Spectral Spatial Variation

Automatic carcinoma detection from hyper/multi spectral imagesis of essential importance due to the fact that these images cannot be presented directly to the clinician. However, standard approachesfor carcinoma detection use hundreds or eventhousands of features. This would cost a high amount of RAM (random access memory) for a pixel wise analysis and would slow down the classification or make it evenimpossible on standard PCs. To overcome this, strong features are required. We propose that the spectral-spatial-variation (SSV) is one of these strong features. SSV is the residuumof the three dimensional hyper spectral data cubeminus its approximation with a fitting in a small volume of the 3D image. By using it, the classification results of carcinoma detection in the stomach with multi spectral imagingwill be increase significantly compared to not using the SSV. In some cases, the AUC can be evenas high as by the usage of 72 spatial features.