Requirement  of  an Automated system for primary screening cervical smears

In 1984 the International Academy of Cytology defined the requirements

1. the system  must not pass as negative any sample that contains malignant cell
2. the system should be able to detect artifacts and identify infectious organisms such as trichomonas vaginalis and candida species

Current requirements are more modest. They are :

1. The system  should  to select suspicious cells (or slides) and present them to the cytologist for final classification
2. Smears excluded from  human evaluation should not contain abnormalities at a rate exceeding that acheivable with primary manual screening.
3. that the system should be able to comment on smear adequacy, scanning should be rapid and reliable and reproducible.
4. the system should not exclude Pap stained smears suitable for classification
5. the sensitivity of the automated device (plus the cytologist) should equal or excede the sensitivity of the =primary screener (ie 95% sensitivity for HSIL).
   

Tasks required of the computer to detect recognise
and classify  relevant cells in cervical smears

In order to ensure the detection , recognition and classification of relevant cells in the smear the computer is required to perform a number critical tasks

1. Load a slide onto the  motorised microscope stage
2. Find a starting point for scanning and proceed to scan the slide in a predetermined way
3. Find objects of interest and determine their focal plane
4. Detect cervical epithelial cells from among other objects on the slide
5. Label each epithelial cell  and define its  boundaries and recognise nucleus and cytoplasm (a process known as segmentation)
6. -Extract diagnostic features of the nucleus eg chromatin content and structure and cytoplasm (over 100 geometric or texture features may be extracted)
7. Eliminate irrelevant cells, debris, artifacts, overlapping  and touching cells
8. Finally classify the cells as  normal or abnormal

Requirements of image analysis systems

Many of the early automated devices relied entirely on  image analysis of the smear on a cell by cell basis using an algorithmic (rule based) computer software programme. This approach failed initially largely because insufficient  computer power to process the huge computational load required for the analysis of a cervical smear in this way.

A recent development in computer technology for the automation of cervical screening has been the introduction of  artificial intelligence systems of image processing  into the automated analysis of cervical smears. These systems include neural  network systems which represent a non algorithmic branch of artificial intelligence which is particularly  suited to recognising  patterns in natural scenes and as such is particularly appropriate for the analysis of cervical smears where much of what the screener recognises as abnormality cannot be precisely defined in purely objective or morphometric terms. However, in contrast to the algorithmic programmes, neural networks are rather slow.

The current commercial automated systems utilise both  algorithm  based and  artifical intelligence programs for the analysis of cervical smears