Back to Search Start Over

The Feasibility of Differentiating Lewy Body Dementia and Alzheimer’s Disease by Deep Learning Using ECD SPECT Images

Authors :
Alzheimer’s Disease Neuroimaging Initiative
Ya-Ting Chang
Guang-Uei Hung
Keh-Shih Chuang
Kun-Ju Lin
Fan-Pin Tseng
Chiung-Chih Chang
Chia-Yu Lin
Zhi-Kun Lin
Yu-Ching Ni
Ing-Tsung Hsiao
Ming-Chyi Pai
Pai-Yi Chiu
Source :
Diagnostics, Volume 11, Issue 11, Diagnostics, Vol 11, Iss 2091, p 2091 (2021)
Publication Year :
2021
Publisher :
Multidisciplinary Digital Publishing Institute, 2021.

Abstract

The correct differential diagnosis of dementia has an important impact on patient treatment and follow-up care strategies. Tc-99m-ECD SPECT imaging, which is low cost and accessible in general clinics, is used to identify the two common types of dementia, Alzheimer’s disease (AD) and Lewy body dementia (LBD). Two-stage transfer learning technology and reducing model complexity based on the ResNet-50 model were performed using the ImageNet data set and ADNI database. To improve training accuracy, the three-dimensional image was reorganized into three sets of two-dimensional images for data augmentation and ensemble learning, then the performance of various deep learning models for Tc-99m-ECD SPECT images to distinguish AD/normal cognition (NC), LBD/NC, and AD/LBD were investigated. In the AD/NC, LBD/NC, and AD/LBD tasks, the AUC values were around 0.94, 0.95, and 0.74, regardless of training models, with an accuracy of 90%, 87%, and 71%, and F1 scores of 89%, 86%, and 76% in the best cases. The use of transfer learning and a modified model resulted in better prediction results, increasing the accuracy by 32% for AD/NC. The proposed method is practical and could rapidly utilize a deep learning model to automatically extract image features based on a small number of SPECT brain perfusion images in general clinics to objectively distinguish AD and LBD.

Details

Language :
English
ISSN :
20754418
Database :
OpenAIRE
Journal :
Diagnostics
Accession number :
edsair.doi.dedup.....a4a2cd0699175cacfef0a1ee7b28bd93
Full Text :
https://doi.org/10.3390/diagnostics11112091