Health IT, MedCity Influencers

What are the technology challenges holding back the digital pathology industry?

The digital pathology industry cannot advance unless healthcare organizations develop scalable, secure, and accessible IT infrastructures to support it.

sucess, hurdles

The vision for automated diagnosis of computer-analyzed biopsy images is one that has the potential to drive enormous advances in pathology.

The idea of being able to have a computer supplement the expertise of a pathologist by providing quantification of patterns hidden within a tissue sample is very attractive and can lead to discoveries that change how we diagnose and treat disease. However, the heavy focus on automated image analysis in pathology has veiled many of the fundamental problems that have kept pathology years behind its radiologic and genetic counterparts. Until these challenges are addressed, automated diagnosis and clinical decision support will remain largely irrelevant in the clinical setting.

The problem in pathology is that whole slide imaging — the practice of creating high-resolution full-magnification digital images of tissue that would traditionally be analyzed under the microscope — creates an enormous infrastructure burden for its adopters. A typical whole slide image scanner (the devices used to create digital images from physical samples) can produce 120 digitized images, each of which is many gigabytes in size, in a 12-hour timeframe. To put that into perspective, every day, a lab with a single scanner could easily produce a terabyte of data. With a couple of scanners, we’re talking about petabytes of data every year.

How and where is that data stored? How is it accessed? Can this data be shared easily and quickly without compromising data security? How is this data integrated with the rest of an organization’s cancer information? Until these questions are answered, the broader vision of computer-based diagnostics is largely irrelevant. Why? Because the large-scale implementation of diagnostics depends on consistent, accessible, organized data.

These IT obstacles are made more difficult to address because of the nature of working in the healthcare space. Security is a major concern that complicates the implementation of these systems. Variation in each healthcare organization’s interpretation of security makes it nearly impossible to develop a “standard” solution. There are substantial differences between each organization’s requirements such as how and where data is stored and determining what access permissions are assigned to which individuals under what settings.

Many groups also have specific goals based on their organization structures that influence their ideal IT setup. Academic medical centers with both research and clinical arms have dramatically different requirements than specialized labs or clinics, which also differ from purely research organizations. All of these differences manifest themselves in the struggle to develop solutions that address the inherently challenging big-data problems of taking pathology digital.

Another challenge that’s often overlooked is usability. While it seems somewhat ludicrous that an interface influences the adoption tendencies for medical products, many of the players in the digital pathology market provide a UI from legacy systems that make day-to-day operation of a pathology solution frustrating at best and unusable at worst.

These challenges make developing and implementing diagnostic-type software solutions exceedingly difficult. A good comparison comes from the mobile phone industry. Everybody is looking for the next “killer app” of pathology, but the apps that we’re all hoping for are useless if there isn’t already the hardware and operating system on which they can be developed and operate. Yet many companies in the digital pathology industry continue to focus on developing that “killer app” without giving significant thought to the systems on which these visionary tools might operate.

This model of building for the visionary diagnostic future without regard for the immediate infrastructure results in constant redevelopment and redesign, workarounds and quick fixes, and ultimately haphazard and constantly changing strategies for making this technology usable at scale.

There is, however, hope. As technologies like cloud get less expensive and more functional, both traditional hardware vendors and a few software-solution companies like my own have started the transition away from legacy IT and towards the infrastructure required for broader digital pathology adoption. This renewed focus on scalable, secure, and accessible infrastructure does not distract from the ultimate vision of improving the pathology experience and driving insights from tissue – it drives it forward by providing a platform of these insights, discoveries, and technologies.

Image: Bigstock


Avatar photo
Avatar photo

Nathan Buchbinder

Nathan is a Co-Founder and the Vice President of Operations at Proscia Inc., a Baltimore-based data solutions provider for digital pathology. Nathan is passionate about medical devices, and has worked on the product development, IP, and business development elements of devices in fields ranging from neonatal care, stem cells therapies, emergency medicine, and pathology software. His experience in this industry ranges from organizing small animal studies to product management. Nathan earned his Bachelor of Science degree in Biomedical Engineering at Johns Hopkins University and his Master degree in Biomedical Innovation Development at the Georgia
Institute of Technology.

This post appears through the MedCity Influencers program. Anyone can publish their perspective on business and innovation in healthcare on MedCity News through MedCity Influencers. Click here to find out how.

Shares0
Shares0