<title>Morphological feature detection for cervical cancer screening</title>

Abstract

An optoelectronic system has been designed to pre-screen pap-smear slides and detect the suspicious cells using the hit/miss transform. Computer simulation of the algorithm tested on 184 pap-smear images detected 95% of the suspicious region as suspect while tagging just 5 % of the normal regions as suspect. An optoelectronic implementation of the hit/miss transform using a 4f Vander-Lugt correlator architecture is proposed and demonstrated with experimental results.

Investigation of fluorescence lifetime imaging for quantitative cervical cancer screening and diagnosis

“…Five dyes are involved in a classic Pap stain [131]: haematoxylin stains cell nuclei crisp blue to black, orange G stains keratinizing cells yellow, eosin Y stains superficial squamous cells orange to pink, light green SF yellowish stains the cytoplasm of all other cells turquoise green to blue and bismarch brown stains nothing and is often neglected. Morphological criteria are conventionally being used to detect the presence of precancerous cells from the smear samples [132].Squamous cell carcinomas represent most cases of cervical carcinomas and are classified by a three-tier (CIN) or two-tier (Bethesda) cytological grading systems[133].…”

“…In addition, the number of neoplastic cells is very small as compared to normal cells. A typical LBC slide could have nearly 100,000 cells and more than 90% of the cells are normal[133]. It is therefore a challenging task to search for the small number of precancerous cells for diagnosis.…”