Yu-Ching Ni1,2, Fan-Pin Tseng3, Ming-Chyi Pai4,5, Ing-Tsung Hsiao6,7, Kun-Ju Lin6,7, Zhi-Kun Lin3, Wen-Bin Lin3, Pai-Yi Chiu8, Guang-Uei Hung9, Chiung-Chih Chang10, Ya-Ting Chang11, Keh-Shih Chuang12. 1. Health Physics Division, Institute of Nuclear Energy Research, Atomic Energy Council, 1000 Wenhua Rd. Jiaan Village, Longtan District, Taoyuan City, 325, Taiwan. janet@iner.gov.tw. 2. Department of Biomedical Engineering and Environmental Sciences, National Tsing-Hua University, Hsinchu, Taiwan. janet@iner.gov.tw. 3. Health Physics Division, Institute of Nuclear Energy Research, Atomic Energy Council, 1000 Wenhua Rd. Jiaan Village, Longtan District, Taoyuan City, 325, Taiwan. 4. Division of Behavioral Neurology, Department of Neurology, National Cheng Kung University Hospital, College of Medicine and Institute of Gerontology, National Cheng Kung University, 138, Sheng Li Road, North District, Tainan, 704, Taiwan. pair@mail.ncku.edu.tw. 5. Alzheimer's Disease Research Center, National Cheng Kung University Hospital, Tainan, Taiwan. pair@mail.ncku.edu.tw. 6. Department of Medical Imaging and Radiological Sciences & Healthy Aging Center, Chang Gung University, Taoyuan, Taiwan. 7. Department of Nuclear Medicine and Molecular Imaging Center, Linkou Chang Gung Memorial Hospital, Taoyuan, Taiwan. 8. Department of Neurology, Show Chwan Memorial Hospital, Changhua, Taiwan. 9. Department of Nuclear Medicine, Chang Bing Show Chwan Memorial Hospital, Changhua, Taiwan. 10. Department of Neurology, Kaohsiung Chang Gung Memorial Hospital, Kaohsiung, Taiwan. 11. Department of Neurology, Institute of Translational Research in Biomedicine, Kaohsiung Chang Gung Memorial Hospital, Chang Gung University College of Medicine, Kaohsiung, Taiwan. 12. Department of Biomedical Engineering and Environmental Sciences, National Tsing-Hua University, Hsinchu, Taiwan.
Abstract
OBJECTIVE: To develop a practical method to 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 evaluate Alzheimer's disease (AD). METHODS: For the properties of low cost and convenient access in general clinics, Tc-99-ECD SPECT imaging data in brain perfusion detection was used in this study for AD detection. Two-stage transfer learning based on the Inception v3 network model was performed using the ImageNet dataset 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. The effect of pre-training parameters for Tc-99m-ECD SPECT image to distinguish AD from normal cognition (NC) was investigated, as well as the effect of the sample size of F-18-FDG PET images used in pre-training. The same model was also fine-tuned for the prediction of the MMSE score from the Tc-99m-ECD SPECT image. RESULTS: The AUC values of w/wo pre-training parameters for Tc-99m-ECD SPECT image to distinguish AD from NC were 0.86 and 0.90. The sensitivity, specificity, precision, accuracy, and F1 score were 100%, 75%, 76%, 86%, and 86%, respectively for the training model with 1000 cases of F-18-FDG PET image for pre-training. The AUC values for various sample sizes of the training dataset (100, 200, 400, 800, 1000 cases) for pre-training were 0.86, 0.91, 0.95, 0.97, and 0.97. Regardless of the pre-training condition ECD dataset used, the AUC value was greater than 0.85. Finally, predicting cognitive scores and MMSE scores correlated (R2 = 0.7072). CONCLUSIONS: With the ADNI pre-trained model, the sensitivity and accuracy of the proposed deep learning model using SPECT ECD perfusion images to differentiate AD from NC were increased by approximately 30% and 10%, respectively. Our study indicated that the model trained on PET FDG metabolic imaging for the same disease could be transferred to a small sample of SPECT cerebral perfusion images. This model will contribute to the practicality of SPECT cerebral perfusion images using deep learning technology to objectively recognize AD.
OBJECTIVE: To develop a practical method to 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 evaluate Alzheimer's disease (AD). METHODS: For the properties of low cost and convenient access in general clinics, Tc-99-ECD SPECT imaging data in brain perfusion detection was used in this study for AD detection. Two-stage transfer learning based on the Inception v3 network model was performed using the ImageNet dataset 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. The effect of pre-training parameters for Tc-99m-ECD SPECT image to distinguish AD from normal cognition (NC) was investigated, as well as the effect of the sample size of F-18-FDG PET images used in pre-training. The same model was also fine-tuned for the prediction of the MMSE score from the Tc-99m-ECD SPECT image. RESULTS: The AUC values of w/wo pre-training parameters for Tc-99m-ECD SPECT image to distinguish AD from NC were 0.86 and 0.90. The sensitivity, specificity, precision, accuracy, and F1 score were 100%, 75%, 76%, 86%, and 86%, respectively for the training model with 1000 cases of F-18-FDG PET image for pre-training. The AUC values for various sample sizes of the training dataset (100, 200, 400, 800, 1000 cases) for pre-training were 0.86, 0.91, 0.95, 0.97, and 0.97. Regardless of the pre-training condition ECD dataset used, the AUC value was greater than 0.85. Finally, predicting cognitive scores and MMSE scores correlated (R2 = 0.7072). CONCLUSIONS: With the ADNI pre-trained model, the sensitivity and accuracy of the proposed deep learning model using SPECT ECD perfusion images to differentiate AD from NC were increased by approximately 30% and 10%, respectively. Our study indicated that the model trained on PET FDG metabolic imaging for the same disease could be transferred to a small sample of SPECT cerebral perfusion images. This model will contribute to the practicality of SPECT cerebral perfusion images using deep learning technology to objectively recognize AD.