PathAI Announces 13 Lab Contracts for Its AI Tools

PathAI Announces 13 Lab Contracts for Its AI Tools

PathAI Announces 13 Lab Contracts for Its AI Tools

ePathAI (Boston, MA) has won contracts with 13 lab organizations that will be using its FDA-cleared AISight digital pathology image management and viewer analysis system. These new clients will also be using PathAI’s software algorithm AIM-PD-L1 NSCLC RUO, which quantitates the percentage of PD-L1 positive tumor and immune cells in non-small cell lung cancer samples.

Among the 13 labs that will be using PathAI’s AI-based software algorithms is PathAI Diagnostics (Memphis, TN)—formerly named Poplar Healthcare. PathAI acquired Poplar Healthcare in August 2021 (see LE, August 2021). PathAI Diagnostics is a full-service anatomic pathology lab with 350 employees, including 25 pathologists.

Other labs that will be using PathAI’s software tools include Caris Life Sciences, NeoGenomics and University of Pittsburgh Medical Center (see table below).

These labs will have early access to additional AI algorithms that PathAI expects to bring to market for research use only (RUO) within the next few months. These products include AI software tools for quantitative PD-L1 tests for melanoma, head and neck, and bladder cancer, as well as an
algorithm for the automated quantification of HER2 IHC images in breast cancer tissue.

Labs will have the potential to validate PathAI’s RUO products so that they can be used as lab-developed tests for clinical diagnostics, according to Andy Beck, MD, PhD, Chief Executive of PathAI.

The new clients were all signed by PathAI within the past six months. Beck anticipates more lab client announcements soon. Eric Walk, MD, Chief Medical Officer, and Parth Chodavadia, Head of Commercial, Digital Diagnostics, are leading the marketing efforts at PathAI.

PathAI has raised a total of $255 million since being formed in 2016. Major backers include Labcorp, Kaiser Permanente, Merck and Bristol Meyers, as well as the private equity firms General Atlantic and General Catalyst.

Spotlight Interview with Proscia’s Nathan Buchbinder

Spotlight Interview with Proscia’s Nathan Buchbinder

Spotlight Interview with Proscia’s Nathan Buchbinder

Proscia Inc. (Philadelphia, PA) markets a digital pathology software platform (Concentriq) that helps upload, organize into patient cases, annotate, and store whole slide images. Concentriq is currently being used by more than 6,000 scientists and pathologists at 300+ clinical and research organizations around the world. Proscia has also developed AI-based applications, including a program for quality control of digitized images (currently for the research market only). Here’s a summary of our recent interview with Nathan Buchbinder, Co-Founder & Chief Product Officer at Proscia.

Describe when and who founded Proscia.
Proscia was founded in 2014 by myself and two other computer scientists from Johns Hopkins University and University of Pittsburgh. These include our Chief Executive David West and our Chief Technology Officer Coleman Stavish. We currently have 100 employees.

How much capital has Proscia raised?
We raised $37 million in June 2022 bringing our total funding to $72 million. More than 10 private equity firms have invested in Proscia, including the following that have board seats: Emerald Development Managers, Flybridge Capital Partners, Razor’s Edge Ventures and Scale Venture Partners.

Why were drug development research firms so quick to adopt digital pathology?

Because their return on investment (ROI) on digitizing slides was self-evident and nearly immediate. Ten of the top 20 pharmaceutical companies, including Amgen, Bayer and Bristol Myers Squibb, are using Proscia to help manage their digitized slide images. These companies operate research sites and collaborate with third-party contract research organizations all around the world. Concentriq gives them a single hub where digitized slide images can be accessed and shared.

What’s the current status of digital pathology for clinical diagnostics?
Adoption started much slower in the clinical market. Some of our early adopters, including Thomas Jefferson University Hospitals and Johns Hopkins’ Department of Pathology, initially used digital pathology primarily for research and education.

However, over the past two years, we’ve seen a huge surge in demand from the clinical market, including integrated delivery networks, reference labs and even smaller pathology practices (~5 pathologists). These labs are using digital pathology for peer reviews, conferencing, consults, and tumor boards, as well as primary diagnosis of cancer cases. Most of our customers are in life sciences and research, but that’s quickly changing.

What’s your advice for pathology labs planning to transition to digital pathology?
Number one, get everyone involved at the start, not just executives and pathologists, but lab managers and histotechs. Number two, don’t underestimate the value of having an archive of digitized slides, not only in terms of internal research and education, but also its value to third-
party life sciences and pharmaceutical companies.

