Developed in Collaboration with AstraZeneca and Daiichi Sankyo, Galen™ Breast HER2 Aids Pathologists with Reproducible HER2 Assessment
TEL AVIV – September 7, 2023 – Ibex Medical Analytics (Ibex), the leader in AI-powered cancer diagnostics, today announced the launch of Galen™ Breast HER2, an AI-powered solution that aids pathologists in setting a higher standard for accurate and reproducible HER2 (human epidermal growth factor receptor 2) scoring in breast cancer patients.
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. Traditionally, pathologists evaluate HER2 in tumor samples visually, which may result in varied interpretations as scoring is semi-quantitative and thus somewhat subjective1. The recent emergence of antibody drug conjugates specifically targeting HER2, which are also effective against HER2-low tumors, meant that a new segment of HER2 expression became clinically actionable. Pathologists now need to be able to evaluate and identify lower levels of HER2 expression, despite limited experience in evaluating those lower cut-offs. AI-powered tools may help pathologists with accurate, rapid, and reproducible interpretation of HER2 protein expression, particularly HER2 low, further supporting oncologists in identifying effective therapies for their patients.
Ibex’s Galen Breast HER2 is an AI-powered HER2 IHC (immunohistochemistry) scoring solution that detects invasive tumor areas and quantifies HER2 expression into four standard categories: 0, 1+, 2+ and 3+, based on the 2018 ASCO/CAP scoring guidelines2, to support patient identification for targeted therapies. The solution uses a novel AI-powered computational pipeline to analyze HER2 IHC-stained slides, automatically detect the invasive tumor areas, identify the tumor cells, determine their staining pattern and rapidly calculate the HER2 IHC score with high accuracy and reproducibility. Galen Breast HER2 provides visualization of the AI findings to the pathologist, who can review the invasive areas detected by the algorithm, the cells’ staining patterns, the percentage calculated for each pattern, and make the final determination, thereby retaining full control of the scoring process.
“With Galen, pathologists can now access a single, integrated AI platform for analyzing both H&E and IHC stained slides, supporting quick and consistent objective HER2 scoring,” said Issar Yazbin, VP Product Management at Ibex Medical Analytics. “We are committed to providing pathologists with the most comprehensive AI platform as they implement digital pathology. In addition to HER2, we are now able to support full review of breast biopsies and excisions, distinguish between multiple types of invasive and non-invasive cancer, detect more than 50 malignant and non-malignant morphological features, and provide the underlying technology for automated quantification of additional prognostic and predictive breast biomarkers such as Ki-67, ER and PR.”
Galen Breast HER2 was developed and validated by Ibex in collaboration with AstraZeneca and Daiichi Sankyo. A multi-reader validation study compared the HER2 scoring performance of pathologists and demonstrated that pathologists supported by AI showed higher consistency and accuracy for HER2 scoring, particularly on the lower levels of HER2 expression, compared to pathologists who did not use AI3. An early evidence program to generate data on the accuracy and efficiency of Galen Breast HER2 in clinical practice is now ongoing across 15 cancer centers and laboratories in the United States, Canada, Europe, the UK and Brazil.
Galen Breast HER2 complements Galen Breast which helps pathologists detect and grade different types of invasive and non-invasive breast cancer, as well as identify multiple other clinically significant features, such as tumor-infiltrating lymphocytes (TILs), lymphovascular invasion (LVI) and microcalcifications. Galen Breast is used in routine practice in laboratories, hospitals and health systems worldwide and has demonstrated robust outcomes across multiple clinical studies, one of which was published in Nature’s peer-reviewed npj Breast Cancer journal4,5.
Information about Galen Breast HER2 and Galen Breast will be available at the 35th European Congress of Pathology in Dublin, Ireland, between September 9-13 (Ibex Medical Analytics – booth number 23).
About Ibex Medical Analytics
Ibex Medical Analytics (Ibex) is transforming cancer diagnostics with world-leading, clinical grade AI-powered solutions, empowering physicians to provide accurate, timely and personalized cancer diagnosis for every patient. Our Galen™ suite of solutions is the first and most widely deployed AI-technology in pathology and is used as part of everyday routine, supporting pathologists and providers worldwide in improving the quality and accuracy of diagnosis, implementing comprehensive quality control, reducing turnaround times and boosting productivity with more efficient workflows. Ibex’s artificial intelligence technology is built on deep learning algorithms trained by a team of pathologists, data scientists and software engineers. For additional company information, please visit https://ibex-ai.com/ and follow us on LinkedIn and Twitter.
Galen Breast HER2 is a Research Use Only (RUO) device and is not CE Marked or FDA cleared. Galen Breast is CE-Marked (IVDD) and registered with the UK MHRA. Galen Breast is intended for Research Use Only (RUO) in the United States and not cleared by the FDA. For more information, including indication for use and regulatory approval in other countries, contact Ibex Medical Analytics.
 Robbins C.J. et al. Multi-institutional Assessment of Pathologist Scoring HER2 Immunohistochemistry. Modern Pathology. 2023, 36(1):100032
 Wolff et al, Human epidermal growth factor receptor 2 testing in breast cancer: American Society of Clinical Oncology/College of American Pathologists Clinical Practice Guideline Focused Update. Arch Pathol Lab Med 142:1364-1382, 2018.