Classifying cervix tissue patterns with texture analysis

摘要

This paper presents a generalized statistical texture analysis technique for characterizing and recognizing typical, diagnostically most important, vascular patterns relating to cervical lesions from colposcopic images. The major contributions of this research include the development of a novel generalized statistical texture analysis approach for accurately characterizing cervical textures and the introduction of a set of textural features that capture the specific characteristics of cervical textures as perceived by human. Experimental study demonstrated the feasibility and promising of the proposed approach in discriminating between cervical texture patterns indicative of different stages of cervical lesions.