Royal Philips has partnered with a pathology lab in the Netherlands called LabPON to create the largest digital pathology database of annotated tissue images in the world.
Using the database, the partners hope to develop deep learning algorithms to inform future tissue assessments.
“Deep learning focuses on the development of advanced computer programs that automatically understand and digitally map tissue images in considerable detail: The more data available, the more refined the computer analysis will be,” Peter Hamilton, group leader of image analytics at Philips Digital Pathology Solutions, said in a statement.
Special-Pricing Available on Medical Displays, Patient Monitors, Recorders, Printers, Media, Ultrasound Machines, and Cameras.This includes Top Brands such as SONY, BARCO, NDS, NEC, LG, EDAN, EIZO, ELO, FSN, PANASONIC, MITSUBISHI, OLYMPUS, & WIDE.
Deep learning algorithms have the potential to to improve the objectivity and efficiency in tumor tissue diagnosis. A May 2015 research review published in the journal Nature revealed that using these algorithms for image analysis can surpass human performance for various tasks.
Philips and LabPON will utilize the IntelliSite Pathology Solution to aggregate sets of annotated pathology images and big data. This will provide pathologists with the information they need to develop image analytics algorithms for computational pathology and pathology education.
LabPON will contribute its repository of approximately 300,000 whole slide images that it generates each year to the database. These images comprise a broad range of tissue and disease types as well as other diagnostic information that’s needed for deep learning.
While the role of the pathologist will remain vital for making the definitive diagnosis, the software tools will help with part of the work — including identifying tumor cells, perineural and vaso-invasive growth, counting mitotic cells and measuring more precisely.
Philips plans to make the database available to research institutes and other partners through its translational research platform.