Deep Learning Based Parkinson’s Disease Progression Analysis Using DaTscan Images

Deep Learning Based Parkinson’s Disease Progression Analysis Using DaTscan Images

IEEE BASE PAPER ABSTRACT:

Parkinson’s disease (PD) is one of the chronic neurological diseases whose progression is slow and symptoms have similarities with other diseases. Early detection and diagnosis of PD is crucial to prescribe proper treatment for patient’s productive and healthy lives. The disease’s symptoms are characterized by tremors, muscle rigidity, slowness in movements, balancing along with other psychiatric symptoms. The dynamics of handwritten records served as one of the dominant mechanisms which support PD detection and assessment. Several machine learning methods have been investigated for the early detection of this disease. But most of these handcrafted feature extraction techniques predominantly suffer from low performance accuracy issues. This cannot be tolerable for dealing with detection of such a chronic ailment. To this end, an efficient deep learning model is proposed which can assist to have early detection of Parkinson’s disease. The significant contribution of the proposed model is to select the most optimum features which have the effect of getting the high-performance accuracies. The feature optimization is done through genetic algorithm wherein K-Nearest Neighbour technique. The proposed novel model results into detection accuracy higher than 95%, precision of 98%, area under curve of 0.90 with a loss of 0.12 only. The performance of proposed model is compared with some state-of-the-art machine learning and deep learning-based PD detection approaches to demonstrate the better detection ability of our model.

PROJECT OUTPUT VIDEO:

ALGORITHM / MODEL USED:

Inception V3 Model.

OUR PROPOSED PROJECT ABSTRACT:

Parkinson’s Disease (PD) is a complex neurodegenerative disorder characterized by the progressive degeneration of dopaminergic neurons in the substantia nigra of the brain. Early and accurate diagnosis of PD, as well as the monitoring of disease progression, is crucial for effective clinical management. In this project, we present a novel approach to analyze and classify different stages of Parkinson’s Disease using DaTscan images, a commonly used imaging technique for assessing dopamine transporter density in the brain. Our study leverages the power of deep learning and the Inception V3 model, implemented in MATLAB, to automatically extract intricate features from DaTscan images. This deep learning model has demonstrated remarkable capabilities in various computer vision tasks, and in our study, it is employed for the classification of DaTscan images into four distinct categories: Normal, Parkinson Disease Initial Stage, Parkinson Disease Moderate Stage, and Parkinson Disease Severe Stage. The dataset used in our research comprises a diverse range of DaTscan images collected from patients at various stages of Parkinson’s Disease. Extensive preprocessing techniques were applied to standardize and enhance the quality of the images, ensuring reliable model training. The Inception V3 model was then fine-tuned on this dataset to capture disease-specific patterns and features. Our proposed approach achieved an impressive accuracy rate of 95.45% in classifying DaTscan images into the four aforementioned categories. This high accuracy demonstrates the effectiveness of deep learning in identifying subtle changes in DaTscan images associated with different stages of Parkinson’s Disease. The model’s performance was also evaluated using standard metrics such as precision, recall, and F1-score, further confirming its robustness and reliability. The implications of our research are profound, as it provides a non-invasive and objective means of assessing the progression of Parkinson’s Disease based on DaTscan images. This technology has the potential to assist clinicians in making more informed decisions regarding treatment strategies and patient care. Additionally, our deep learning-based approach can serve as a valuable tool for early diagnosis, allowing for timely intervention and improved patient outcomes. In summary, our project showcases the power of deep learning, specifically the Inception V3 model, in the field of medical image analysis for Parkinson’s Disease progression assessment. The achieved accuracy of 95.45% highlights the potential of this technology to revolutionize the diagnosis and monitoring of Parkinson’s Disease, ultimately enhancing the quality of life for affected individuals.

SYSTEM REQUIREMENTS:

HARDWARE REQUIREMENTS: 

• System : Pentium i3 Processor.
• Hard Disk : 500 GB.
• Monitor : 15’’ LED.
• Input Devices : Keyboard, Mouse.
• Ram : 8 GB.

SOFTWARE REQUIREMENTS: 

• Operating system : Windows 10 Pro.
• Coding Language : MATLAB
• Tool :         MATLABR2021A

REFERENCE:

SURA MAHMOOD ABDULLAH, THEKRA ABBAS, MUNZIR HUBIBA BASHIR, ISHFAQ AHMAD KHAJA, MUSHEER AHMAD, NAGLAA F. SOLIMAN, AND WALID EL-SHAFAI, “Deep Transfer Learning Based Parkinson’s Disease Detection Using Optimized Feature Selection”, IEEE Access (Volume: 11), 2023.