@inproceedings{671729cb15db4590aadef62e465ccb00,
title = "Advit: Vision Transformer On Multi-Modality Pet Images For Alzheimer Disease Diagnosis",
abstract = "We present a new model trained on multi-modalities of Positron Emission Tomography images (PET-AV45 and PET-FDG) for Alzheimer's Disease (AD) diagnosis. Unlike the conventional methods using multi-modal 3D/2D CNN architecture, our design replaces the Convolutional Neural Net-work (CNN) by Vision Transformer (ViT). Considering the high computation cost of 3D images, we firstly employ a 3D-to-2D operation to project the 3D PET images into 2D fusion images. Then, we forward the fused multi-modal 2D images to a parallel ViT model for feature extraction, followed by classification for AD diagnosis. For evaluation, we use PET images from ADNI. The proposed model outperforms several strong baseline models in our experiments and achieves 0.91 accuracy and 0.95 AUC.",
keywords = "Alzheimer's Disease, Multi-modalities, PET image, Vision Transformer (ViT)",
author = "Xin Xing and Gongbo Liang and Yu Zhang and Subash Khanal and Lin, \{Ai Ling\} and Nathan Jacobs",
note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 19th IEEE International Symposium on Biomedical Imaging, ISBI 2022 ; Conference date: 28-03-2022 Through 31-03-2022",
year = "2022",
doi = "10.1109/ISBI52829.2022.9761584",
language = "English",
series = "Proceedings - International Symposium on Biomedical Imaging",
publisher = "IEEE Computer Society",
booktitle = "ISBI 2022 - Proceedings",
}