Identifying precursory cancer lesions using temporal texture analysis

Abstract

This paper describes a method for the temporal analysis of texture in colposcopy. The objective is to find temporal texture patterns in order to detect precursory cancer lesions analyzing colposcopy video frames. Preprocessing of the frames is necessary in order to deal with patient movement and non uniform illumination. We use a stabilization algorithm based in a homography and to eliminate incorrect transformations between frames. Illumination correction is done using a local pixel transformation based in the mean around a small window. Temporal reaction after acetic acid application in the cervix is evaluated through the use of a co-occurrence matrix in different regions of the cervix. The reaction is plotted and analyzed through time. Different patterns for normal and abnormal regions are found by this temporal texture analysis showing the possibility to detect important lesions. The proposed method uses standard colposcopy equipment and it was tested using sequences obtained from different patients.