Diagnosis of Parkinson's disease based on feature fusion on T2 MRI images

Abstract

Deep‐learning methods (especially convolutional neural networks) using magnetic resonance imaging (MRI) data have been successfully applied to computer‐aided diagnosis of Parkinson's Disease (PD). Early detection and prior care may help patients improve their quality of life, although this neurodegenerative disease has no known cure. In this study, we propose a FResnet18 model to classify MRI images of PD and Health Control (HC) by fusing image texture features with deep features. First, Local Binary Pattern and Gray‐Level Co‐occurrence Matrix are used to extract the handcrafted features. Second, the modified ResNet18 network is used to extract deep features. Finally, the fused features are classified by Support Vector Machine. The classification accuracy rate for MRI images reaches 98.66%, and the findings demonstrate that the model can successfully differentiate between PD and HC. The suggested FResnet18 provides greater performance compared with existing approaches, and it is shown through extensive experimental findings on the Parkinson's Disease Progression Markers Initiative data set that feature fusion may improve classification performance.

Visual Communication Design of Weak and Small Target Images Based on Image Processing Model and Data Fusion

“…Cui X. et al proposed a classification model by fusing image features and depth features to improve the performance of the MRI aided diagnosis model. Experimental results showed that the accuracy rate of this method was as high as 98.66%, and it had higher performance [24]. Aiming at the challenges in crowd counting, Wang L. et al proposed a multi-layer FF network framework for single-image crowd technology, and the experimental results proved the excellent performance of this method [25].…”