Visualization and Navigation Platform for Co-Registered Whole Tissue Slides

Abstract

The routine use of digital pathology by clinicians is just beginning to grow rapidly. This adoption will be accelerated by new software applications that increase pathologists’ productivity and quality of work. Increasingly specific stains are available to better diagnose diseases such as cancer. Pathologists are confronted with growing complexity when correlating images from differently stained tissue sections. Here traditional microscopy, which generally allows local viewing of only one image at a time, reaches its limits. Digital pathology can offer tools to facilitate such tasks when assessing complex cases. In this contribution we present a visualization and navigation platform prototype. The basic viewing functions are implemented in a style analogous to Google Maps. The principles of meaningful navigation, however, are based on two sophisticated image analysis types. Firstly, the user interface is designed to intuitively handle panels of automatically co-registered whole-slide images; secondly, heat maps – the result of quantitative image analysis – help the user to quickly navigate to the relevant regions. Under the assumption that the general image analysis challenges can be met robustly, this prototype was used to collect feedback from more than ten pathologists and to analyze how they operated the system. These results are the basis for product development requirements for clinical pathology applications.