Functional Magnetic Resonance Imaging
Functional Magnetic Resonance Imaging (fMRI) studies brain activity by measuring blood oxygenation levels, aiming to understand brain function and its relation to cognition and behavior. Current research heavily utilizes deep learning, including transformer networks, autoencoders, and diffusion models, to analyze high-dimensional fMRI data, improve spatial and temporal resolution, and decode cognitive states or even reconstruct visual imagery from brain activity. These advancements are improving diagnostic accuracy for neurological disorders like autism and Alzheimer's disease, and enabling novel applications such as personalized brain-computer interfaces and the development of more brain-like artificial intelligence models.
Papers
An Interpretable Cross-Attentive Multi-modal MRI Fusion Framework for Schizophrenia Diagnosis
Ziyu Zhou, Anton Orlichenko, Gang Qu, Zening Fu, Vince D Calhoun, Zhengming Ding, Yu-Ping Wang
Psychometry: An Omnifit Model for Image Reconstruction from Human Brain Activity
Ruijie Quan, Wenguan Wang, Zhibo Tian, Fan Ma, Yi Yang
Joint-Embedding Masked Autoencoder for Self-supervised Learning of Dynamic Functional Connectivity from the Human Brain
Jungwon Choi, Hyungi Lee, Byung-Hoon Kim, Juho Lee
See Through Their Minds: Learning Transferable Neural Representation from Cross-Subject fMRI
Yulong Liu, Yongqiang Ma, Guibo Zhu, Haodong Jing, Nanning Zheng