Roche announces the release of its newest artificial intelligence (AI) based digital pathology algorithms to aid pathologists in evaluation of breast cancer markers, Ki-67, ER and PR

  • Roche introduces three artificial intelligence (AI)-based, deep learning image analysis Research Use Only (RUO) algorithms developed for breast cancer, which is the second most common cancer in the world with an estimated 2.3 million new cases in 2020¹ and the most common cancer in women globally¹,²
  • Manual methods for quantification of the breast cancer markers can be time consuming and have reported significant interobserver variability 2,3, which can impact decision making to determine patient therapy 
  • Artificial intelligence (AI) advances and growing digitisation of pathology are a promising approach to meet the demand for more accurate detection, classification and prediction of patients with breast cancer 4,5

Roche (SIX: RO, ROG; OTCQX: RHHBY) today announced the research use only (RUO) launch of three new automated digital pathology algorithms, uPath Ki-67 (30-9), uPath ER (SP1) and uPath PR (1E2) image analysis for breast cancer, which are important biomarkers for breast cancer patients. Breast cancer is the second most common cancer in the world with an estimated 2.3 million new cases in 2020¹ and is the most common cancer in women globally¹,². These new algorithms complete the Roche digital pathology breast panel of image analysis algorithms.

uPath Ki-67 (30-9) image analysis, uPath ER (SP1) image analysis and uPath PR (1E2) image analysis for breast cancer use pathologist-trained deep learning algorithms to enable quick calculation of Ki-67, ER and PR tumour cell nuclei positivity. This includes a whole slide analysis workflow with automated pre-computing of the slide image prior to pathologist assessment, and a clear visual overlay highlighting tumour cells with and without nuclear staining. uPath Ki-67 (30-9) image analysis, uPath ER (SP1) image analysis and uPath PR (1E2) image analysis for breast cancer produce actionable assessments of scanned slide images that are objective and reproducible, aiding pathologists in quantification of these breast cancer markers.

Intended for use with Roche’s high medical value assays and slides stained on a BenchMark ULTRA instrument using ultraView DAB detection kit, the uPath Ki-67 (30-9) image analysis, uPath ER (SP1) image analysis and uPath PR (1E2) image analysis algorithms are ready-to-use and integrated within Roche's uPath enterprise software and NAVIFY® Digital Pathology, the cloud version of uPath. These algorithms are for Research Use Only. Not for use in diagnostic procedures.


Roche is committed to the expansion of digital pathology solutions to address unmet medical needs and breast cancer diagnostics is a key opportunity area. Innovations like image analysis algorithms have the potential to impact patient care by increasing the information available to pathologists and enhancing diagnostic confidence.

said Jill German, Head of Roche Diagnostics Pathology Customer Area.

In December 2021, Roche will be presenting an abstract (# P1-02-17) on our artificial intelligence, deep learning development of our breast panel RUO algorithms at the San Antonio Breast Cancer Symposium, which features the latest research and development on breast cancer research. To find out more about this symposium, visit

About Roche Digital Pathology

As the leading provider of pathology lab solutions, Roche is delivering an end-to-end digital pathology solution from tissue staining to producing high-quality digital images that can be reliably assessed using automated clinical image analysis algorithms.

Whole slide imaging combined with modern artificial intelligence (AI)-based image analysis tools have the potential to transform the practice of pathology. The use of AI and deep learning methods to interpret whole slide images in digital pathology enables pathologists to derive novel and meaningful diagnostic insights from tissue samples. AI-based image analysis automates quantitative tasks and enables fast, repeatable evaluation of information-rich tissue images that are sometimes difficult to interpret manually. AI-based image analysis uncovers aspects that are invisible to the human eye and reduces the risk of human error. Patients, whose tissue samples are analysed using AI-based image analysis, can benefit from a faster and more accurate diagnosis with IVD products. The insights gained from these analyses can help pathologists determine the best treatment option for cancer patients.

Roche offers two deployment options for its uPath software: an on-premise solution and a cloud solution, marketed as NAVIFY Digital Pathology. The VENTANA DP 200 slide scanner and Roche uPath enterprise software are CE-IVD marked for in-vitro diagnostic use and are available in the U.S. for Research Use Only (RUO). Not for use in diagnostic procedures. Image analysis algorithms developed by third-party entities and their utilisation are the responsibility of the third party provider. 

About breast cancer

Breast cancer is the second most common cancer in the world, with an estimated 2.3 million new cancer cases diagnosed in 2020 (12% of all cancers) and is the most common cancer in women globally¹,². (see references at bottom) 

About Roche

Roche is a global pioneer in pharmaceuticals and diagnostics focused on advancing science to improve people’s lives. The combined strengths of pharmaceuticals and diagnostics, as well as growing capabilities in the area of data-driven medical insights help Roche deliver truly personalised healthcare. Roche is working with partners across the healthcare sector to provide the best care for each person.

Roche is the world’s largest biotech company, with truly differentiated medicines in oncology, immunology, infectious diseases, ophthalmology and diseases of the central nervous system. Roche is also the world leader in in vitro diagnostics and tissue-based cancer diagnostics, and a frontrunner in diabetes management. In recent years, the company has invested in genomic profiling and real-world data partnerships and has become an industry-leading partner for medical insights.

Founded in 1896, Roche continues to search for better ways to prevent, diagnose and treat diseases and make a sustainable contribution to society. The company also aims to improve patient access to medical innovations by working with all relevant stakeholders. More than thirty medicines developed by Roche are included in the World Health Organization Model Lists of Essential Medicines, among them life-saving antibiotics, antimalarials and cancer medicines. Moreover, for the twelfth consecutive year, Roche has been recognised as one of the most sustainable companies in the pharmaceutical industry by the Dow Jones Sustainability Indices (DJSI).

The Roche Group, headquartered in Basel, Switzerland, is active in over 100 countries and in 2020 employed more than 100,000 people worldwide. In 2020, Roche invested CHF 12.2 billion in R&D and posted sales of CHF 58.3 billion. Genentech, in the United States, is a wholly owned member of the Roche Group. Roche is the majority shareholder in Chugai Pharmaceutical, Japan. For more information, please visit

All trademarks used or mentioned in this release are protected by law.


  1. World Health Organization. GLOBOCAN 2020; All cancers fact sheet. [Internet; cited June 2021]. Available from:
  2. Nielsen TO, et al: Assessment of Ki67 in Breast Cancer: Updated Recommendations From the International Ki67 in Breast Cancer Working Group. J Natl Cancer Inst. 2021 Jul 1;113(7):808-819. doi: 10.1093/jnci/djaa201. PMID: 33369635; PMCID: PMC8487652.
  3. Reisenbichler ES, Lester SC, Richardson AL, et al: Interobserver concordance in implementing the 2010 ASCO/CAP recommendations for reporting ER in breast carcinomas: A demonstration of the difficulties of consistently reporting low levels of ER expression by manual quantification. Am J Clin Pathol 140: 487-494, 2013
  4. Robertson S, Azizpour H, Smith K, Hartman J. Digital image analysis in breast pathology-from image processing techniques to artificial intelligence. Transl Res. 2018 Apr;194:19-35. doi: 10.1016/j.trsl.2017.10.010. Epub 2017 Nov 7. PMID: 29175265.
  5. Ibrahim A, Gamble P, Jaroensri R, Abdelsamea MM, Mermel CH, Chen PC, Rakha EA. Artificial intelligence in digital breast pathology: Techniques and applications. Breast. 2020 Feb;49:267-273. doi: 10.1016/j.breast.2019.12.007. Epub 2019 Dec 19. PMID: 31935669; PMCID: PMC7375550.