Intelligent systems for computer-assisted clinical endoscopic image analysis

The importance of computer-assisted diagnosis in endoscopy is to assist the physician in detecting the status of tissues by characterising the features from the endoscopic image. Due to the complex nature of clinical manifestations, employing a single "feature" technique to detect different abnormalities may not necessarily yield accurate results. In this paper schemes have been developed to extract new texture features from the texture spectra in the chromatic and achromatic domains for a selected region of interest from each colour component histogram of endoscopic images. The implementation of an advanced neural network scheme and the concept of fusion of multiple classifiers dedicated to specific feature parameters have been also adopted in this paper. The endoscopic images used in this study have been obtained using the new M2ATM Swallowable Imaging Capsule - a patented, video colour-imaging disposable capsule. The detection accuracy of the proposed system has reached to 100%, providing thus an indication that such intelligent schemes could be used as a supplementary diagnostic tool in endoscopy.