Synthetic-Brain-Aging

Source code

The source code for the paper [1] can be found in the directory code.

Data sharing

In this repo, we publish a synthetic collection of three datasets generated by our proposed methodology (the following paper [1]). More details are shown in the corresponding subsection.

If you use either of these datasets, please cite the following and refer to the corresponding Data Use Agreement.

• [1] Fast 3D image generation for healthy brain aging using diffeomorphic registration. Fu, Jingru and Tzortzakakis, Antonios and Barroso, José and Westman, Eric and Ferreira, Daniel and Moreno, Rodrigo and for the Alzheimer's Disease Neuroimaging Initiative, 2022. doi: 10.1002/hbm.26165

• [2] OASIS-3: Longitudinal Neuroimaging, Clinical, and Cognitive Dataset for Normal Aging and Alzheimer Disease. Pamela J LaMontagne, Tammie L.S. Benzinger, John C. Morris, Sarah Keefe, Russ Hornbeck, Chengjie Xiong, Elizabeth Grant, Jason Hassenstab, Krista Moulder, Andrei Vlassenko, Marcus E. Raichle, Carlos Cruchaga, Daniel Marcus, 2019. medRxiv. doi: 10.1101/2019.12.13.19014902

• [3] The Alzheimer's disease neuroimaging initiative (ADNI): MRI methods. Jack Jr C R, Bernstein M A, Fox N C, et al. Journal of Magnetic Resonance Imaging: An Official Journal of the International Society for Magnetic Resonance in Medicine, 2008, 27(4): 685-691.

• [4] Muehlboeck J S, Westman E, Simmons A. TheHiveDB image data management and analysis framework[J]. Frontiers in neuroinformatics, 2014, 7: 49. doi: 10.3389/fninf.2013.00049

Data access

• OASIS3 and ADNI: Please check AIDA Data Hub page link
• GENIC: Please contact Daniel Ferreira Padilla

Synthetic collection of three data sets

This collection includes the synthetic aging brain T1 MRI scans derived from three data sets: two publicly available data sets i) OASIS-3, ii) ADNI, and a new data set GENIC from our collaborator Daniel Ferreira Padilla. Note that the goal of this project is to augment the HEALTHY longitudinal brain MRI data as much as possible at different ages.

The details of three synthetic data sets are shown as follows:

DATA SET      NUMBER OF SYNTHETIC SCANS      NUMBER OF SUBJECTS      
OASIS-3       3948                           347
ADNI          2500                           353
GENIC         1100                           96

Each directory contains a series of synthetic T1-w scans and corresponding segmentation for each subject. All segmentations are collected by using FreeSurfer (aparc+aseg.mgz). Details for each directory are shown as follows:

FILENAME      SHAPE             SPACE
imgX.nii.gz   160 x 160 x 192   synthetic scan in template space
segX.nii.gz   160 x 160 x 192   corresponding segmentation in template space

In addition, we also provide the metadata file, including linear ages and regressed ages for each synthetic scan for each data set, respectively. Please refer to paper [1] for more details on the age assignment.

Data Use Agreement

• OASIS-3
• ADNI
• [GENIC] A reasonable request should be sent to Daniel Ferreira Padilla to access the data