PathPresenter is a web-based platform, built by academic pathologists whose passion is to educate, promote collaboration, and provide the best educational environment using state-of-the-art technology.
The platform allows uploading digital slides from all major whole slide scanners. It also accommodates the uploading of radiology DICOM images and various other document file types.
The core education platform provides free access to more than 35,000 whole slide images (WSI), encompassing every specialty in pathology. PathPresenter allows integration of a plethora of data to use for education, research, and patient care.
A WSI Web Viewer has been implemented by VISILAB. The viewer allows upload and visualize images from different proprietary formats as well as DICOM including. The Viewer include annotations tools and it is a useful tool for Digital Pathology.
A library to convert all type and formats of whole slide images (WSI) into DICOM format to be used in digital pathology has been developed by SAS-SESCAM group. This converter has been demonstrated in the showcases “DICOM Digital Pathology Connectathon”, that took place in San Diego, CA, in October, 2017 and Helsinki, May 2018. The converter was showed together with the above mentioned viewer. The entire system was successfully interoperable with several slide scanners and PACS systems from other manufacturers.
ANGIOPATH is a morphometric tool allowing us to measure different aspects of the shape and size of vascular vessels in a complete and accurate way. The tool detect and close all vessels providing useful parameter for angiogenesis research. The method is fast and accurate improving existing tools for angiogenesis analysis. ANGIOPATH is a standalone software, used in different research studies.
To experiment human computing in digital pathology images, UNIUD developed a crowsourcing application hosted by one major crowdsourcing site. The application can be used to collect a number of human evaluations of immunohistochemical nuclear markers and aggregate them to obtain a possibly reliable result, according to crowdsourcing principles. The application has been successfully tested on MIB1 stained breast cancer images, with very high correlation vs. expert evaluation (doi: 10.1186/1746-1596-9-S1-S6). While unlikely usable in clinical routine, crowdsourcing might provide a fast lane to image evaluation in research contexts.