Early Diagnosing and Transformation Prediction of Alzheimer’s Disease Using Multi-Scaled Self-Attention Network on Structural MRI Images with Occlusion Sensitivity Analysis

Article type: Research Article

Authors: Fan, Xinxin^{a; b; 1} | Li, Haining^{c; 1} | Liu, Lin^b | Zhang, Kai^a | Zhang, Zhewei^a | Chen, Yi^a | Wang, Zhen^d | He, Xiaoli^e | Xu, Jinping^{a; *} | Hu, Qingmao^{a; *} | Alzheimer’s Disease Neuroimaging Initiative²

Affiliations: [a] Institute of Biomedical and Health Engineering, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China | [b] University of Chinese Academy of Sciences, Beijing, China | [c] Department of Neurology, General Hospital of Ningxia Medical University, Yinchuan, China | [d] Zhuhai Institute of Advanced Technology, Zhuhai, China | [e] Department of Psychology, Ningxia University, Yinchuan, China

Correspondence: [*] Correspondence to: Dr. Jinping Xu, Institute of Biomedical and Health Engineering, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, China. E-mail: [email protected] and Dr. Qingmao Hu, Institute of Biomedical and Health Engineering, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, China. E-mail: [email protected].

Note: [1] These authors contributed equally in this work.

Note: [2] Data used in preparation of this article were obtained from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database (https://adni.loni.usc.edu). As such, the investigatorswithin the ADNI contributed to the design and implementation of ADNI and/or provided databut did not participate in analysis or writing of this report. A complete listing of ADNIinvestigators can be found at: http://adni.loni.usc.edu/wp-content/uploads/how_to_apply/ADNI_Acknowledgement_List.pdf.

Abstract: Background: Structural magnetic resonance imaging (sMRI) is vital for early Alzheimer’s disease (AD) diagnosis, though confirming specific biomarkers remains challenging. Our proposed Multi-Scale Self-Attention Network (MUSAN) enhances classification of cognitively normal (CN) and AD individuals, distinguishing stable (sMCI) from progressive mild cognitive impairment (pMCI). Objective: This study leverages AD structural atrophy properties to achieve precise AD classification, combining different scales of brain region features. The ultimate goal is an interpretable algorithm for this method. Methods: The MUSAN takes whole-brain sMRI as input, enabling automatic extraction of brain region features and modeling of correlations between different scales of brain regions, and achieves personalized disease interpretation of brain regions. Furthermore, we also employed an occlusion sensitivity algorithm to localize and visualize brain regions sensitive to disease. Results:Our method is applied to ADNI-1, ADNI-2, and ADNI-3, and achieves high performance on the classification of CN from AD with accuracy (0.93), specificity (0.82), sensitivity (0.96), and area under curve (AUC) (0.95), as well as notable performance on the distinguish of sMCI from pMCI with accuracy (0.85), specificity (0.84), sensitivity (0.74), and AUC (0.86). Our sensitivity masking algorithm identified key regions in distinguishing CN from AD: hippocampus, amygdala, and vermis. Moreover, cingulum, pallidum, and inferior frontal gyrus are crucial for sMCI and pMCI discrimination. These discoveries align with existing literature, confirming the dependability of our model in AD research. Conclusion:Our method provides an effective AD diagnostic and conversion prediction method. The occlusion sensitivity algorithm enhances deep learning interpretability, bolstering AD research reliability.

Keywords: Alzheimer’s disease, deep learning, explainable deep learning, multilevel feature learning, structural MRI

DOI: 10.3233/JAD-230705

Journal: Journal of Alzheimer's Disease, vol. 97, no. 2, pp. 909-926, 2024