Analysis of electrophysiological signals like ECG and EEG is crucial for cerebrovascular diagnosis, presenting a spatio-temporal challenge due to recorded data from multiple electrodes. Traditional methods and deep time-series models focus only on the time component, overlooking space and frequency variations. Alternatively, computer vision and fusion models enable the joint analysis of both spatio-temporal dimensions. The use of signal-to-image transformation to uncover spatio-temporal correlations is inspected in this review, providing four different transformation approaches. A review of the state of the art has resulted in a large number of articles analyzing electrophysiological signals using typical imaging models. In addition, recent studies show that combining raw signals with their transformation to image can result in superior performances compared to the other approaches.