Journal
INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS
Volume 37, Issue 12, Pages 11362-11381Publisher
WILEY-HINDAWI
DOI: 10.1002/int.23046
Keywords
deep learning; feature fusion; MRI; Parkinson's disease; ResNet18
Categories
Funding
- Key projects of Zhejiang Provincial Department of Culture and Tourism [20225418921]
- Highquality Course for Graduate Education of Shandong Province [SDYKC19178]
- Undergraduate Teaching Reform Research Key Project of Shandong Province [Z2021208]
- Zhejiang Medicine and Health Science and Technology Plan [2019KY260]
- Natural Science Foundation of Zhejiang Province [LQ19H090006]
Ask authors/readers for more resources
In this study, a FResnet18 model is proposed to classify MRI images of PD and HC by fusing image texture features with deep features. The results show that the model can successfully differentiate between PD and HC with high accuracy, and it outperforms existing approaches.
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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available