Optimization of Infrared Spectral Manipulation for Surgical Visual Aid

During a surgical procedure, blood covering the surgical field hinders the surgeon's visual inspection. We propose a novel application of hyperspectral imagery in the biomedical field. We conceived a method to exploit the capabilities of hyperspectral imaging systems in order to provide clearer images of areas covered by blood to the surgeon. We developed a neural network approach to generate a nonlinear combination of spectral reflectance bands in the near infrared region revealing images that could not be seeing in unprocessed images. The ex- perimental results are compared with conventional image processing techniques. We present in vitro experiments using human blood and in situ experiments using guinea pigs to attest the validity of the proposed method.