Media backgrounder - Philips digital pathology

March 18, 2010

At the United States & Canadian Academy of Pathology 2010 annual meeting (March 20-26, Washington DC, USA), Philips will present a prototype pathology slide scanner and associated image management system as works-in-progress.


Radiology and pathology are cornerstones of cancer diagnosis, the former allowing tumors to be accurately located and biopsied and the latter providing confirmation of their malignancy. Radiology has already ‘gone digital’. Without that process having taken place, many of today’s computer-aided imaging modalities would not be possible. Today, radiologists are just as comfortable looking at radiology images on computer screens as they are examining a conventional film X-ray on a light box. However, the same cannot be said for the world of pathology.


As part of their current practice, pathologists examine tissue slices, mounted on glass slides and treated with appropriate stains, through a microscope. Preparing the slides and getting them to the pathologist, as well as the pathologist’s interpretation procedure, are all time-consuming processes. Accurate interpretation, which is critical to the best outcome for the patient, requires a great deal of skill and experience. At the moment, few tools exist to accurately quantify features of the images that pathologists see through their microscopes.


Increased demand
As part of its holistic care cycle approach to cancer care, Philips has explored many unmet needs in oncology. One of these is the ever-increasing demand for anatomic pathology-based diagnosis. The demographic shift to larger numbers of people in older age-groups means that there will be more people suffering from disease, much of it cancer. In addition, today’s high levels of obesity will expose a greater proportion of the population to the risk of cancer at an earlier age. On top of these factors, today’s complex mix of novel and proven therapies increasingly requires pathology data that targets the right therapy for the right patient at the right time (personalized medicine). However, the increased demand for pathology services is not currently being matched by the supply of skilled pathologists, who remain a scarce resource in most parts of the world. There is therefore a real need for technology that improves the efficiency of pathology labs while also improving the quality of diagnosis.


Going digital
As has already been the case in radiology departments, the solution may lie in the digitization of pathology images, not only so that they can be more easily stored, retrieved, viewed and distributed but also so that image analysis software can be employed to help pathologists quantify what they see.



Glass slide in prototype slide scanner


Philips’ integrated solutions for digital pathology will be designed to accomplish all of these objectives. They leverage its existing expertise in medical radiology imaging (e.g. X-ray and CT scans) and its expertise in radiology Picture Archiving and Communications Systems (PACS).


To capture the images, Philips is developing a slide scanner in close collaboration with leading pathology departments to ensure that it meets the requirements for a seamless fit into existing workflows. This includes the need for an intuitive user interface and a high level of automation. Furthermore, with its total slide handling and imaging time of less than 50 seconds per slide, plus the ability to pre-load up to 300 slides, the scanner will be designed to meet the high throughput requirements of pathology departments. The scanner will feature 40x optical magnification and a high-resolution image sensor, as well as dynamic autofocus techniques (originally developed by Philips for Blu-ray Disc players) to follow the contours of tissue slices, which are never perfectly flat.


Even though a pathology slide is relatively small (typically 1.5 cm x 1.5 cm), imaging tissue samples at the necessary resolution requires hundreds of millions of pixels and generates typical file sizes of around 10 GB per image (at 40x magnification).  Therefore, pathology image management systems must be designed to efficiently store, retrieve and view these large digital image files. To meet this requirement, Philips’ system will be designed to handle data rates as high as 500 MB/sec. The company’s proprietary iSyntax image viewing technology will enable rapid panning and zooming for homing in on and viewing fine detail. The system will also include image analysis software for feature recognition and quantification. Furthermore, supporting information such as patient data and radiology images can be fed into the prototype system to produce a comprehensive overview.


Improving efficiency
Digitization of pathology images may also open up new ways of working to further improve the efficiency of pathology services. For example, seeking the expert opinion of external specialists may no longer involve physically sending slides to them. It may also no longer be necessary to locate pathology lab technicians and pathologists alongside one another in the same facility. The ability to rapidly communicate images between facilities could even allow the setting up of distributed pathology services based around virtual networks.


Future collaboration
Philips is currently working with leading pathology departments to evaluate the technical feasibility of the system. In order to fully exploit the benefits of digital pathology, there is still much to be done. For example, no industry standard comparable to DICOM (Digital Imaging and Communications in Medicine – a standard for handling, storing, printing and transmitting information in medical imaging), currently exists for digital pathology images.


Philips therefore welcomes partnerships with organizations that can help to develop such standards. It is also actively seeking collaborations with companies that specialize in histological stains, staining techniques and other histopathology procedures in order to further develop the system – for example, to develop associated image analysis and clinical decision support tools.