Author(s) :

Yamuna V, Monisha S, Namratha V, Shalini K, Vandana S

Conference Name :

International Conference on Recent Trends in Computing & Communication Technologies (ICRCCT’2K24)

Abstract :

Parkinson’s disease (PD) is a progressive neurodegenerative disorder affecting millions globally. Early detection is crucial for timely intervention and improved patient outcomes. Conventional diagnostic methods rely on clinical assessments and neurological examinations, which may not detect subtle early stage changes. The integration of image processing techniques and machine learning (ML) algorithms has demonstrated promising results in early PD detection. Image processing extracts valuable information from medical imaging modalities such as MRI, PET, and SPECT, revealing structural and functional brain changes associated with PD prior to the manifestation of clinical symptoms. Advanced algorithms enhance image quality, segment regions of interest, and extract relevant features indicative of early PD signs. ML algorithms analyze these features and identify patterns distinguishing healthy individuals from those with early stage PD. Supervised learning techniques such as SVM, random forests, and deep neural networks can classify new cases, while unsupervised learning methods assist in identifying PD patient subgroups. This combined approach offers advantages including objective and quantitative measures of brain changes, detection of subtle alterations, and integration of multiple information sources to improve diagnostic accuracy. Recent studies have demonstrated the potential of this approach in detecting early stage PD, analyzing MRI scans to identify brain atrophy patterns and applying deep learning to PET images to detect abnormal dopamine metabolism. These advancements contribute to earlier diagnosis, disease progression monitoring, and treatment efficacy evaluation, presenting significant potential for revolutionizing early PD detection and management.

No. of Downloads :

6