Eye-tracking research has proven valuable in understanding numerous cognitive functions. Recently, Frey et al. provided an exciting deep learning method for learning eye movements from fMRI data. However, it needed to co-register fMRI into standard space to obtain eyeballs masks, and thus required additional templates and was time consuming. To resolve this issue, in this paper, we propose a framework named MRGazer for predicting eye gaze points from fMRI in individual space. The MRGazer consisted of eyeballs extraction module and a residual network-based eye gaze prediction. Compared to the previous method, the proposed framework skips the fMRI co-registration step, simplifies the processing protocol and achieves end-to-end eye gaze regression. The proposed method achieved superior performance in a variety of eye movement tasks than the co-registration-based method, and delivered objective results within a shorter time (~ 0.02 Seconds for each volume) than prior method (~0.3 Seconds for each volume).

翻译：眼动追踪研究已被证明对理解众多认知功能具有重要价值。近期，Frey等人提出了一种基于深度学习的有趣方法，可从fMRI数据中学习眼动模式。然而，该方法需要将fMRI共配准至标准空间以获取眼球掩膜，从而需要额外模板且耗时较长。为解决此问题，本文提出了一种名为MRGazer的框架，用于从个体空间的fMRI预测眼动注视点。MRGazer包含眼球提取模块和基于残差网络的眼动预测模块。与先前方法相比，所提框架跳过了fMRI共配准步骤，简化了处理流程并实现了端到端的眼动回归。所提方法在多种眼动任务中均优于基于共配准的方法，并且在更短的时间内（每体素约0.02秒，而先前方法每体素约0.3秒）提供了客观结果。