Classification of the Multiple Stages of Parkinson’s Disease by a Deep Convolution Neural Network Based on 99mTc-TRODAT-1 SPECT Images

Abstract

Single photon emission computed tomography (SPECT) has been employed to detect Parkinson’s disease (PD). However, analysis of the SPECT PD images was mostly based on the region of interest (ROI) approach. Due to limited size of the ROI, especially in the multi-stage classification of PD, this study utilizes deep learning methods to establish a multiple stages classification model of PD. In the retrospective study, the 99mTc-TRODAT-1 was used for brain SPECT imaging. A total of 202 cases were collected, and five slices were selected for analysis from each subject. The total number of images was thus 1010. According to the Hoehn and Yahr Scale standards, all the cases were divided into healthy, early, middle, late four stages, and HYS I~V six stages. Deep learning is compared with five convolutional neural networks (CNNs). The input images included grayscale and pseudo color of two types. The training and validation sets were 70% and 30%. The accuracy, recall, precision, F-score, and Kappa values were used to evaluate the models’ performance. The best accuracy of the models based on grayscale and color images in four and six stages were 0.83 (AlexNet), 0.85 (VGG), 0.78 (DenseNet) and 0.78 (DenseNet).

Low-Parameter Small Convolutional Neural Network Applied to Functional Medical Imaging of Tc-99m Trodat-1 Brain Single-Photon Emission Computed Tomography for Parkinson’s Disease

“…"Classification of the Multiple Stages of Parkinson's Disease by a Deep Convolution Neural Network Based on 99mTc-TRODAT-1 SPECT Images" is the CNN model architecture proposed by I-Shou University for TRODAT SPECT classification [15]. It uses five CNN models-namely, AlexNet, GoogLeNet, ResNet, VGG, and DenseNet-for deep learning.…”

Detection of Postural Control in Young and Elderly Adults Using Deep and Machine Learning Methods with Joint–Node Plots

“…The fully connected CNN layers extracted and stored the features of the input image. The used CNNs were described by Hsu et al [ 40 ] ( Table 2 ). The CNN has been confirmed to be efficient and useful for image feature extraction in the fields of biomedicine and biology [ 41 , 42 , 43 ].…”

Uncertainty-driven ensembles of multi-scale deep architectures for image classification

“…Pneumonia Acc = 99.34 [99] 112 120 CXR images CheXNet 14 diseases Acc = 87.00 [100] 1125 CXR images SLB and FFB Nets Normal vs. COVID Acc = 99.52 [101] 1508 CXR images EfficientNet Normal vs. COVID vs. Pneumonia Acc = 99.62 98 PET/CT CNN PD vs. CTRL Acc = 93.00 [110] 406 MRI CNN PD vs. CTRL Acc = 95.30 [111] 341 PET CNN PD vs. CTRL Acc = 84.20 [112] 200 SPECT CNN PD vs. CTRL Acc = 85.00 [113] 230 MRI CNN PD vs. CTRL Acc = 81.00 performance. This is one of the reasons why we used relatively small kernel sizes, in addition to the huge computational cost of convolution in three-dimensional images.…”