Automatic classification and prediction models for early Parkinson’s disease diagnosis from SPECT imaging - ScienceDirect
Machine learning and pattern recognition methods could simplify the development of these automatic PD diagnosis approaches. For instance, Prashanth et al. (2014) use intensity features extracted from SPECT images along with an SVM classifier, while Focke et al. (2011) use the voxel-based morphometry (VBM) on T1-weighted MRI with an SVM classifier to identify idiopathic Parkinson syndrome patients. In another work, Salvatore et al. (2014) proposes a method based on principal component analysis (PCA) on morphological T1-weighted MRI, in combination with an SVM for diagnosis of PD and progressive supranuclear palsy (PSP) patients. Cookies are used by this site. Cookie settings | Your Privacy Choices All content on this site: Copyright © 2024 Elsevier B.V., its licensors, and contributors. All rights are reserved, including those for text and data mining, AI training, and similar technologies. For all open access content, the Creative Commons licensing terms apply. These cookies are necess
Machine learning and pattern recognition methods could simplify the development of these automatic PD diagnosis approaches. For instance, Prashanth et al. (2014) use intensity features extracted from SPECT images along with an SVM classifier, while Focke et al. (2011) use the voxel-based morphometry (VBM) on T1-weighted MRI with an SVM classifier to identify idiopathic Parkinson syndrome patients. In another work, Salvatore et al. (2014) proposes a method based on principal component analysis (PCA) on morphological T1-weighted MRI, in combination with an SVM for diagnosis of PD and progressive
Explore this link on the map →