Medicine and Health Sciences Commons^™

An Explainable Deep Learning Prediction Model For Severity Of Alzheimer's Disease From Brain Images, Godwin O. Ekuma

MSU Graduate Theses

Deep Convolutional Neural Networks (CNNs) have become the go-to method for medical imaging classification on various imaging modalities for binary and multiclass problems. Deep CNNs extract spatial features from image data hierarchically, with deeper layers learning more relevant features for the classification application. The effectiveness of deep learning models are hampered by limited data sets, skewed class distributions, and the undesirable "black box" of neural networks, which decreases their understandability and usability in precision medicine applications. This thesis addresses the challenge of building an explainable deep learning model for a clinical application: predicting the severity of Alzheimer's disease (AD). AD …

Leukocyte Surface Biomarkers Implicate Deficits Of Innate Immunity In Sporadic Alzheimer's Disease, Xin Huang, Yihan Li, Christopher Fowler, James D. Doecke, Yen Ying Lim, Candace Drysdale, Vicky Zhang, Keunha Park, Brett Trounson, Kelly Pertile, Rebecca Rumble, John W. Pickering, Robert A. Rissman, Floyd Sarsoza, Sara Abdel-Latif, Yong Lin, Vincent Doré, Victor Villemagne, Christopher C. Rowe, Jurgen Fripp, Ralph Martins, James S. Wiley, Paul Maruff, Jacobo E. Mintzer, Colin L. Masters, Ben J. Gu

Research outputs 2022 to 2026

Introduction:

Blood-based diagnostics and prognostics in sporadic Alzheimer's disease (AD) are important for identifying at-risk individuals for therapeutic interventions.

Methods:

In three stages, a total of 34 leukocyte antigens were examined by flow cytometry immunophenotyping. Data were analyzed by logistic regression and receiver operating characteristic (ROC) analyses.

Results:

We identified leukocyte markers differentially expressed in the patients with AD. Pathway analysis revealed a complex network involving upregulation of complement inhibition and downregulation of cargo receptor activity and Aβ clearance. A proposed panel including four leukocyte markers – CD11c, CD59, CD91, and CD163 – predicts patients’ PET Aβ status with an …