Studying cytology of the uterine cervix on win '98/NT platform using color image processing and mathematical morphology of shapes: a cancerous cell detection and scoring system

摘要

Cervical Cytopathologists are mainly interested in automatically detecting the abnormal cells (Dysplasia), CIS (carcenoma in citu) and SCC (Squamous Cell Carcenoma) and also its scoring. This paper presents an interative algorithm based on colorimage processing, a combination of morphological algorithms based on shape analysis and finally the connected component analysis for scoring. This system runs on Windows '98/NT PC-400 MHs (Pentium-II) platform, using Visual C++ (6.0) environment in threedifferent architectures: Single document interface, multiple document interface and dialog based applications. The system takes around 1.5 seconds per image of 512×484 square pixels using high speed threading architecture. The system's accuracy is 95%.