What’s your outlook for digital pathology adoption in the United States?
It will be widespread with nearly 100% adoption within five years. Drivers include the new Category III CPT codes for digital pathology and the potential for Medicare reimbursement. In addition, the application of AI, which requires digitized slides, will increase pathologist accuracy and efficiency.

The shift from microscope to monitor will be transformational. Winners and losers will be determined based on how fast and how well they implement technology. It could help the biggest commercial labs gain share in anatomic pathology or result in a different outcome that we can’t imagine today.

Did Digital Pathology Utilization Increase During The Pandemic?

Did Digital Pathology Utilization Increase During The Pandemic?

Did Digital Pathology Utilization Increase During The Pandemic?

The conventional wisdom says that digital pathology use surged as a result of the pandemic. However, Medicare data for CPT 88361 (computer-assisted IHC for breast cancer) tells a different story. The volume of Medicare Part B allowed claims for 88361 declined by 16% to 160,819 in 2020, followed by only a 3% rebound to 165,231 in 2021. CPT 88361 is the only code devoted specifically to bill Medicare for reading digitized slides. It therefore gives an indication of digital pathology trends in the clinical market.

Another indication that the digital pathology market has not taken off during the pandemic is the falling number of pathologists using it. A total of 736 pathologists billed Medicare for CPT 88361 in 2020 (the latest year of available data), which was down from 871 pathologists in 2019. The number of independent labs billing Medicare for CPT 88361 declined from 96 labs in 2013 to 66 labs in 2019 but increased slightly to 69 labs in 2020.

The main barrier, irrespective of the pandemic, to more widespread adoption of digital pathology has been the added expense of digitizing slides without reimbursement. The problem is that digital pathology comes as an “add on” process that is produced from a traditional glass slide. Digital pathology does not eliminate the need to process, section, glass-slide-mount and stain biopsy specimens. A high-end conventional microscope costs between $9,000 and $12,000, while a complete digital pathology
system can cost between $100,000 and $400,000.

In addition, pathologist practice patterns are hard to change, especially without a clear clinical benefit and/or compelling financial incentive.

 Artificial intelligence could be the game changer that jumpstarts the digital pathology market. AI-based decision-support tools that boost pathologist productivity and reduce errors need digitized images to read. AI vendors (PathAI, Paige, Ibex Medical Analytics, etc.) claim their software can help pathologists read 30+% more slides per day. This may provide hospitals and labs with the return on investment necessary to justify an investment in digital pathology scanners.

Did Digital Pathology Utilization Increase During The Pandemic?

AMA Announces New Add-On Digital Pathology Codes

AMA Announces New Add-On Digital Pathology Codes

The American Medical Association (AMA) CPT Editorial Panel has
announced 13 new digital pathology add-on codes effective on January
1, 2023. The new digital pathology Category III CPT codes will be used
to report additional clinical staff work and service requirements associated
with digitizing glass slides for primary diagnosis.

Introduction of the codes will allow CMS to monitor the usage of digital
pathology. However, no relative value units (RVUs) or national payment
rates have been assigned to the new codes.

“It’s an important first step, but widespread use in clinical practice will
need to be demonstrated before the new codes are moved to Category I
and assigned RVUs,” notes Jonathan Myles, MD, Chair of the Council
on Government and Professional Affairs at the College of American
Pathologists (CAP).

The new digital pathology add-on codes are linked with 13 of the most commonly billed pathology procedures, including CPT 88305 (Level IV-Tissue Exam). CAP’s Myles says that the new add-on codes should only be reported when used for clinical diagnosis and not for things like archiving slides, training or validation of AI algorithms, or tumor board conferences. “It’s clear that digital pathology will be a part of the practice of pathology and lab medicine, but it has to be proven to be in widespread clinical use to gain Medicare reimbursement,” says Myles.

Assuming that digital pathology volumes prove to be significant, the very earliest that CMS could  assign RVUs and establish national payment rates for the new add-on codes would be for an effective date of January 1, 2024, notes Laboratory Economics. However, the process is more likely to take at
least a few years. In the meantime, each individual Medicare Administrative Contractor (MAC), as well as private insurers, could establish their own payment rates, but are not required to do so.

Many pathology labs in the United States are experimenting, but very few have gone fully digital, according to Michael Rivers, Vice President and Lifecycle Leader for Digital Pathology, Roche Tissue Diagnostics (Santa Clara, CA). “Digitization is a means to an end. It will allow the application
of innovative AI solutions to pathology images and ultimately integrated multi-modal analysis of patient cases combining anatomic pathology, clinical lab and gene-sequencing data,” says Rivers.

