S.T. Monteiro, Y. Kosugi, K. Uto, and E. Watanabe (Japan)
Hyperspectral imagery, neural networks, blood, surgical
guidance, image manipulation, medical imaging.
During a surgery, the inevitable presence of blood
covering the surgical field demands efforts to keep the
area as clean as possible. A new hyperspectral data
processing method is being developed to deliver clearer
images to the surgeon. The analysis of optical absorption
properties of the blood and water indicates that, between
the visible and near infrared spectral regions, some
valuable information under the blood layer may be
obtained using a spectral imaging system. We propose a
neural network approach to provide a nonlinear
combination of spectral band reflectance in order to reveal
images that could not be seeing with unprocessed images.
This paper describes the implementation of single-layer
and multi-layer perceptron architectures to perform the
hyperspectral data processing. We present experimental
results attesting the viability of the proposed method. We
demonstrate that hyperspectral imagery can be exploited
as visual aid for surgical guidance.