Analysis of biomedical spectra and images: from data to diagnosis

While it is now clear that both infrared spectroscopy and spectroscopic imaging can play roles in providing medically relevant information, the raw spectral or imaging measurement seldom reveals directly the property of clinical interest (i.e. is this tissue cancerous? What is the blood glucose concentration? Is tissue perfusion adequate?) Instead, pattern recognition algorithms, clustering methods, regression, and other theoretical methods provide the means to distill diagnostic information from the original measurements. This article discusses the role of these approaches in the discovery of diagnostically relevant spectral and spatial patterns.