Generalizable deep learning model for early Alzheimer's disease detection from structural MRIs

Abstract

Early diagnosis of Alzheimer's disease plays a pivotal role in patient care and clinical trials. In this study, we have developed a new approach based on 3D deep convolutional neural networks to accurately differentiate mild Alzheimer's disease dementia from mild cognitive impairment and cognitively normal individuals using structural MRIs. For comparison, we have built a reference model based on the volumes and thickness of previously reported brain regions that are known to be implicated in disease progression. We validate both models on an internal held-out cohort from The Alzheimer's Disease Neuroimaging Initiative (ADNI) and on an external independent cohort from The National Alzheimer's Coordinating Center (NACC). The deep-learning model is accurate, achieved an area-under-the-curve (AUC) of 85.12 when distinguishing between cognitive normal subjects and subjects with either MCI or mild Alzheimer's dementia. In the more challenging task of detecting MCI, it achieves an AUC of 62.45. It is also significantly faster than the volume/thickness model in which the volumes and thickness need to be extracted beforehand. The model can also be used to forecast progression: subjects with mild cognitive impairment misclassified as having mild Alzheimer's disease dementia by the model were faster to progress to dementia over time. An analysis of the features learned by the proposed model shows that it relies on a wide range of regions associated with Alzheimer's disease. These findings suggest that deep neural networks can automatically learn to identify imaging biomarkers that are predictive of Alzheimer's disease, and leverage them to achieve accurate early detection of the disease.

Figure 1

Overview of the deep learning framework and performance for Alzheimer’s automatic diagnosis. (a) Deep learning framework used for automatic diagnosis. (b) Receiver operating characteristic (ROC) curves for classification of cognitively normal (CN), mild cognitive impairment (MCI) and Alzheimer’s disease (AD), computed on the ADNI held-out test set. (c) ROC curves for classification of cognitively normal (CN), mild cognitive impairment (MCI) and Alzheimer’s disease (AD) on the NACC test set. (d) Visualization using t-SNE projections of the features computed by the proposed deep-learning model. Each point represents a scan. Green, blue, red colors indicate predicted cognitive groups. CN and AD scans are clearly clustered. (e) Visualization using t-SNE projections of the 138 volumes and thickness in the ROI-volume/thickness model. Compared to (d) the separation between CN and AD scans is less marked. The t-SNE approach is described in details in the methods section.

Figure 2

Progression analysis for MCI subjects. (a) Progression analysis based on the deep learning model. (b) Progression analysis based on the ROI-volume/thickness model. The subjects in the ADNI test set are divided into two groups based on the classification results of the deep learning model from their first scan diagnosed as MCI: group A if the prediction is AD, and group B if it is not. The graph shows the fraction of subjects that progressed to AD at different months following the first scan diagnosed as MCI for both groups. Subjects in group A progress to AD at a significantly faster rate, suggesting that the features extracted by the deep-learning model may be predictive of the transition.

Figure 3

Performance across different subgroups. Performance of the deep learning model (in blue) and of the ROI-volume/thickness model (in red) for different subpopulations of individuals, separated according to sex, education, and ApoE4 status.

Figure 4

Datasize Impact. Performance of the baseline ROI-volume/thickness model (left) and the proposed deep learning model (right) when trained on datasets with different sizes (obtained by randomly subsampling the training set). The performance of the ROI-volume/thickness model improves when the training data increases from 50 to 70%, but remains essentially stagnant after further increases. In contrast, the performance of the deep learning model consistently improves as the size of the training set increases. Given that the deep learning model is trained on a very small dataset compared to standard computer-vision tasks for natural images, this suggests that building larger training sets is a promising avenue to further improving performance.

Figure 5

(a–c) Visualization of the aggregated importance of each voxel (in yellow) in the deep learning model when classifying subjects into CN/MCI/AD. For each subject, the importance map was computed using the gradient of the deep-learning model with respect to its input (Details in “Methods” section). The computed gradients are visualized over the MNI T1-weighted template. (d–f) Top 30 regions of interest, sorted by their normalized gradient count, which quantifies their importance (see “Methods” section), for each of the classes.