Image analysis will enable Pathologist to do better what they do. It is better, faster, cheaper, more accurate. Image analysis and tele-consultation have been and will be the two main value drivers for digital pathology. The increase of companion diagnostics for personalized therapies will drive this requirement to both narrow the gap between diagnostics and therapeutics.
Diagnostic review of pathology specimens is based on pathologist’s interpretation and measurements of the tissue.Performing exact measurements is of course not possible, but the existing variation caused by this method of diagnosis poses a challenge.
There is a lack of pathologists in most western countries and so their workload is increasing and this might result in delayed reports or inaccurate report in hurry. When treatment decisions are taken based on these reports it might turn into a terrible risk for the patients. Digital pathology encompasses effective algorithm such that it reduces the variability in pathology result. Many pathologist accept the fact that there are significant improvements in the result when compared to the previous results.
The protocols used introduce an efficient sampling methodology and are designed and implemented to reduce the variability. Few studies have proved the variability caused by using many different protocols.
Some studies have also investigated the preciseness of intuitive eye-balling measurements. Laura et al. found that when eye-balling Ki67 quantification, a significant discordance occurred between 18 of the total 45 observers. This was in contrast to image analysis and manual counting where no significant discrepancy was found .
In conclusion, to reduce variability there is a strong need for new ways of performing quantification according to protocols that eliminate the eye-balling approach.