The Feasibility of Differentiating Lewy Body Dementia and Alzheimer’s Disease by Deep Learning Using ECD SPECT Images
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 demen...
Guardado en:
| Autores principales: | , , , , , , , , , , , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
MDPI AG
2021
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/2efa42b875a84204a57d49221bc93ee3 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| id |
oai:doaj.org-article:2efa42b875a84204a57d49221bc93ee3 |
|---|---|
| record_format |
dspace |
| spelling |
oai:doaj.org-article:2efa42b875a84204a57d49221bc93ee32021-11-25T17:21:33ZThe Feasibility of Differentiating Lewy Body Dementia and Alzheimer’s Disease by Deep Learning Using ECD SPECT Images10.3390/diagnostics111120912075-4418https://doaj.org/article/2efa42b875a84204a57d49221bc93ee32021-11-01T00:00:00Zhttps://www.mdpi.com/2075-4418/11/11/2091https://doaj.org/toc/2075-4418The 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.Yu-Ching NiFan-Pin TsengMing-Chyi PaiIng-Tsung HsiaoKun-Ju LinZhi-Kun LinChia-Yu LinPai-Yi ChiuGuang-Uei HungChiung-Chih ChangYa-Ting ChangKeh-Shih ChuangAlzheimer’s Disease Neuroimaging InitiativeMDPI AGarticleECD SPECT imagesLewy body dementiaAlzheimer’s diseasetransfer learningMedicine (General)R5-920ENDiagnostics, Vol 11, Iss 2091, p 2091 (2021) |
| institution |
DOAJ |
| collection |
DOAJ |
| language |
EN |
| topic |
ECD SPECT images Lewy body dementia Alzheimer’s disease transfer learning Medicine (General) R5-920 |
| spellingShingle |
ECD SPECT images Lewy body dementia Alzheimer’s disease transfer learning Medicine (General) R5-920 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 The Feasibility of Differentiating Lewy Body Dementia and Alzheimer’s Disease by Deep Learning Using ECD SPECT Images |
| description |
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. |
| format |
article |
| author |
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 |
| author_facet |
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 |
| author_sort |
Yu-Ching Ni |
| title |
The Feasibility of Differentiating Lewy Body Dementia and Alzheimer’s Disease by Deep Learning Using ECD SPECT Images |
| title_short |
The Feasibility of Differentiating Lewy Body Dementia and Alzheimer’s Disease by Deep Learning Using ECD SPECT Images |
| title_full |
The Feasibility of Differentiating Lewy Body Dementia and Alzheimer’s Disease by Deep Learning Using ECD SPECT Images |
| title_fullStr |
The Feasibility of Differentiating Lewy Body Dementia and Alzheimer’s Disease by Deep Learning Using ECD SPECT Images |
| title_full_unstemmed |
The Feasibility of Differentiating Lewy Body Dementia and Alzheimer’s Disease by Deep Learning Using ECD SPECT Images |
| title_sort |
feasibility of differentiating lewy body dementia and alzheimer’s disease by deep learning using ecd spect images |
| publisher |
MDPI AG |
| publishDate |
2021 |
| url |
https://doaj.org/article/2efa42b875a84204a57d49221bc93ee3 |
| work_keys_str_mv |
AT yuchingni thefeasibilityofdifferentiatinglewybodydementiaandalzheimersdiseasebydeeplearningusingecdspectimages AT fanpintseng thefeasibilityofdifferentiatinglewybodydementiaandalzheimersdiseasebydeeplearningusingecdspectimages AT mingchyipai thefeasibilityofdifferentiatinglewybodydementiaandalzheimersdiseasebydeeplearningusingecdspectimages AT ingtsunghsiao thefeasibilityofdifferentiatinglewybodydementiaandalzheimersdiseasebydeeplearningusingecdspectimages AT kunjulin thefeasibilityofdifferentiatinglewybodydementiaandalzheimersdiseasebydeeplearningusingecdspectimages AT zhikunlin thefeasibilityofdifferentiatinglewybodydementiaandalzheimersdiseasebydeeplearningusingecdspectimages AT chiayulin thefeasibilityofdifferentiatinglewybodydementiaandalzheimersdiseasebydeeplearningusingecdspectimages AT paiyichiu thefeasibilityofdifferentiatinglewybodydementiaandalzheimersdiseasebydeeplearningusingecdspectimages AT guangueihung thefeasibilityofdifferentiatinglewybodydementiaandalzheimersdiseasebydeeplearningusingecdspectimages AT chiungchihchang thefeasibilityofdifferentiatinglewybodydementiaandalzheimersdiseasebydeeplearningusingecdspectimages AT yatingchang thefeasibilityofdifferentiatinglewybodydementiaandalzheimersdiseasebydeeplearningusingecdspectimages AT kehshihchuang thefeasibilityofdifferentiatinglewybodydementiaandalzheimersdiseasebydeeplearningusingecdspectimages AT alzheimersdiseaseneuroimaginginitiative thefeasibilityofdifferentiatinglewybodydementiaandalzheimersdiseasebydeeplearningusingecdspectimages AT yuchingni feasibilityofdifferentiatinglewybodydementiaandalzheimersdiseasebydeeplearningusingecdspectimages AT fanpintseng feasibilityofdifferentiatinglewybodydementiaandalzheimersdiseasebydeeplearningusingecdspectimages AT mingchyipai feasibilityofdifferentiatinglewybodydementiaandalzheimersdiseasebydeeplearningusingecdspectimages AT ingtsunghsiao feasibilityofdifferentiatinglewybodydementiaandalzheimersdiseasebydeeplearningusingecdspectimages AT kunjulin feasibilityofdifferentiatinglewybodydementiaandalzheimersdiseasebydeeplearningusingecdspectimages AT zhikunlin feasibilityofdifferentiatinglewybodydementiaandalzheimersdiseasebydeeplearningusingecdspectimages AT chiayulin feasibilityofdifferentiatinglewybodydementiaandalzheimersdiseasebydeeplearningusingecdspectimages AT paiyichiu feasibilityofdifferentiatinglewybodydementiaandalzheimersdiseasebydeeplearningusingecdspectimages AT guangueihung feasibilityofdifferentiatinglewybodydementiaandalzheimersdiseasebydeeplearningusingecdspectimages AT chiungchihchang feasibilityofdifferentiatinglewybodydementiaandalzheimersdiseasebydeeplearningusingecdspectimages AT yatingchang feasibilityofdifferentiatinglewybodydementiaandalzheimersdiseasebydeeplearningusingecdspectimages AT kehshihchuang feasibilityofdifferentiatinglewybodydementiaandalzheimersdiseasebydeeplearningusingecdspectimages AT alzheimersdiseaseneuroimaginginitiative feasibilityofdifferentiatinglewybodydementiaandalzheimersdiseasebydeeplearningusingecdspectimages |
| _version_ |
1718412460003688448 |