A three-dimensional principal component analysis approach for exploratory analysis of hyperspectral data: identification of ovarian cancer samples based on Raman microspectroscopy imaging of blood plasma.

Hyperspectral imaging is a powerful tool to obtain both chemical and spatial information of biological systems. However, few algorithms are capable of working with full three-dimensional images, in which reshaping or averaging procedures are often performed to reduce the data complexity. Herein, we propose a new algorithm of three-dimensional principal component analysis (3D-PCA) for exploratory analysis of complete 3D spectrochemical images obtained through Raman microspectroscopy. Blood plasma samples of ten patients (5 healthy controls, 5 diagnosed with ovarian cancer) were analysed by acquiring hyperspectral imaging in the fingerprint region (∼780-1858 cm-1). Results show that 3D-PCA can clearly differentiate both groups based on its scores plot, where higher loadings coefficients were observed in amino acids, lipids and DNA regions. 3D-PCA is a new methodology for exploratory analysis of hyperspectral imaging, providing fast information for class differentiation.