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.

Methods for rapid and high quality acquisition of whole slide images

“…There are also many foreign objects such as blood cells, mucus and inflammation. Nevertheless, this traditional preparation method is simple and cheap, at cost of around 1-2 US dollars (Bengtsson and Malm 2014).…”

“…This is generally achieved by converting the analogue signals (light intensities) into digital images and then quantitatively measuring and interpreting these digital images utilising computer based image processing techniques. For instance, the area ratio of nuclei and cytoplasm for diagnosis of the cancer can be obtained by using cells and nuclei segmentation and feature extraction techniques, and used as a feature to classify the abnormality of the specimen (Bengtsson and Malm 2014).…”

“…The consistent appearance of specimens is an essential step for quantitative evaluation required by the computer aided screenings. The only downside to the LBC preparation methods is associated with its cost because more material like preservative liquids and filters are required as well as complex and expensive slide preparation machines, thus increasing the cost of making a slide to multiple times that of traditional pap smear slides (∼10 US dollars versus 1-2 US dollars) (Bengtsson and Malm 2014).…”

“…The SurePath LBC preparation method mentioned above was developed to further improve the FPSP system performance. In 2003, another automated screening system, ThinPrep Imaging System (TIS) (Hologic Inc., Boxborough, MA), was approved by the FDA; it uses the Thin-prep preparation method (Bengtsson and Malm 2014). The technical details of these two systems are described as follows: FocalPoint Slide Profiler: The FocalPoint Slide Profiler is able to process both conventional PAP smear slides and SurePath LBC prepared slides.…”

“…For scanning cervical cytology specimens, the digital slide image should be at multiple focal planes (as three-dimensional (3D) image stack), at a spatial resolution close to the light diffraction limit (∼0.25µm/pixel) and free of optical aberrations (Bengtsson and Malm 2014). Conventionally, microscopes with high magnification objectives (normally 40×, with an air objective, i.e., the medium between the objective and microscope slide is air) are required in order to interpret subtle diagnostic details in the specimen, such as the texture of cell nuclei.…”