EARLY PARKINSON'S DISEASE IDENTIFICATION FROM BRAIN MRI IMAGES USING DEEP LEARNING
Keywords:
- An area under the curve (AUC) with convolutional neural networks (CNN)), and magnetic resonance imaging (MRI).Abstract
Alzheimer's disease (PD), which significantly impacts The calibre of life for millions of elderly adults has become a major disorder that affects the brain and spinal cord globally.. Effective therapy and oversight of PD rely going early detection and precise diagnosis. However, diagnosing PD has been challenging due to its similarities with other neurological disorders, leading to a 25% rate of faulty manual diagnoses.
Magnetic Resonance Imaging (MRI) of the brain has demonstrated significant promise in identifying and diagnosing Parkinson's disease. This research suggests utilizing neural networks with convolutions (CNNs), a form of profound learning model, to distinguish Parkinson's illness and differentiate between affected individuals and healthy subjects.. The study utilizes the Initiative for Parkinson Progression Markers (PPMI) dataset for classification.
The Parkinson’s disease recognition system leverages CNN to analyze the images. The effectiveness of The suggested approach is
assessed in light of measurements such as accuracy, particularity, sensitivity, as well as the Area Under the Curve (AUC).
