Independent component analysis for unmixing multi-wavelength photoacoustic images

Independent component analysis (ICA) is a blind source unmixing method that may be used under certain circumstances to decompose multi-wavelength photoacoustic (PA) images into separate components representing individual chromophores. It has the advantages of being fast, easy to implement and computationally inexpensive. This study uses simulated multi-wavelength PA images to investigate the conditions required for ICA to be an accurate unmixing method and compares its performance to linear inversion. An approximate fluence adjustment based on spatially homogeneous optical properties equal to that of the background region was applied to the PA images before unmixing with ICA or LI. ICA is shown to provide accurate separation of the chromophores in cases where the absorption coefficients are lower than certain thresholds, some of which are comparable to physiologically relevant values. However, the results also show that the performance of ICA abruptly deteriorates when the absorption is increased beyond these thresholds. In addition, the accuracy of ICA decreases in the presence of spatially inhomogeneous absorption in the background.