Mindpeak sets standards with PD-L1 Cell Atlas

October 10, 2023
A refined approach for AI-assisted cancer diagnosis was developed by setting standards in the interpretation of scoring guidelines with a "PD-L1 Cell Atlas".

Hamburg (Germany), 10 October  2023 - Europe's leading provider of AI software for pathology, Mindpeak (Hamburg), has announced groundbreaking work with leading expert  pathologists to improve AI-assisted cancer diagnosis. The collaboration on a "PD-L1 Cell Atlas" marks a significant step in medical research and helps to advance the development and application of Artificial Intelligence (AI) in oncology biomarker readout for precision medicine.

A refined approach for AI-assisted cancer diagnosis was developed by setting standards in the interpretation of  scoring guidelines with a  "PD-L1 Cell Atlas", leading to improved interreader concordance among pathologists. This cell atlas will not only increase accuracy in the development of AI software for PD-L1 biomarker scoring, but will ultimately lead to better patient selection for more efficient immunotherapy using precision medicine drugs. The collaboration results were presented at ECP 2023, including the following authors: Prof. Sunil Badve (Winship Cancer Institute, Emory University Atlanta GA); Dr. George L. Kumar and Dr. Maria Karasarides (Bristol Myers Squibb Princeton NJ); Prof. Joseph Rüschoff and Prof. Hans-Ulrich Schildhaus (Discovery Life Sciences Biomarker Services GmbH Kassel); Dr. Tobias Lang, Felix Faber and Dr. Khalid Daifalla (Mindpeak GmbH Hamburg). 

The pathologists' expertise, particularly in difficult cases where distinguishing between cancer cells and immune cells is challenging, was combined with Mindpeak's leading expertise in AI software for biomarker scoring and was integrated into Mindpeak's AI software. This unique knowledge exchange between human experience and AI technology has significantly increased the effectiveness of cancer diagnosis.

Felix Faber, founder and CEO of Mindpeak, expressed his satisfaction with the groundbreaking collaboration: "I am very pleased that together with these outstanding experts we are able to contribute to the even better and more efficient application of AI in cancer diagnostics and the development of cancer therapies. This pioneering work forms an essential basis for the entire development of AI-assisted cancer treatment."

The results of the study have been presented at the 35th European Congress of Pathology from 9-13 September in Dublin under the title "A roadmap for single-cell annotation using artificial intelligence algorithms: analysis of programmed death ligand 1 immunohistochemistry expression in gastric cancer biopsies" by Prof. Sunil Badve, Head of the Department of Pathology and Laboratory Medicine at Emory University School of Medicine (Atlanta, USA). 

A roadmap for single-cell annotation using artificial intelligence algorithms: analysis of programmed death ligand 1 immunohistochemistry expression in gastric cancer biopsies.

About Mindpeak:

Mindpeak is Europe's leading provider of AI software for pathology. With a focus on tissue biomarker analysis and discovery, Mindpeak serves clinical laboratories and biopharma companies around the world. Mindpeak's algorithms were the first AI in digital pathology to be used in routine clinical diagnostics in the US and EU.

In the News

Related reading

In the News
8 min read

Redefining HER2-ultralow Detection: Mindpeak & AstraZeneca at ASCO 2025

Mindpeak GmbH is looking back at an unforgettable experience at this year’s ASCO2025!

Seeing our work presented in front of 2,000+ experts on the world’s leading oncology stage was more than an honor - it was a defining moment in Mindpeak’s mission to transform cancer diagnostics with AI.

This year stood out as we reached key milestones - most notably, unveiling the transformative results of our collaboration with AstraZeneca, driving the evolution of breast cancer therapies.

Key Highlights:

AI-powered HER2-ultralow detection: Our technology, deployed in one of the world’s largest clinical studies, enabled HER2-ultralow detection at scale - supporting AstraZeneca's Enhertu clinical program.

Clinical Impact: As seen in our session, our AI was instrumental in generating reproducible, high-quality data that contributes to more personalized treatment strategies for breast cancer patients.

Digital pathology at center stage: With our tech featured across multiple sessions and posters, Mindpeak's vision of accessible, automated cancer diagnostics is becoming a reality.

#ASCO2025 wasn't just about showcasing innovation - it was about proving real-world impact.

