The Feasibility of Differentiating Lewy Body Dementia and Alzheimer’s Disease by Deep Learning Using ECD SPECT Images
Yu-Ching Ni,
Fan-Pin Tseng,
Ming-Chyi Pai,
Ing-Tsung Hsiao,
Kun-Ju Lin,
Zhi-Kun Lin,
Chia-Yu Lin,
Pai-Yi Chiu,
Guang-Uei Hung,
Chiung-Chih Chang,
Ya-Ting Chang,
Keh-Shih Chuang,
Alzheimer’s Disease Neuroimaging Initiative
Affiliations
Yu-Ching Ni
Health Physics Division, Institute of Nuclear Energy Research, Atomic Energy Council, Taoyuan 325, Taiwan
Fan-Pin Tseng
Health Physics Division, Institute of Nuclear Energy Research, Atomic Energy Council, Taoyuan 325, Taiwan
Ming-Chyi Pai
Division of Behavioral Neurology, Department of Neurology, National Cheng Kung University Hospital, College of Medicine and Institute of Gerontology, National Cheng Kung University, Tainan 701, Taiwan
Ing-Tsung Hsiao
Department of Medical Imaging and Radiological Sciences & Healthy Aging Center, Chang Gung University, Taoyuan 333, Taiwan
Kun-Ju Lin
Department of Medical Imaging and Radiological Sciences & Healthy Aging Center, Chang Gung University, Taoyuan 333, Taiwan
Zhi-Kun Lin
Health Physics Division, Institute of Nuclear Energy Research, Atomic Energy Council, Taoyuan 325, Taiwan
Chia-Yu Lin
Health Physics Division, Institute of Nuclear Energy Research, Atomic Energy Council, Taoyuan 325, Taiwan
Pai-Yi Chiu
Department of Neurology, Show Chwan Memorial Hospital, Changhua 500, Taiwan
Guang-Uei Hung
Department of Nuclear Medicine, Chang Bing Show Chwan Memorial Hospital, Changhua 505, Taiwan
Chiung-Chih Chang
Department of Neurology, Kaohsiung Chang Gung Memorial Hospital, Kaohsiung 833, Taiwan
Ya-Ting Chang
Department of Neurology, Institute of Translational Research in Biomedicine, Kaohsiung Chang Gung Memorial Hospital, Chang Gung University College of Medicine, Kaohsiung 833, Taiwan
Keh-Shih Chuang
Department of Biomedical Engineering and Environmental Sciences, National Tsing-Hua University, Hsinchu 300, Taiwan
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.
