This paper provides a comprehensive overview of recent advancements in stress detection using spectral imaging techniques. Originally developed for remote sensing, hyperspectral imaging has evolved, and with advancements in technology, it is now being applied in diverse fields, including healthcare and psychological research. The rich spectral and spatial data provided by hyperspectral imaging enable the extraction of tissue oxygen saturation (StO2) value as a physiological marker, for detecting stress. The integration of machine learning and deep learning is explored to enhance the accuracy and reliability of stress detection systems. Key features, available datasets and limitations in this field are also discussed. This review serves as a comprehensive resource for researchers in the fields of medical imaging, psychophysiology and deep learning, offering insights into the state-of-the-art applications and future prospects for hyperspectral imaging in stress detection.