Screening for cervical cancer using automated analysis of PAP-smears

Abstract

Cervical cancer is one of the most deadly and common forms of cancer among women if no action is taken to prevent it, yet it is preventable through a simple screening test, the so-called PAP-smear. This is the most effective cancer prevention measure developed so far. But the visual examination of the smears is time consuming and expensive and there have been numerous attempts at automating the analysis ever since the test was introduced more than 60 years ago. The first commercial systems for automated analysis of the cell samples appeared around the turn of the millennium but they have had limited impact on the screening costs. In this paper we examine the key issues that need to be addressed when an automated analysis system is developed and discuss how these challenges have been met over the years. The lessons learned may be useful in the efforts to create a cost-effective screening system that could make affordable screening for cervical cancer available for all women globally, thus preventing most of the quarter million annual unnecessary deaths still caused by this disease.

Figure 1

A typical PAP-smear and a high resolution field of view through a 40x lens. Approximately 10.000 such fields of view are needed to cover the whole slide.

Figure 2

To the left a few normal cells and to the right some clearly atypical, premalignant cells.

Figure 3

Illustration showing the anatomy of a uterus. For specimen acquisition it is important that cells are acquired from both the endocervical and ectocervical regions, that is, both above and below the region known as the transformation zone.

Figure 4

Illustration schematically showing image scanning using one- or two-dimensional sensor arrays. With a 2D array an image or a stack of images at different focus levels are read before the microscope stage moves a few hundred micrometers to a new position where this process is repeated as soon as the vibrations caused by the move have died out. With a 1D array the microscope stage is moving continuously and single lines in the direction orthogonal to the move are read into the computer creating a continuous flow of image data.

Figure 5

Images displaying four common types of artefacts found in PAP-smears. From top to bottom: bacteria, leucocytes, stain residues, and overlapping and folded material.