We’re building AI that scales, adapts, and empowers clinicians worldwide. The response we received confirmed: we’re solving the right problems, in the right way.

A heartfelt thank you to our partners at AstraZeneca, to the many labs and clinicians who made this possible, and to the incredible team at Mindpeak. Your dedication and ambition are the heartbeat of this movement.

Let’s keep pushing forward - the future of AI-driven cancer care is happening now.

In the News
8 min read

AI-Supported Pathology Training Presented at ASCO 2025 in Collaboration with AstraZeneca

We were proud to present our collaborative research with AstraZeneca at the 2025 American Society of Clinical Oncology (ASCO) Annual Meeting. The study, focusing on AI-assisted training for HER2 IHC interpretation, was delivered by Marina De Brot on Friday, May 30th, in Hall D2, in Front of over 2000 people.

Enhancing Diagnostic Accuracy in HER2-Low and HER2-Ultralow Breast Cancer

The classification of HER2-low—and the emerging HER2-ultralow category - has become increasingly significant with the advent of HER2-targeted antibody-drug conjugates such as Enhertu. These therapies are providing new treatment options for patients with minimal HER2 expression, underscoring the importance of accurate diagnostic interpretation.

However, differentiating IHC 1+ from IHC 0, particularly in cases of faint membrane staining, remains a major diagnostic challenge. In line with the 2025 ASCO Annual Meeting theme introduced by ASCO President Dr. Robin Zon, our work aims to improve diagnostic precision and expand equitable access to personalized cancer treatments.

Global AI-Enabled Training Initiative

To address this challenge, we deployed an AI-supported training program through the Mindpeak GmbH ComPath Academy. The initiative engaged 287 pathologists across 11 countries, providing standardized education and decision support on HER2 IHC scoring.

Impactful Results for Clinical Practice

The study results were both clinically and statistically significant. Notably, the AI-supported training led to a 40% increase in accurate identification of HER2-ultralow cases—potentially expanding access to life-extending targeted therapies for a broader group of patients.

As highlighted in coverage by OncLive following the official ASCO press conference, this research reflects the evolving standards in cancer care. Accurate identification of HER2-low and HER2-ultralow patients is now a critical component of therapeutic decision-making in both metastatic and early-stage breast cancer settings.

Empowering, Not Replacing, Pathologists

This initiative is not about replacing pathologists with AI - it’s about empowering them. By combining expert training with advanced AI tools, we aim to improve diagnostic consistency and ensure that more patients receive the therapies they need.

We extend our thanks to everyone who joined us at ASCO 2025 and look forward to continuing our work toward a more precise, equitable future in cancer diagnostics.

In the News
8 min read

Continuing the Story: AstraZeneca and Mindpeak GmbH present new real-world results on AI-assisted HER2 scoring at ASCO 2025

Continuing the Story: AstraZeneca and Mindpeak GmbH present new real-world results on AI-assisted HER2 scoring at ASCO 2025Following our oral presentation last Friday on the AI-assisted training for HER2 IHC interpretation, we are proud to share insights on the Monday’s poster session that took place at this year American Society of Clinical Oncology (ASCO) Annual Meeting.This time, it’s about  real-world diagnostics. In collaboration with six academic centers across the globe, we evaluated whether AI can truly enhance accuracy and consistency in daily pathology practice.And the answer is clear:AI support boosted diagnostic agreement  among pathologists to 86.4% for HER2-low and by 15% to 80.6% for HER2-ultralow - a major leap in consensus for some of the most challenging scoring decisions.Misclassification of HER2-null cases dropped by 64.5%, meaning more patients who may benefit from novel therapies like Enhertu can now be correctly identified.Accuracy rose across the board, especially in the critical 0 vs. 1+ distinction - an area long known for variability and clinical impact.Together, the oral and poster presentations offer a comprehensive view of how AI can support reproducible, high-quality HER2 assessment at scale - from training to clinical practice.As the clinical importance of HER2-low and ultralow scoring continues to grow, our findings provide strong evidence that AI can play a pivotal role in expanding access to targeted therapies like Enhertu - by enabling greater diagnostic precision.

Ready to advance your diagnostics

Connect with our team to explore how precision pathology works in your setting