Digital Pathology Blog

Until recently, the practice of pathology has been entirely “human-driven”.  Well-trained pathologists examine all tissues and arrive at diagnoses based on their application of learned criteria and experience.  However, it is well-known that the accuracy of human interpretation can be hampered by subjectivity (inter-observer variability), inconsistency (intra-observer variability), and fatigue. Recently, the rise of digital methods in pathology has led to a growing interest in applying artificial intelligence (AI) to aid or even improve on the analysis of medical specimens.  For the pathologist, AI has the potential to improve accuracy, productivity, and workflow by allowing the computer do what it does well: consume lots of data, recognize patterns, and perform automated analyses.  Objective and reproducible specimen examination, along with certainty  that all material has been “seen,” leads to greater accuracy.  AI can be trained to identify specific features and present them selectively to human observers, leading to prescreening (“guided screening”) of specimens and promising improved workflow and productivity.  And, finally, the “holy grail”: under the right circumstances, AI-driven systems can make novel observations of morphologic patterns in pathology specimens, potentially leading to new knowledge and ultimately computer-generated diagnosis.  In this blog, we describe our general approach to applying AI to digital pathology specimens, detail some of the important steps involved in establishing an AI workflow, and discuss the potential benefits of AI.

The American Recovery and Reinvestment Act (ARRA) 2009 introduced the Health Information Technology for Economical and Clinical Health (HITECH) Act with the aim to incentivize “meaningful” implementation and usage of Electronic Health Records (EHRs) throughout the nation. Under HITECH, two incentive programs for Medicare and Medicaid were introduced which allow eligible professionals (EPs) to claim thousands of dollars in incentives over several years, if they could meet the requirements set out for different stages of Meaningful Use.

In April, the field of digital pathology achieved a major milestone with the FDA giving clearance to Philips Medical Systems to market its whole slide imaging (WSI) system for primary diagnosis. While a significant step forward, there is still much work to be done before digital pathology (DP) becomes a mainstream technology for clinical use. 

Growing up as an avid member of the 60’s TV generation, one of my favorite genres included nature shows. In the years long before YouTube, we often arranged our week to be home in time to watch Marlin Perkins’ Mutual of Omaha's Wild Kingdom on Sunday evenings. And of all the spectacular scenery shown, a very specific type of photography captured my imagination – time-lapse video. 

You’ve seen the same amazing footage.  It begins with a barren desert that looks almost choked off from life, with the exclusion of a few scraggly cacti and perhaps a plodding reptile or two.  Next comes the torrential rainstorm, and a vivid rainbow of breathtaking plants seem to blossom out of nowhere.  Clearly, the stunning display was hiding in place all along.  With the “magic” of time-lapse photography, we are given the rare opportunity to view the entire picture from start to finish.

Telepathology and whole slide imaging have become integrated into pathology laboratories worldwide. With applications in teaching and research well established, it is now recognized that digital pathology has a role in the clinical realm as well. 

Digital pathology provides clear advantages for pathologists’ quality assurance processes and performance evaluations as well as streamlined workflows for consultative expert collaborations and multi-disciplinary tumor boards. With the advancement of artificial intelligence and histopathology analytics, there is no limit to the application of digital techniques to the practice of pathology.

I’ve spent a lot of time in Starbucks, and over the years, it seems little has really changed with the basic operations. The line to the register is flanked by food options and souvenirs leading to someone who takes your order and your money (The Register). Your order moves to someone standing at the espresso machine (On Bar). Other Starbucks associates are simultaneously working the Drive-Thru customers (On Drive-Thru).

Another associate is grinding beans, ensuring the coffee urns are full, teas are brewed, cups, lids and cup protectors are in place, and coolers are well stocked with sandwiches, croissants and breakfast sandwiches (Customer Support).

So, who has the most important job at Starbucks? The Register? On Bar? On Drive-Thru? Customer Support?

My grandfather was born on Groundhog Day in 1915. If he had not passed away 10 years ago, he would have been 102 this year. Given what he ate, drank and smoked, it is a miracle he lived as long as he did. When I was about 8 or 9 years he told me to “Never bet against Notre Dame football, Joe Louis or the New York Yankees”. Today he would have to replace the entries on that list with, among others, the New England Patriots.

During this year’s game, how many people went to Netflix or their e-book reader half way through the third quarter? I tweeted that, apparently, the balls were harder to catch when fully inflated and “Go Patriots!”

Liquid biopsy is defined as, “A test done on a sample of blood to look for cancer cells from a tumor that are circulating in the blood or for pieces of DNA from tumor cells that are in the blood. A liquid biopsy may be used to help find cancer at an early stage. It may also be used to help plan treatment or to find out how well treatment is working or if cancer has come back. Being able to take multiple samples of blood over time may also help doctors understand what kind of molecular changes are taking place in a tumor.”*

Often times the test is regarded as “non-invasive” as it can be performed with simple venipuncture specimens or voided urine samples.

These tests are gaining traction within the industry as a viable alternative to traditional screening methods for cancer. Study results are turning up positive data in favor of the tests, and a recent report by financial services firm Cowen & Co. said annual sales for the tools could surpass $10 billion.

Regardless of your politics or mine, on January 20th a new administration will assume leadership of our country. A few months ago, if you told me I would be hearing “The Cubs won the World Series” and “Donald J. Trump will be our next President,” I would have thought the likelihood of either or both happening would be unlikely. It has been quite seachange of events since November. Although too early to think about the next election process, I am predicting the Cubs to win the World Series in 2017.

In the pre-PowerPoint era of the 1980s, armed with a carousel filled with 35mm slides, I traveled the country giving an introductory presentation on ploidy and cell cycle analysis. We now lightheartedly refer to this period as my “What’s a pixel? talk” years. To create the slides, I sketched out the layout for each on a sheet of copy paper, and then faxed them to Houston where a delightful gentleman named Jim would magically create the Kodachromes. This usually involved a phone call or two to talk about colors and fonts, following which Jim would mail the slides to me a week or two later.