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: | Sanskriti Gupta |
| Institution: | The NorthCap University |
| Department: | Electronics and communications |
| Country: | |
| Proposed Analysis: | Alzheimer’s disease is a progressive, irreversible, neurodegenerative disorder and multifaceted disease, occurs most frequently in older age. Alzheimer’s disease slowly destroys brain cells causing loss of memory, thinking skill, behavior and learning and ultimately ability to perform simple tasks. Brain is the centre of human nervous system. Brain is made up of more than 100 billion of nerves that are connected to trillions of other connection called synapses. It contains spatially distributed but functionally connected regions that continuously share stimulus and responses to each other. A number of computational and biological tools have developed to collect this information. Any dysfunction in the neural activity due to Alzheimer causes mainly due to failure of damage in the brain connectivity network. For the early detection of Alzheimer’s disease, the neuroimaging data and its analysis made much attraction in recent years. In order to detect and study Alzheimer and other brain related diseases; there exists some neuroimaging modalities such as positron emission tomography (PET), magnetic resonance imaging (MRI), computed tomography (CT). The past two decades have witnessed the increasing use of resting state functional magnetic resonance imaging (rs-fMRI) as a tool for mapping human brain network. The resting brain activity is measured through observing the changes in oxygen and blood flow in the brain parts and among the brain parts, which creates a signal referred to blood-oxygen-level dependent (BOLD) signal that can be measured using functional magnetic resonance imaging technique. The BOLD signal represents low-frequency spontaneous fluctuations of oxygen and blood flow in brain network regions. As of now, there are very few standard automated fMRI tools in hospitals that can be used for disease diagnosis whose performances are not up to the mark. This has led the motivation to development of better tools or algorithms to classify fMRI data and more importantly to recognize brain disorder data from healthy subjects that can aid doctors. Numerous techniques using statistical approaches, frequency domain approaches including wavelets and machine learning algorithms have been used in the past to classify patients with brain disorder using fMRIs. However their accuracies can hardly be relied upon. In recent years, owing to the increasing success of deep learning methods in the areas of speech, signal, image, video and text mining, and recognition, these methods are being explored in neurodisorder disease diagnosis as well using structural MRI (sMRI) or functional MRI (fMRI) data. In this project classification of Alzheimer affected and healthy individuals will be performed using deep learning techniques. These techniques require large amount of data for training the networks and faster processors, but are known to give higher accuracies. Deep learning networks will be first trained using fMRIs of both Alzheimer affected and healthy persons. Once the network is trained, fMRI of an unclassified patient will be fed to the network in order to diagnose whether the patient is affected by alzheimer or not and if he/she is, what is the level of disease. |
| Additional Investigators |
