Multisensory Integration through Neural Coherence

Excerpt

Whereas the ubiquity and fundamental relevance of multisensory processing have become increasingly clear, the neural mechanisms underlying multisensory interaction are much less well understood. In this chapter, we review recent studies that may cast new light on this issue. Although classical studies have postulated a feedforward convergence of unimodal signals as the primary mechanism for multisensory integration (Stein and Meredith 1993; Meredith 2002), there is now evidence that both feedback and lateral interaction may also be relevant (Driver and Spence 2000; Foxe and Schroeder 2005; Ghazanfar and Schroeder 2006; Kayser and Logothetis 2007). Beyond this changing view on the anatomical substrate, there is increasing awareness that complex dynamic interactions of cell populations, leading to coherent oscillatory firing patterns, may be crucial for mediating cross-systems integration in the brain (von der Malsburg and Schneider 1986; Singer and Gray 1995; Singer 1999; Engel et al. 1992, 2001; Varela et al. 2001; Herrmann et al. 2004a; Fries 2005). Here, we will consider the hypothesis that synchronized oscillations may also provide a potential mechanism for cross-modal integration and for the selection of information that is coherent across different sensory channels. We will (1) contrast the two different views on cross-modal integration that imply different mechanisms (feedforward convergence vs. neural coherence), (2) review recent studies on oscillatory responses and cross-modal processing, and (3) discuss functional aspects and scenarios for the involvement of neural coherence in cross-modal interaction.