A Dynamic Local-Global Spatiotemporal Transformer Network for Pain Intensity Estimation in Patients With Disorders of Consciousness.

Abstract

Clinical diagnosis of disorders of conscious ness (DOC) suffers from a high misdiagnosis rate, particularly in differentiating the minimally conscious state (MCS) from the vegetative state/unresponsive wakefulness syndrome (VS/UWS). Recent studies have linked pain perception to the level of consciousness. This study proposes a dynamic local-global spatiotemporal transformer (DLGSTT) network for estimating pain intensity from facial expressions. The DLGSTT network integrates a global multi-scale feature extraction module with a local attention feature ex traction module to efficiently capture diverse features in facial expressions and enhance the perception of expression changes. Additionally, a discrete cosine transform (DCT) enhanced temporal transformer module is incorporated to extract temporal features from the dynamic changes in facial expressions, with pain intensity scores used to quantify pain perception. Experimental results demonstrate that the DLGSTT network outperforms state-of-the-art algorithms on public datasets. Furthermore, when applied to a self-collected dataset of 33 DOC patients, the results show a significant correlation between pain intensity and levels of consciousness, and reveal gender-based differences in pain perception thresholds. Our method is validated as a feasible clinical tool for the auxiliary diagnosis of DOC patients, serving as a valuable complement to behavioral scales and potentially improving diagnostic accuracy.