2D high-resolution synthetic MR images of Alzheimer's patients and healthy subjects using PACGAN

This dataset encompasses a NIfTI file containing a collection of 500 images, each capturing the central axial slice of a synthetic brain MRI. Accompanying this file is a CSV dataset that serves as a repository for the corresponding labels linked to each image: Label 0: Healthy Controls (HC) Label 1: Alzheimer's Disease (AD) Each image within this dataset has been generated by PACGAN (Progressive Auxiliary Classifier Generative Adversarial Network), a framework designed and implemented by the AI for Medicine Research Group at the University of Bologna. PACGAN is a generative adversarial network trained to generate high-resolution images belonging to different classes. In our work, we trained this framework on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset, which contains brain MRI images of AD patients and HC. The implementation of the training algorithm can be found within our GitHub repository, with Docker containerization. For further exploration, the pre-trained models are available within the Code Ocean capsule. These models can facilitate the generation of synthetic images for both classes and also aid in classifying new brain MRI images.