Digital pathology for primary diagnostic use

July 25, 2017

In April 2017, marketing of the first whole slide imaging system for digital pathology was allowed for primary diagnostic use in the United States.This system allows for review and interpretation of digital pathology images prepared from general surgical pathology tissue. It is a groundbreaking moment for the industry. The clinical lab is at the crossroads between the old way of doing pathology and the new way: digital pathology and the new field of computational pathology.

Pathology at a turning point

With the number of cancer cases growing in the U.S., increasingly limited resources, and a heavy industry-wide focus on delivering personalized medicine, pathology services are under great pressure to provide quality analyses quickly. This trend is not expected to slow either, as new cancer cases are projected to rise nearly 70 percent to 22 million within the next two decades.1 The number of tests applied per case, which directly correlates to the complexity of the pathologist’s workload, is also increasing to accommodate the information requirements of personalized medicine.

At the same time, the pathologist workforce is diminishing, with AAMC reporting2 an 11.3 percent drop in the number of active pathologists between 2010 and 2015. Additionally, 63.2 percent of active pathologists are age 55 or older, signaling a potential workforce crisis as the majority of pathologists will likely retire in the next decade. To address these challenges, the industry must sustain and add value to the vital service that pathology provides to healthcare and, in particular, to cancer care.

Digital technology amplifies expertise

Pathologists must work as efficiently and effectively as possible to analyze the complex information that influences the design of personalized treatments. Digital technology has already proven that it can drive innovation in healthcare, and now it has the potential to open up a new dimension for pathology services through the use of digital pathology.

Essentials of digital pathology

  • Digitize your workflow. Organize and review a large number of histopathology cases quickly and with ease.
  • Connect your team. Connect people and locations, so specialized histopathology resources can be shared.
  • Unify patient data. Integrate and aggregate cross functional views of a patient’s clinical work-up.
  • Gain new insights. Enable research analysis of large sets of clinical data.

Digital pathology aims to reduce the pressure on pathologists by streamlining workflow, sharpening diagnostic processes, facilitating partnership, and enabling collaboration regardless of location. A full digital workflow in histology addresses the inherent issues of distributing and archiving glass slides, meaning pathologists no longer need to worry about the difficult logistics involved in sending glass slides, nor run the risk of losing or damaging specimens.

Digital pathology could have immediate implications for patient care as well: the digital workflow could eliminate issues with handling materials and could detect abnormalities as they occur, ensuring a more comprehensive and quantitative quality control process. Moreover, pathologists spend 13 percent of their time performing administrative tasks that could be done by digital technology. The application of this technology could increase productivity by up to 18 percent because it eliminates time-consuming analog tasks, reduces costs, and enhances lab performance.3

While institutions across the globe have already been benefitting from digital pathology, until April digital pathology could only be used in the U.S. for research. Now pathology slides prepared from formalin-fixed paraffin embedded (FFPE) tissue are available.

An automated digital pathology solution

The currently available digital pathology solution is an automated image creation, management, and review system that can be used as an aid to the pathologist for primary diagnosis. The technology can support pathologists to review and interpret digital images of surgical pathology slides prepared from FFPE tissue. The system is comprised of an ultra-fast production scanner, an image management system, and display. It has advanced features to manage the scanning, storage, presentation, and sharing of information.

In assessing this solution, data from a clinical study of approximately 2,000 surgical pathology cases4 showed sufficient scientific evidence that the device is non-inferior to the microscope. This was one of the largest studies ever conducted to compare the use of digital pathology to optical microscopes. Sixteen pathologists at four clinical study sites conducted approximately 16,000 reads across 2,000 cases.

The use of this digital pathology system allows for reimbursement of primary diagnostics, which is the bulk of high volume and networked pathology laboratories. With the demonstrable benefits of digital pathology, more U.S. labs will likely go 100 percent digital in the near future. In doing so, they will join clinical pathology laboratories outside of the U.S. that have completed their transition to full digital histology diagnosis—including LabPON in the Netherlands, AZ St-Jan in Belgium, Hospitals Granada in Spain, Hall im Tirol and Innsbruck in Austria, Idexx globally, and Finn in the UK.

Deep learning technology

While this is certainly an important milestone for expanding the use of digital pathology, digitization is not the end game—it’s simply the first step. Where digital pathology enables more efficient workflows, computational pathology will take the field one step further, allowing pathologists to use digital images in different and more efficient ways. In the future, smart image recognition algorithms could help streamline pathologists’ workflows and help them to focus on the things that matter most. Two examples:

  • A standard prostate cancer biopsy procedure gathers eight to twelve separate biopsies, which results in multiple slides. The majority typically do not contain cancer. Studies at Nijmegen University, the Netherlands, show that deep learning techniques have the potential to significantly streamline the histopathological analysis if the algorithm can automatically exclude the normal slides without rejecting any containing cancer. It is estimated that up to 32 percent of slides could be confidently excluded in this way from further review.5
  • Identifying the presence or absence of cancer in lymph nodes is a routine and critically important task for a pathologist. However, it can be extremely laborious using conventional methods. Research at Harvard Medical School and Massachusetts Institute of Technology indicates that pathologists supported with computational tools could be both more accurate and faster.6

The first WSI device available for the U.S. market signifies innovation in pathology services by promoting increased efficiencies and collaboration between pathologists and answering some of the industry’s toughest challenges. It also opens the door for a completely new, computational dimension of pathology that could help improve diagnosis and
patient care.


  1. National Cancer Institute. Cancer statistics.
  2. AAMC. 2016 Physician Specialty Data Report: Executive Summary.
  3. Stratman C, Drogowski L, Ho J. Digital pathology in the clinical workflow. [Power point presentation]
  4. Philips Media.Multi-center clinical validation study by Philips to be submitted to FDA in support of expanded indications for use for Philips IntelliSite Digital Pathology Solution in the U.S.
  5. Litjens G, Sánchez CI, Timofeeva Net al. Deep learning as a tool for increased
    accuracy and efficiency of histopathological diagnosis. Sci Rep. 2016;6:26286.
  6. Wang D, Khosla A, Gargeya R, Irshad H, Beck A. Harvard Medical School (BIDMC) and Massachusetts Institute of Technology (CSAIL). ISBI Challenge on cancer metastasis in lymph node.

Russell Granzow serves as General Manager of Philips Digital Pathology Solutions, provider of Philips IntelliSite Pathology Solution.