Mosaicing of medical video-endoscopic images: data quality improvement and algorithm testing

This conlribution deals with the construction of a cartography of the internal surface of organs based on image sequences acquired during clinical video-endoscopic exams. This paper describes a metrological approach to adapt the images acquisition conditions and the pre-processing tools to the evaluation of our specifically developed registration and mosaicing algorithm. A 3D-micrometric positioning system and an endoscope's tip holding structure was used to acquire sequences of images following a specific protocol. Forty images of a test scene (bladder planar photography) were acquired along a determined displacement looped path. An algorithm for correcting non-linear radial distortion caused by the endoscope was implemented. This algorithm computes projective (camera) and polynomial (distortion) transformations. The optimization process regislers the corrected distorted pattern image with the non-distorted one. Mutual information was used as a measure of similarity and stochastic gradient descent method for optimization. The visual quality of the images was then improved by a shading correction and by removing the optical fibers pattern from the images (specific low-pass filtering). A low-pass filter was used for obtaining the background that is subtracted from every image. The registration algorithm based on mutual inrormation as similarity measure and stochastic gradient descent as optimization method was used to obtain the transformation parameters that were applied to the images for building a mosaic (cartography). Finally, these parameters were applied to a similar sequence of images of a dots pattern (in place of the photography) allowing us to compute significant error parameters for the quality of the mosaicing. The results of the various processes are presented and the evaluation of the performancc of the cartography is discussed.