Leading pathology’s technology transformation
Eye on Innovation
Eye on Innovation features exciting advances taking place at Mayo Clinic Laboratories. This monthly series shines a spotlight on recently developed tests and highlights how Mayo Clinic translates ideas and discoveries into testing resources that improve diagnosis and care for patients across the globe.
At its core, the practice of pathology rests on a physician evaluating and interpreting what he or she sees on a slide and — based on training, expertise, and experience — making an accurate diagnosis. Jason Hipp, M.D., Ph.D., knows the value of the deliberate assessment and critical thinking that pathologists bring to each case. And he’s looking to enhance their ability to focus on that aspect of care, while relegating the granular and sometimes tedious work that also is a crucial component of pathology to tools better suited to those tasks.
“We want cases prepared for the pathologist, so they can leverage their expertise to do the clinical assessment — not strain to look at tiny features, or count items, or do other repetitive tasks that a computer can do,” he says. “We want pathologists to use their clinical judgement that integrates the context in the patient’s case with all the other variables we need to consider. We want to take those lower-level tasks off the pathologist’s plate, so they can do the pure pathology that only humans can do.”
Jason Hipp, M.D., Ph.D.
Dr. Hipp is eager to make that happen as he assumes the role of chair for Computational Pathology and Artificial Intelligence (AI) — a new division within Mayo Clinic’s Department of Laboratory Medicine and Pathology. He’s also the director of Digital Innovation for Mayo Clinic Laboratories, a newly established role that places him on the leading edge of the technology transformation taking place in pathology today.
Dr. Hipp is particularly interested in machine-learning algorithms, which can identify patterns in vast amounts of data. “An individual pathologist can’t look at every lymphocyte or tumor cell on every slide and calculate its size and evaluate all its characteristics, but an algorithm can do that easily. We want to take advantage of that ability.”
He continues: “An algorithm can be built to look at every pixel in thousands of digital pathology images — a billion pixels in each,” he says. “It can identify information embedded in those images that the human brain cannot cognitively comprehend, and it can learn the patterns, thus reliably answering the question, ‘Does it look like this or this?’ That will allow us to do pathology on a scale that is unheard of now.”
But it’s not enough to have the tools alone. Dr. Hipp envisions a new type of physician who has a clear understanding of the technology, and its power and potential for pathology. “We need clinical data scientists. It’s a new hybrid where pathologists are either trained or have extensive experience in data science, or data scientists have clinical experience,” he says.
“In computational pathology, digital medicine, and AI, we must build a bridge from computer science to the practice of pathology. There’s a huge gap there that needs to be filled.”
The tools and expertise, however, don’t truly add value in health care unless they can make a difference for patients. Many projects and studies related to computational pathology and clinical informatics have been implemented and their findings published, but few have arrived at the bedside. Dr. Hipp sees Mayo Clinic as the organization to change that.
“There are many high-profile publications and journals describing this technology and detailing the research. But how many patients are benefitting in their treatment as a result of this technology? That’s not happening yet,” he says.
“Mayo Clinic has always excelled at translating new discoveries into clinical applications. It has done that throughout its history. Now we need to do it digitally. That’s what drew me to this role. Mayo Clinic has decided to build and create the future in this space for the benefit of patients.”
Dr. Hipp envisions a time when pathology technology allows for faster, more reliable diagnoses, not only for patients at Mayo Clinic, but for people throughout the world.
“A pathologist can perform at a subspecialty level by using these algorithms, which is unheard of. At Mayo Clinic, we have subspecialists, so that’s not as much of a game-changer here. But look at pathologists in rural areas or in underserved countries,” Dr. Hipp says. “In Africa, there’s often one pathologist in an entire country. This is going to impact community hospitals around the world in a significant way, and that’s where most patients get their diagnoses — in the communities where they live. When you think globally, and we should because that’s Mayo Clinic’s reach, we want to empower everyone.”
Since March 2019, Paul Jannetto, Ph.D., director of the Metals Laboratory at Mayo Clinic, along with his colleagues across the enterprise and his laboratory staff, have developed, validated, and implemented an artificial intelligence (AI)-augmented test with algorithms designed to interpret kidney stone FTIR spectra. With more than 90,000 kidney stones analyzed each year at Mayo Clinic, this new AI-assisted test has streamlined lab processes and improved patient care.
Almost four years ago, Mayo Clinic launched the Digital Pathology Program, a major pathology initiative. Phase 2 of this multi-phase rollout has recently been completed, which involved the implementation of cutting-edge digital equipment and software, and converting glass slides of patient samples into digital images. The conversion enables pathologists and laboratory technologists to view, store, retrieve, and share medical images more universally, without waiting for glass slides to be retrieved and delivered. This has significantly improved patient care because pathologists can now discuss cases with clinicians and surgeons in real time.
Since March 2020, the COVID-19 pandemic has had a lasting impact on the lives of millions of people around the world, including the many brave health care workers who risked their own health to provide lifesaving care to those infected by the virus. That care was made possible, in part, by the lasting impact that the pandemic has also had on laboratory testing.