10.6084/M9.FIGSHARE.C.6248197.V1
Bin Lu
Bin
Lu
University of Chinese Academy of Sciences
Institute of Psychology
Hui-Xian Li
Hui-Xian
Li
University of Chinese Academy of Sciences
Institute of Psychology
Zhi-Kai Chang
Zhi-Kai
Chang
University of Chinese Academy of Sciences
Institute of Psychology
Le Li
Le
Li
Beijing Language and Culture University
Ning-Xuan Chen
Ning-Xuan
Chen
University of Chinese Academy of Sciences
Institute of Psychology
Zhi-Chen Zhu
Zhi-Chen
Zhu
University of Chinese Academy of Sciences
Institute of Psychology
Hui-Xia Zhou
Hui-Xia
Zhou
University of Chinese Academy of Sciences
Institute of Psychology
Xue-Ying Li
Xue-Ying
Li
University of Chinese Academy of Sciences
Institute of Psychology
Sino-Danish Centre for Education and Research
Yu-Wei Wang
Yu-Wei
Wang
University of Chinese Academy of Sciences
Institute of Psychology
Shi-Xian Cui
Shi-Xian
Cui
University of Chinese Academy of Sciences
Institute of Psychology
Sino-Danish Centre for Education and Research
Zhao-Yu Deng
Zhao-Yu
Deng
University of Chinese Academy of Sciences
Institute of Psychology
Zhen Fan
Zhen
Fan
Fudan University
Hong Yang
Hong
Yang
Zhejiang University
Xiao Chen
Xiao
Chen
University of Chinese Academy of Sciences
Institute of Psychology
Paul M. Thompson
Paul M.
Thompson
University of Southern California
Francisco Xavier Castellanos
Francisco Xavier
Castellanos
New York University
Nathan Kline Institute for Psychiatric Research
Chao-Gan Yan
Chao-Gan
Yan
University of Chinese Academy of Sciences
Institute of Psychology
Chinese Academy of Sciences
A practical Alzheimer’s 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 Alzheimer’s 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 scanners/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 Alzheimer’s 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.
Artificial Intelligence and Image Processing
figshare
2022
2022-10-14
2022-10-14
Collection
10.6084/m9.figshare.c.6248197
CC BY 4.0