Reconstruction of hyperspectral cutaneous data from an artificial neural network-based multispectral imaging system

Romuald Jolivot (1) , Pierre Vabres (1, 2) , Franck S. Marzani (1)

1 Le2i - Laboratoire Electronique, Informatique et Image [UMR6306]
2 CHU Dijon

The development of an integrated MultiSpectral Imaging (MSI) system yielding hyperspectral cubes by means of artificial neural networks is described. The MSI system is based on a CCD camera, a rotating wheel bearing a set of seven interference filters, a light source and a computer. The resulting device has been elaborated for in vivo imaging of skin lesions. It provides multispectral images and is coupled with a software reconstructing hyperspectral cubes from multispectral images. Reconstruction is performed by a neural network-based algorithm using heteroassociative memories. The resulting hyperspectral cube provides skin optical reflectance spectral data combined with bidimensional spatial information. This combined information will hopefully improve diagnosis and follow-up in a range of skin disorders from skin cancer to inflammatory diseases.

Mots clés: Imaging system; Multispectral images; Hyperspectral cube reconstruction; Neural networks; Spectral reflectance; Skin cancer

Domaines: Traitement du signal et de l'image [eess.SP]; Traitement du signal et de l'image [eess.SP]

Romuald Jolivot, Pierre Vabres, Franck S. Marzani. Reconstruction of hyperspectral cutaneous data from an artificial neural network-based multispectral imaging system. Computerized Medical Imaging and Graphics, 2011, 35, pp.85-88. ⟨10.1016/j.compmedimag.2010.07.001⟩. ⟨hal-00586919⟩