AUTHOR=Liu Shui , Jie Chen , Zheng Weimin , Cui Jingjing , Wang Zhiqun 

TITLE=Investigation of Underlying Association Between Whole Brain Regions and Alzheimer’s Disease: A Research Based on an Artificial Intelligence Model

JOURNAL=Frontiers in Aging Neuroscience

VOLUME=Volume 14 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/aging-neuroscience/articles/10.3389/fnagi.2022.872530

DOI=10.3389/fnagi.2022.872530

ISSN=1663-4365

ABSTRACT=Alzheimer’s disease (AD) is the most common form of dementia, causing progressive cognitive decline. Radiomic features obtained from structural magnetic resonance imaging (sMRI) have shown a great potential in predicting this disease. However, radiomic features based on the whole brain segmented regions have not been explored yet. In our study, we collected structural MRI data including 80 AD patients and 80 healthy control (HC). For each patient, the T1WI images were segmented into 106 subregions, and radiomics features were extracted from each subregion. Then we analyzed the radiomics features of specific brain subregions that were most related to AD. Based on the selective radiomics features from specific brain subregions, we built an integrated model using best machine learning algorithms and the diagnostic accuracy was evaluated. As the results, the subregions most relevant to AD included hippocampus, inferior parietal lobe, precuneus, and lateral occipital gyrus. These subregions exhibited the several important radiomics features including shape, gray level size zone matrix (GLSZM), gray level dependence matrix (GLDM), etc. Based on the comparison among different algorithms, we constructed the best model using logistic regression algorithm, which reached an accuracy of 0.962. Conclusively, we constructed an excellent model based on radiomic features from several specific AD-related subregions, which could give a potential biomarker for predicting AD.