Two first-in-class AI diagnostic solutions for breast cancer and colorectal cancer developed by Owkin are approved for use in Europe

Duration:10 mins

Tags: AI / Cancer


Date:September 2nd, 2022


Two first-in-class AI diagnostic solutions for breast cancer and colorectal cancer developed by Owkin are approved for use in Europe

Friday, 2nd September – Artificial intelligence (AI) biotech company Owkin today announced that two first-in-class rapid, affordable AI-based diagnostic solutions designed to improve outcomes for patients with breast cancer and colorectal cancer have been approved for use in Europe.

Owkin Dx RlapsRisk™  BC and Owkin Dx MSIntuit™ CRC have received CE-IVD approval for diagnostic use in the European Union. By using AI to analyze digital pathology images, they are designed to help clinicians make precision medicine – diagnostic and treatment based on a patient's individual characteristics – more accessible to more patients at an earlier stage of their disease. 

RlapsRisk BC is the first CE-IVD approved digital pathology-based AI diagnostic that predicts the risk that early breast cancer patients will relapse. MSIntuit CRC is the first CE-IVD approved AI solution that enables the identification of microsatellite stable (MSS) patients from routine histology slides, enabling a significant reduction in time and the number of diagnostic tests for detecting MSI in clinical practice. 

These are the first approved diagnostics products developed by Owkin, which aims to develop more biomarker pre-screening and outcome prediction diagnostics across a range of disease areas. Owkin’s mission is to join patient care with medical research to discover new mechanisms of diseases and derive better treatments for unmet medical needs.

Meriem Sefta, Chief Diagnostics Officer at Owkin, said:

Our mission is to use AI to find the right treatment for every patient. Novel drugs allow us to personalize treatments to patients’ individual disease characteristics, promising a new era of precision medicine. But one roadblock that doctors face is finding these patients rapidly, accurately and efficiently.

Our first approved diagnostic solutions could help millions of patients with breast or colorectal cancer to receive the therapies they need sooner. This is a crucial moment in Owkin’s mission to use AI to better understand diseases and develop more accurate diagnostics and treatments for patients.

Owkin Dx RlapsRisk BC

RlapsRisk BC is an AI prognostic solution that predicts whether a breast cancer patient (ER+/HER2-) will go on to relapse after treatment, informing oncologists which high-risk patients may benefit from targeted therapies and which low-risk patients could potentially avoid chemotherapy.

The solution aims to revolutionize breast cancer care management by using AI to assess the risk of relapse after treatment from digital images of tissue samples. Currently, breast cancer patients at risk of relapse are identified through expensive, time-consuming molecular or genetic testing. RlapsRisk BC offers doctors a way to identify patients at risk of relapsing by using AI on digital pathology data that will already be held on nearly all breast cancer patients in around 15 minutes.

Dr Magali Lacroix-Triki, MD, PhD, an expert breast pathologist at the Department of Medical Biology and Pathology, Institut Gustave Roussy, Paris, said:

Owkin's RlapsRisk BC enables pathologists to provide oncologists and patients with insights on the risk of relapse, crucial information for the treatment decision-making to avoid unnecessary chemotherapy. Thanks to RlapsRisk, HER2-, ER+ patients will benefit from an automated and accurate prognosis test using just a simple, standard-stained tumor slide.

AI-based digital pathology diagnostics could help us to provide a comprehensive analysis of each tumor from just one representative standard-stained tumor slide, in a complementary process to the pathologist’ diagnosis. This would democratize access to precision medicine, unlocking a new era of treatment for patients across the world.

Caption: RlapsRisk BC provides an interpretability report to the pathologist with a risk score, derived from the most predictive regions of the histology slide. Image shown may represent the range of the product, or be for illustration purposes only and may not be an exact representation of the product. 

It offers comparable performance to standard molecular testing, yet uses far more readily-accessible data, reducing turnaround time and democratizing access to precision medicine. 

RlapsRisk BC was developed with Gustave Roussy after winning the 2019 “AI for Health'' challenge grant from Region Île de France. Its corresponding research has been presented at ESMO 2021 and USCAP 2022.

Owkin Dx MSIntuit CRC

MSIntuit CRC is an AI digital pathology diagnostic solution that pre-screens for a biomarker in colorectal cancer tumors known as microsatellite instability (MSI) – a defect in a cell’s ability to correct mistakes that occur when DNA is copied. This diagnostic rules out microsatellite stable (MSS) phenotypes, allowing pathologists to concentrate their resources on confirming those patients who exhibit MSI. 

By using an AI model to analyze digital images of tissue samples, doctors are able to more efficiently screen patients when compared to standard testing techniques, which include time and patient tissue sample-consuming polymerase chain reaction (PCR) testing or immunohistochemistry. 

Professor Magali Svrcek, MD, PhD, Sorbonne Université, AP-HP, Saint-Antoine Hospital, Department of Pathology, Paris, said:

As colorectal cancer is the third most common cancer in the world, it is crucial that we are able to screen patients for biomarkers that make them eligible for potentially lifesaving treatments. dMMR/MSI screening should be performed on all colorectal cancer patients, but pathologists' time and resources are often too stretched.

Owkin's new AI diagnostic solution MSIntuit CRC will roughly half the number of cases requiring screening. It is designed to help more patients receive treatment sooner. AI-based digital pathology algorithms like these, developed in consultation with pathologists, will soon become an integral part of our daily practice. They will help patients to benefit from the best treatment for them sooner – a new era of personalized medicine.

Patients with MSI-high tumors are eligible for treatment with the novel immunotherapy drug pembrolizumab, which a 2020 clinical trial found led to significantly longer progression-free survival than standard treatment when received as first-line therapy for MSI-H–dMMR metastatic colorectal cancer.

MSIntuit CRC provides an interpretability report to the pathologist, in which the most predictive regions found by the model on the histology slide are outlined.

MSIntuit CRC will help clinicians to gain accurate insights into patients’ individual needs at an earlier stage, enabling a precision medicine approach to treatment. By ruling out those patients who would not benefit from immunotherapy, MSIntuit CRC introduces a pre-screening step which saves pathologists’ and oncologists’ time and resources. Such an optimization supports the scaling of MSI screening for more patient populations and further disease indications. 

MSIntuit was created by using deep learning – a type of AI that replicates how the human brain gains knowledge – on hundreds of patient samples until it could accurately detect the presence of MSI on images of tumors. Its accuracy has been validated by a clinical blind validation study on hundreds more patient samples.

About Owkin

Owkin is a French-American startup that uses artificial intelligence to find the right treatment for every patient. Our focus is to use AI to discover and develop better treatments for unmet medical needs, starting with the fight against cancer.

We use AI to identify new drug candidates, de-risk and accelerate clinical trials and build diagnostic tools that improve patient outcomes. Using federated learning, a pioneering collaborative AI framework, Owkin enables medical and biopharma partners to unlock valuable insights from siloed datasets while protecting patient privacy and securing proprietary data. 

Owkin was co-founded by Thomas Clozel MD, a former assistant professor in clinical onco-hematology, and Gilles Wainrib, a pioneer in the field of machine learning in biology, in 2016. Owkin has raised over $300 million and became a unicorn through a $180 million investment from biopharma company Sanofi in November 2021.