There are many active research projects accessing and applying shared ADNI data. Use the search above to find specific research focuses on the active ADNI investigations. This information is requested annually as a requirement for data access.
| Principal Investigator | |
| Principal Investigator's Name: | Kleython José Coriolano Cavalcanti de Lacerda |
| Institution: | University of São Paulo |
| Department: | Psicology |
| Country: | |
| Proposed Analysis: | Postdoctoral research proposal: Developing new convolutional neural networks for the classification of neurodegenerative diseases using the ADNI dataset Abstract: Neurodegenerative diseases are a group of progressive diseases that affect the central nervous system, including Alzheimer's disease, frontotemporal dementia, Lewy body dementia, and Parkinson's disease with dementia. Accurate classification of these diseases is important for early diagnosis and effective treatment. The aim of this research is to develop new convolutional neural networks (CNNs) for the accurate classification of neurodegenerative diseases using the ADNI dataset. Specific objectives: Perform a systematic literature review on CNNs for the classification of neurodegenerative diseases. Select and preprocess data from the ADNI dataset, which includes magnetic resonance images, positron emission tomography, and clinical data from patients with Alzheimer's disease, frontotemporal dementia, Lewy body dementia, and Parkinson's disease with dementia. Develop new CNNs for the classification of neurodegenerative diseases using the Keras framework in Python. Evaluate the performance of the developed CNNs using performance metrics such as accuracy, precision, recall, and F1-score. Compare the performance of the developed CNNs with other approaches for the classification of neurodegenerative diseases reported in the literature. Methods and analysis: This study will use the ADNI dataset, which includes magnetic resonance images, positron emission tomography, and clinical data from patients with Alzheimer's disease, frontotemporal dementia, Lewy body dementia, and Parkinson's disease with dementia. The data will be preprocessed using image preprocessing techniques such as intensity correction and normalization. New CNNs will be developed for the classification of neurodegenerative diseases using the Keras framework in Python. The CNNs will be trained using the training set of the ADNI dataset and evaluated using the test set. Performance metrics such as accuracy, precision, recall, and F1-score will be used to evaluate the performance of the CNNs. A comparison of the performance of the developed CNNs with other approaches for the classification of neurodegenerative diseases reported in the literature will be performed. Expected results: It is expected that this research will develop new CNNs for the accurate classification of neurodegenerative diseases using the ADNI dataset. Additionally, it is expected that the results of this research will provide a significant contribution to the development of advanced methods for early diagnosis and effective treatment of neurodegenerative diseases. |
| Additional Investigators |