“My prediction is that if the Category III codes are converted to Category I code status, in the future Medicare could potentially reimburse the new add-on codes at roughly 3% to 5% of the global rates for related existing codes,” says Erick Lin, MD, PhD, Senior Director, Medical Affairs, PathAI (Boston, MA). Thus, the add-on code for digitizing one unit of CPT 88305 (current global rate of $72) could be reimbursed at between $2 and $4. The key is for all pathology labs to be aware of the new add-on codes, prepare systems to report, and then begin reporting the new codes effective January 1, 2023. If all clinical utilization is appropriately reported on claims, it can help facilitate Medicare’s establishment of national reimbursement rates, explains Lin.

“Although digital pathology, including usage of AI algorithms, could improve pathologist efficiency, this should not be the sole focus of reimbursement calculations. Digital pathology helps labs and pathologists expand their network of brainpower through greater access to information,
second opinions and subspecialist expertise. This ultimately could lead to optimized diagnostic decision-making and inherently leads to better patient management,” according to Esther Abels, Chief Clinical and Regulatory Officer, Visiopharm Corp. (Westminster, CO) and President of the Digital Pathology Association (Carmel, IN).

BioReference Labs Goes Live With Digital Pathology Plus AI

BioReference Labs Goes Live With Digital Pathology Plus AI

BioReference Labs Goes Live With Digital Pathology Plus AI

OPKO’s BioReference Labs (Elmwood Park, NJ) went live in December with new whole-slide imaging scanners from Leica Biosciences (Buffalo Grove, IL). The scanners have been integrated with a digital pathology solution, PathFlow, made by Gestalt Diagnostics (Spokane, WA). PathFlow is a cloud-based software system that has helped integrate BioReference’s LIS, workflow and scanned slide images with artificial intelligence algorithms developed by MindPeak (Hamburg, Germany). BioReference is also using PathFlow for slide image management and archival storage.

BioReference is using MindPeak’s AI tool (named BreastIHC) to detect and quantify breast cancer cells from digitized slide images with immunohistochemistry at its main laboratory in northern New Jersey. Pathologists can access their case and slide images securely on their computer monitors and use their mouse to outline regions of interest (ROI). All cells within this outlined ROI are instantly classified into positively stained tumor and unstained tumor cells. The panel of algorithms include five key tumor markers (ER, PR, Ki-67, HER2, and P53) which can be counted and scored.

Eventually, Dan Roark, Chief Executive Officer, Gestalt Diagnostics, expects the AI algorithms to both automatically identify the regions of interest in addition to performing IHC marker positivity scoring.

Digital Pathology & AI Market Growth
Separately, Roark says that after more than 10 years of limited adoption, digital pathology is finally starting to take off in the clinical market in the United States. Whole slide scanners have gotten quicker and less expensive. For example, it used to take 8-10 minutes to scan a slide but now takes as little as 30 seconds. But the biggest driver is the pathologist efficiency gains obtained when AI is applied to digitized slides. “The number of RFP requests we receive is exploding,” says Roark.

Worldwide Opportunities for U.S.-Based Pathologists
The U.S. has more working pathologists per capita than most other countries. For example, there are approximately 20,000 actively practicing pathologists in the United States, according to the American Medical Association. This works out to a ratio of one pathologist for every 17,000 people.

CDx Diagnostics Leads In Digital Pathology

CDx Diagnostics Leads In Digital Pathology

CDx Diagnostics Leads In Digital Pathology

CDx Diagnostics (Suffern, NY), which specializes in oral, esophageal, and laryngeal cancer testing, is by far the biggest digital pathology lab as measured by volume of Part B claims for CPT 88361. CDx was paid for 55,082 Part B tests for CPT 88361 (including combined global, TC-only and PC-only claims) in 2019, according to provider utilization and payment data from CMS.

CPT 88361 is used to bill Medicare for digital quantification of HER2, estrogen receptor (ER), progesterone receptor (PR) and Ki-67 for breast cancer. This code can also be used for digital analysis of other cancers, including oral and esophageal cancers.

NeoGenomics has four labs (California, Florida, Michigan and Texas) in the top 25 with a combined total volume of 19,950 Part B allowed tests for CPT 88361 in 2019.

Sonic Healthcare USA has two lab locations (New York and Texas) that performed CPT 88361 with a combined volume of 6,760 allowed Part B tests for CPT 88361.

Overall, Medicare Part B allowed volume for CPT 88361 totaled 191,205 tests in 2019, down 10% from 212,003 tests in 2018.

Swedish Flag