RlapsRisk BC

Assess the risk of breast cancer relapse

RlapsRisk BC is an AI diagnostic to help pathologists and oncologists determine the right treatment pathway for early breast cancer patients

Clinical context

Revolutionize breast cancer care management by democratizing access to actionable medical insights

14 secs
Incidence is high. Every 14 seconds, across the globe, a woman is diagnosed with breast cancer. 2
+20%
Since 2008, worldwide breast cancer incidence has increased by more than 20 percent. 2
10%
Approximately 10% of all patients will relapse after their initial treatment each year. 3

Clinicians lack the tools to identify these high-risk patients at an early stage. Current methods either lack consistency in accuracy 4,5,6 or they are expensive and non-routine, 7 such as genomic sequencing.

Video
Professor Fabrice André on RlapsRisk BC

RlapsRisk BC

Our research shows accurate discrimination between high and low risk of relapse 1

Testing

Suitable for adults with primary invasive breast cancer (ER+/HER2-)

78% icon
Cumulative sensitivity

Cumulative sensitivity is greater than those obtained by standard clinical scores 1

80% icon
Dynamic specificity

Achieves 80% specificity for post-treatment, time-dependent accuracy at 5 years 1

Microscope icon
Digital pathology

Intended to work with surgically resected tissue on digitized slides

Report icon
PDF report

Delivered as a PDF report with intuitive design

Algorithm icon
Workflow agnostic

Deployment is feasible across IMS systems, or even a shared directory

Tablet screenScreen image

Therapeutic and pathologist workflow

Integrating AI-powered diagnostics seamlessly

Due to variability across pathology labs, workflows may vary by institutions and disease indications.

Subtype confirmed

ER+/HER2- invasive carcinoma of the breast

Surgery

Tumor excision

Pathologist

Selects slide of indication

WSI Review

Analysis of digitized slide

Owkin diagnostic
RlapsRisk BC

PDF report

Pathologist

Delivers final pathology report

Multidisciplinary board

Further testing / treatment decision

Testimonial

“Thanks to the solution we now have a better understanding of the underlying mechanism of highly aggressive tumors and the treatment needs for these patients. Identifying very high-risk patients earlier will enable us to adjust the therapeutic strategy for more favorable patient outcomes.”
Professor Fabrice André, MD, PhD
Director of Research, Gustave Roussy
Incoming President of ESMO

Research and development

Timeline of milestones

Owkin wins the AI for Health challenge
2019
Owkin wins the AI for Health challenge
First model trained
2020
First model trained
Abstract presented at ESMO Congress, Switzerland
2021
Abstract presented at ESMO Congress, Switzerland
Abstract presented at USCAP
2022
Abstract presented at USCAP
Abstract presented at ESMO
2022
Abstract presented at ESMO
2019
July
Jul
2020
May
May
2021
September
Sep
2022
March
Mar
2022
September
Sep

Trained with data from a fruitful partnership with Gustave Roussy

Based on 1800 breast cancer patients (incl. 1480 HER2-/HR+)

Digitized HES slides
Demographic variables
Five years follow-up
Disease variables
RlapsRisk box model diagram

Clinical variables C-index = .72

AI model C-index = .75

AI model integrating clinical variables C-index = .78

Image AI analysis outperforms clinical scores

RlapsRisk BC achieves 78% sensitivity and 80% specificity for post-treatment, time-dependent accuracy at 5 years, outperforming current clinical scores in practice. 1

Cumulative Sensitivity/Dynamic Specificity are natural extensions of sensitivity/specificity to the setting of time-to-event outcomes, such as the metastasis-free interval (MFI), understood as the time to distant relapse occurrence from initial surgery. In use here, as they easily accommodate time-dependent outcome status as well as right-censoring.

Validating product performance

We work closely with medical institutions and pathology lab networks to validate our solutions and ensure their performances are robust across clinics, hospitals, and laboratories.
Training cohort
Close

When run on our training cohort, RlapsRisk BC’s performance demonstrates strong discrimination between risk groups, better informing oncologists on the risk classification of their patients to aid in treatment decisions.

Blind validation cohort
Close

Through blind validation on a separate cohort, RlapsRisk BC demonstrates that it is well calibrated with similar performances on data it was not trained on.

P-value < 0.01.         Sample size N = 676

Citations
  1. Garberis IJ, Gaury V, Drubay D, et al. Blind validation of an AI-based tool for predicting distant relapse from breast cancer HES stained slides. Poster presented at: European Society for Medical Oncology (ESMO); May 9th - 13th 2022; Paris France.
  2. https://www.bcrf.org/breast-cancer-statistics-and-resources/
  3. Long-term hazard of recurrence in HER2+ breast cancer patients untreated with anti-HER2 therapy, Strasser-Weippl et al. 2015, BMC
  4. Gown AM. Current issues in ER and HER2 testing by IHC in breast cancer. Mod Pathol. 2008 May;21 Suppl 2:S8-S15. doi: 10.1038/modpathol.2008.34. PMID: 18437174.
  5. Casterá C, Bernet L. HER2 immunohistochemistry inter-observer reproducibility in 205 cases of invasive breast carcinoma additionally tested by ISH. Ann Diagn Pathol. 2020 Apr;45:151451. doi: 10.1016/j.anndiagpath.2019.151451. Epub 2019 Dec 17. PMID: 31955049.
  6. Polley MY, Leung SC, McShane LM, et al. An international Ki67 reproducibility study. J Natl Cancer Inst. 2013 Dec 18;105(24):1897-906. doi: 10.1093/jnci/djt306.
  7. Blok EJ, Bastiaannet E, van den Hout WB, et al. Systematic review of the clinical and economic value of gene expression profiles for invasive early breast cancer available in Europe. Cancer Treat Rev. 2018 Jan;62:74-90. doi: 10.1016/j.ctrv.2017.10.012.
The device is currently under development, and not for clinical use. Please contact Owkin for more information. Images shown may represent the range of products, or be for illustration purposes only, and may not be an exact representation of the product.
Manufacturer: Owkin France. RlapsRisk is a trademark of Owkin Inc. European Patent Application No. EP21306284.7 / International Application No. PCT/US2022/043692
Information updated on 17th July 2023