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: | Tim Riedel |
Institution: | Hasso Plattner Institute |
Department: | Digital Health and Machine Learning |
Country: | |
Proposed Analysis: | I want to pre-train an autoencoder machine learning model on the ADNI dataset, which uses Vision Transformers, that need a lot of data. Specifically I am using a masked image modelling approach by masking the images randomly and reconstructing the images in the pre-training step, thereby learning a feature representation of the input images. This can be used in a fine-tune step to reduce the number of classification examples necessary to train a classifier with good accuracies. The pre-trained model will also be evaluated on other datasets for segmentation, such as BraTS18. |
Additional Investigators |