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: | Jinn-Yi Yeh |
Institution: | National Chiayi University |
Department: | Management Information Systems |
Country: | |
Proposed Analysis: | In recent years, the success of deep learning has created a strong interest in learning related knowledge from both industry and students. However, convolutional neural network (CNN) models are often regarded as a mysterious black box. They do not provide explanations for specific predictions and decision making. This study proposes a visual modeling framework to investigate and solve the interpretability problem of CNNs in localizing hippocampal repertoires in MRI images of the brain. The proposed approach will construct a computer-aided diagnosis system for target detection of Alzheimer's disease, and interpret and visualize the layers of the convolutional neural network, focusing on the structure and interpretation of the CNN and locating the hippocampal gyrus in brain MRI images, before performing a modified hierarchical CNN. Although these visualizations are not perfect, it is hoped that they will help beginners to better understand CNNs and develop an interest in more complex network models. |
Additional Investigators |