Synthesizing affective neurophysiological signals using generative models: A review paper.

The integration of emotional intelligence in machines is an important step in advancing human-computer interaction. This demands the development of reliable end-to-end emotion recognition systems. However, the scarcity of public affective datasets presents a challenge. In this literature review, we emphasize the use of generative models to address this issue in neurophysiological signals, particularly Electroencephalogram (EEG) and Functional Near-Infrared Spectroscopy (fNIRS). We provide a comprehensive analysis of different generative models used in the field, examining their input formulation, deployment strategies, and methodologies for evaluating the quality of synthesized data. This review serves as a comprehensive overview, offering insights into the advantages, challenges, and promising future directions in the application of generative models in emotion recognition systems. Through this review, we aim to facilitate the progression of neurophysiological data augmentation, thereby supporting the development of more efficient and reliable emotion recognition systems.

Atlas-Free Automatic Segmentation of Sheep Brain MRI.

Automated 3D brain segmentation methods have been shown to produce fast, reliable, and reproducible segmentations from magnetic resonance imaging (MRI) sequences for the anatomical structures of the human brain. Despite the extensive experimental research utility of large animal species such as the sheep, there is limited literature on the segmentation of their brains relative to that of humans. The availability of automatic segmentation algorithms for animal brain models can have significant impact for experimental explorations, such as treatment planning and studying brain injuries. The neuroanatomical similarities in size and structure between sheep and humans, plus their long lifespan and docility, make them an ideal animal model for investigating automatic segmentation methods.This work, for the first time, proposes an atlas-free fully automatic sheep brain segmentation tool that only requires structural MR images (T1-MPRAGE images) to segment the entire sheep brain in less than one minute. We trained a convolutional neural network (CNN) model - namely a four-layer U-Net - on data from eleven adult sheep brains (training and validation: 8 sheep, testing: 3 sheep), with a high overall Dice overlap score of 93.7%.Clinical relevance- Upon future validation on larger datasets, our atlas-free automatic segmentation tool can have clinical utility and contribute towards developing robust and fully automatic segmentation tools which could compete with atlas-based tools currently available.