A Practical Alzheimer Disease Classifier via Brain Imaging-Based Deep Learning on 85,721 Samples

Abstract

Beyond detecting brain lesions or tumors, comparatively little success has been attained in identifying brain disorders such as Alzheimers disease (AD), based on magnetic resonance imaging (MRI). Many machine learning algorithms to detect AD have been trained using limited training data, meaning they often generalize poorly when applied to scans from previously unseen populations. Therefore, we built a practical brain MRI-based AD diagnostic classifier using deep learning/transfer learning on a dataset of unprecedented size and diversity. A retrospective MRI dataset pooled from more than 217 sites/scanners constituted one of the largest brain MRI samples to date (85,721 scans from 50,876 participants) between January 2017 and August 2021. Next, a state-of-the-art deep convolutional neural network, Inception-ResNet-V2, was built as a sex classifier with high generalization capability. The sex classifier achieved 94.9% accuracy and served as a base model in transfer learning for the objective diagnosis of AD. After transfer learning, the model fine-tuned for AD classification achieved 90.9% accuracy in leave-sites-out cross-validation on the Alzheimers Disease Neuroimaging Initiative (ADNI, 6,857 samples) dataset and 94.5%/93.6%/91.1% accuracy for direct tests on three unseen independent datasets (AIBL, 669 samples / MIRIAD, 644 samples / OASIS, 1,123 samples). When this AD classifier was tested on brain images from unseen mild cognitive impairment (MCI) patients, MCI patients who converted to AD were 3 times more likely to be predicted as AD than MCI patients who did not convert (65.2% vs 20.6%). Predicted scores from the AD classifier showed significant correlations with illness severity. In sum, the proposed AD classifier offers a medical-grade marker that has potential to be integrated into AD diagnostic practice.