Polyp Shape Recovery from Single Endoscope Image using Medical Suture

Background:Polyp shapes play an important role in colorectal diagnosis. However, endoscopy images are usually composed of nonrigid objects such as a polyp. Hence, it is challenging for polyp shape recovery. It is demanded to establish a support system of the colorectal diagnosis system based on polyp shape.Introduction:Shape from Shading (SFS) is one valuable approach based on photoclinometry for polyp shape recovery. SFS and endoscope image are compatible on the first sight, but there are constraints for applying SFS to endoscope image. Those approaches need some parameters like a depth from the endoscope lens to the surface, and surface reflectance factor . Furthermore, those approaches assume the whole surface which has the same value of for the Lambertian surface.Methods:This paper contributes to mitigating constraint for applying SFS to the endoscope image based on a cue from the medical structure. An extracted medical suture is used to estimate parameters, and a method of polyp shape recovery method is proposed using both geometric and photometric constraint equations. Notably, the proposed method realizes polyp shape recovery from a single endoscope image.Results:From experiments it was confirmed that the approximate polyp model shape was recovered and the proposed method recovered absolute size and shape of polyp using medical suture information and obtained parameters from a single endoscope image.Conclusion:This paper proposed a polyp shape recovery method which mitigated the constraint for applying SFS to the endoscope image using the medical suture. Notably, the proposed method realized polyp shape recovery from a single endoscope image without generating uniform Lambertian reflectance.

Elements of Math and Physics

Concepts and formulas that are generally useful in atmospheric radiative transfer are gathered here for later use. These include units for light wavelengths and frequencies. Optical elements for instrument description and characterization (solid angle descriptions, étendue, and the diffraction limit) are presented. Lambertian reflectance and emission properties are described, and the bi-directional reflectance distribution function, BRDF, introduced.

Evaluation of Satellite Image Correction Methods Caused by Differential Terrain Illumination

The problem due to differential terrain illumination on satellite imagery is experienced by most of areas which are on mountainous terrain. This may cause variations in reflectance of similar ground features which lead to a misclassification of land cover classes due to different topographic positions. This phenomenon most commonly occurred in the areas which are located on southern and northern hemisphere because of the low sun inclination. This problem has been a major interest for researchers to be solved prior to the land cover classification process. For satellite images which experience this kind of problem, topographic correction need to be applied in order to reduce the illumination effects prior to land cover classification process. This research is aimed at conducting topographic correction of multi spectral SPOT satellite data as well as evaluating the three topographic correction methods. They are Cosine which is based on Lambertian reflectance assumption, as well as Minnaert correction and C correction methods which are based on non-Lambertian reflectance assumption. The data used in this study are two scenes of SPOT images of forested mountainous area of Miyazaki Prefecture, Kyushu, Japan. Research steps had been conducted in this study including geometric correction, sample data collection for calculating Minnaert constants and C constants at location which represents the whole study area, topographic correction for two scenes SPOT images, and results analysis. The results show that Cosine method did not show good performance for the study area which is topographically dominated by rugged terrain. Whereas Minnaert method and C method gave satisfactory results as is indicated by the statistical data as well as visual interpretation. However the Minnaert correction method showed slightly better performance than the C correction method.