from progressive MCI explained over half the variance (R2 = 0.51, p < .001); the strongest independently contributing biomarker was hippocampal volume (R2 = 0.13). When comparing sensitivity of different models to progressive MCI (independent biomarker models, additive models, nonlinear interaction models), we observed a significant improvement (p < .001) for various two-way interaction models. The best performing model included an interaction between amyloid-β-PET and P-tau, while accounting for hippocampal volume (sensitivity = 0.77, AUC = 0.826). Closely related biomarkers contributed uniquely to predict conversion to Alzheimer's. Nonlinear biomarker interactions were also implicated, and results showed that although for some patients adding additional biomarkers may add little value (i.e., when hippocampal volume is high), for others (i.e., with low hippocampal volume) further invasive and expensive examination may be warranted. Our framework enables visualisation of these interactions, in individual patient biomarker 'space', providing information for personalised or stratified healthcare or clinical trial design.

Project description:BackgroundAlzheimer's disease (AD) is a widespread neurodegenerative disease that mostly affects the elderly population. Given its prevalence, a precise and efficient stratification system based on AD symptomology that uses functional magnetic resonance imaging (MRI) has great potential in the clinical diagnosis and prognosis estimation of AD patients. It was evident that deep learning methods have performed extremely well in the field of automated stratification of AD based on MRI because of their high predicting accuracy and reliability.MethodsWe proposed a deep convolutional neural network (CNN) and iterated random forest (RF) architecture for MRI image stratification by both anatomical location and image modality using the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. We employed 3 cross-sectional data sets from the ADNI to conduct our binary-stratification [AD and normal controls (NCs), or AD and mild cognitive impairment (MCI)], and multi-stratification (AD, MCI, and NCs) process using MRI. And the accuracy, recall, specificity, area under the curve of receiver operating characteristic curve (AUC), F1 and Matthew's correlation coefficient (MCC) scores to assess accuracy of auxiliary clinical diagnoses.ResultsCompared to other combinations of algorithms, our model obtained remarkable overall stratification accuracies in all different classification sets. In terms of AD vs. MCI, the mean training AUC of the 3 runs were 85.1% in 95% confidence intervals (CIs). In terms of AD vs. NC, the mean training AUC of the 3 runs was 90.6% in 95% CIs. In terms of the 3 stratifications of AD, MCI, and NC, relative precision, recall, and specificity for each category in the training test (TS) were all near 89%, while the F1 and MCC scores of both sets were 59.9% and 59.5%, respectively.ConclusionsUsing a deep CNN and iterated RF architecture, we showed that brain image stratification is a promising means for evaluating AD, and examining the underlying etiology of the disease, by applying computer and medical images to achieve the early auxiliary diagnosis of AD. However, we still have a long way to go from the discovery of image markers to clinical application.