Article

Computational pathology as the next generation of companion diagnostics

Published on 20 Nov, 2026 | 10 min read
illustration of human and robot

Key takeaways

  • Understand the transition from manual, semi-quantitative scoring methods to computational pathology solutions
  • Identify the inherent limitations and sources of variability in traditional manual biomarker scoring
  • Evaluate why computational pathology is essential for accessing future therapies where clinical benefit is tied to complex, non-visual biomarker outputs
  • Understand the current regulatory landscape for companion diagnostics
  • Examine a real-world case study and discuss emerging trends that will shape the future of oncology and pathology
Computational Pathology as the Next Generation of Companion Diagnostics

Computational pathology as the next generation of companion diagnostics: what pathologists need to know (01:03:12)

For decades, companion diagnostics have relied on visual IHC scoring. Manual biomarker scoring is reaching its limits—future targeted therapies may respond to gradients of expression the human eye cannot reliably resolve at scale. Computational pathology may redefine companion diagnostics and the evolving role of the pathologist.1

Join three Roche experts—a pathologist, an algorithm development lead, and a regulatory affairs lead—for a 60-minute panel discussion.

Hosted and moderated by Dr. Aleksandra Zuraw, DVM, PhD, DACVP—Founder, Digital Pathology Place.

Speech Bubble Icon

Contact us

Do you have questions about our products or services? We’re here to help. Contact a Roche representative in your region.

Section 1: Overview
Introduction (2:50)

Provides an overview of the webinar goals, speakers, and how computational pathology may redefine companion diagnostics.

Section 2: CDx Landscape
CDx landscape (7:17)

What does the companion diagnostic landscape look like today — what data are we using and how is it being scored?

Section 3: Current CDx Limitations
Current CDx limitations (6:46)

Where does the current companion diagnostic model begin to reach its limitations?

Section 4: CDx vs. Traditional AI tools
CDx vs. traditional AI tools (7:21)

How does a computational companion diagnostic differ from assistive or computer-aided AI tools? 

Section 5: Future of Personalized Oncology
Future of personalized oncology  (4:17)

Why does personalized oncology now require higher-resolution biomarker measurement? 

Section 6: What is a computational pathology CDx?
What is a computational pathology CDx? (10:13)

What is a computational pathology–based companion diagnostic?

Section 7: Future CDx Requirements
Future CDx requirements (5:54)

Why is computational pathology no longer optional for certain companion diagnostics? 

Section 8: Role of the Pathologist
Role of the pathologist (7:05)

What is the role of the pathologist in a computational companion diagnostic workflow? 

Section 9: Lab Considerations
Lab considerations (6:32)

What must laboratories consider if computational companion diagnostics become routine?

Contributors

Roche-Hochhaus - Ansicht Südwest - Burckhardt Partner AG - 2011 - Rotkreuz

Roche Diagnostics

Roche Diagnostics is a division of Roche, developing and integrating diagnostic solutions that address today’s healthcare challenges while anticipating tomorrow’s needs. In more than 100 countries, we provide one of the industry’s most comprehensive in vitro diagnostics portfolios spanning molecular diagnostics, clinical chemistry and immunoassays, tissue diagnostics, Point of Care testing, patient self-testing, next-generation sequencing, laboratory automation and IT, as well as digital health and decision-support solutions.

Our articles are authored by Roche Diagnostics subject matter experts, drawing on collective expertise across multiple disciplines to provide reliable insights for healthcare professionals worldwide.

Explore articles from our community

Contact us

Do you have questions about our products or services? We’re here to help. Contact a Roche representative in your region.

References

  1. Garassino, M.C. et al. Normalized membrane ratio of TROP2 as a predictor of clinical outcomes with datopotamab deruxtecan in non-small-cell lung cancer. Nat. Med. 1–12 (2026).