International Multi-site Study of Ibex Medical Analytics’ AI-powered Solution Demonstrates Improved HER2 Biomarker Scoring in Breast Cancer

HER2, one of the proteins responsible for division and proliferation of breast cancer cells, is expressed in many breast tumors and its accurate assessment is critical for identifying patients who are likely to benefit from HER2-directed therapies. Principal investigator, Professor Savitri Krishnamurthy, MD, Professor of Pathology and Laboratory Medicine at The University of Texas MD Anderson Cancer Center, and corresponding study author shared, “Our analysis shows the algorithm performs very well. The study provides evidence that AI can be a useful ancillary tool to aid pathologists in agreeing with expert breast pathologists, as well as creating more concordance amongst themselves for HER2 protein expression at the lower end of the spectrum, including HER2 0 and 1+ cases. This AI tool could be extremely useful for practicing pathologists, particularly in today’s era, where there is a lot of pressure to create HER2-low results in a more reproducible and objective way.”

The study included 120 breast cancer patients’ biopsies from four different medical centers in the US, Europe and the Middle East, and evaluated multiple pathologists’ performance when assisted by Ibex Breast HER2 versus the standard of care (manual HER2 quantification and scoring). Their performance was compared with the reference HER2 scores established by a panel of five international breast pathology experts. The findings illustrate the promise of Ibex’s AI as a valuable addition to the HER2 IHC diagnostic workflow, particularly for distinguishing between HER2-low cases close to the HER2 0/1+ cut-off, a critical distinction contributing to metastatic breast cancer treatment decisions.

Key Highlights of the Study:

• Increased Consistency: Pathologists’ average inter-observer agreement was significantly higher when assisted by AI (83.7%) than with the standard of care (75%), in all slides, and specifically for HER2 0 and 1+ slides (87.4% with AI vs. 69.8% without AI).
• Improved Accuracy (relative to experts): Pathologists supported by AI demonstrated improved accuracy, when scoring HER2 0 and 1+ slides (88.8% with AI vs. 81.9% without AI).
• Validation and Robustness: The AI demonstrated exceptional robustness, with high performance across multiple labs, HER2 antibodies, scanners and patient demographics.

HER2 in Breast Cancer

The emergence and proven efficacy of HER2 antibody-drug conjugate therapies for treatment of HER2 expressing breast cancers has necessitated more accurate and reproducible HER2 IHC scoring, particularly for lower levels of HER2 expression.

For example, Enhertu (trastuzumab deruxtecan) was recently approved by the US FDA and EU EMA for patients with HER2-low metastatic breast cancer (HER2 IHC 1+ or 2+ / ISH-)^3,4; it has also demonstrated clinical efficacy for HER2-ultra-low patients.⁵ Pathologists now need to evaluate and identify lower levels of HER2 expression, despite limited experience with those lower cut-offs, highlighting the need for AI-based decision support solutions that are particularly useful for HER2-low identification.

Professor Stuart J. Schnitt, MD, Chief of Breast Oncologic Pathology at Dana-Farber Brigham Cancer Center, Associate Director at Dana-Farber Cancer Institute-Brigham and Women’s Hospital Breast Oncology Program, Professor of Pathology, Harvard Medical School, one of the study’s expert breast pathologists shares, “With the availability of new drugs to treat patients with low levels of HER2 expression, there is a need for a computational image analysis and quantification solution. The AI identifies areas of invasive cancer and categorizes the different classes of HER2 protein expression very clearly. A case’s final score includes visualization of the AI findings and staining pattern percentages, leading to confidence in the assessment.”

Ibex Breast HER2 is part of Ibex Breast, an integrated AI solution offering a streamlined diagnostic workflow that detects 54 tissue morphologies in breast H&E slides, which has been widely adopted by leading pathology labs worldwide.^6,7 Pathologists can review H&E and IHC stained slides with AI support, facilitating rapid, consistent and objective diagnosis, scoring and reporting of breast biopsies and excisions.

“Our AI-powered solutions are designed together with pathologists, for pathologists, enabling them to leverage cutting-edge technology to make more confident diagnosis,” remarked Dr. Manuela Vecsler, VP of Clinical and Scientific Affairs at Ibex Medical Analytics. “We are thrilled to see our HER2 IHC scoring solution recognized in a prestigious journal like JCO Precision Oncology. This study reaffirms our commitment to providing the most accurate and reliable tools for pathologists, ultimately improving patient care.”

About Ibex Medical Analytics

Ibex Medical Analytics is transforming cancer diagnostics with clinical grade AI powered solutions for pathology. Empowering clinicians and supporting pathologists, Ibex is on a mission to provide accurate, timely and personalized cancer diagnosis for every patient. Ibex is the first and most widely deployed AI-powered platform in pathology. Pathologists worldwide use Ibex as part of their everyday routine to improve the accuracy of cancer diagnosis, implement comprehensive quality control measures, reduce turnaround times, and boost productivity with more efficient workflows. For additional company information, please visit https://ibex-ai.com/ and follow us on LinkedIn and Twitter.

*The Ibex platform includes solutions that are CE-IVD cleared and registered with the UK MHRA, TGA in Australia and ANVISA in Brazil. It is for Research Use Only (RUO) in the United States and pending FDA clearance. For additional details please approach Ibex.

[1] Krishnamurthy et al. JCO Precis Oncol 8, e2400353(2024).

[2] Wolff AC, et al. Arch Pathol Lab Med. 2023 Sep 1;147(9):993-1000

[3] Modi et al. NEJM, 2022; 387:9;

[4] Mosele et al. Nat Med 2023; 29, 2110–2120

[5] Curigliano et al. JCO, 2024. 42(LBA1000-LBA1000)

[6] Sandbank et al. npj Breast Cancer (2022), 8:129.https://doi.org/10.1038/s41523-022-00496-w

[7] Broeckx et al. Virchows Arch (2023) 483 (Suppl 1): S36