Diagnosing cancer, especially at an early stage, is an extremely challenging and time-consuming task, even for the most experienced radiologists. A massive shortage of radiologists in many countries, coupled with an ever rising demand for imaging is putting even greater pressure on the doctors who are responsible for making critical decisions about patient care.
London-based Kheiron Medical Technologies, which focuses on supporting cancer diagnostics with machine learning, has closed a €20 million Series A round led by Atomico with participation from existing investors Connect Ventures, Greycroft, Hoxton Ventures and EXOR Seeds.
Kheiron Medical’s first product, Mia, has been developed to improve the outcomes for those diagnosed with breast cancer – more than two million women every year. Reliable early detection can mean the difference between life and death for these women, but it is very resource intensive to build and maintain high-performance breast screening programmes under increasing quality expectation pressures.
Founded in 2016, Kheiron intends to use the new investment to further scale the clinical validation of Mia, including conducting a series of large-scale clinical trials and roll-outs in Europe, the US and Asia to rigorously assess and demonstrate the clinical effectiveness and safety of the software.
“The foundation of Kheiron’s approach to rigorous development and testing is to ensure reliably improved patient outcomes and safety by helping doctors in their daily practice,” said Kheiron CEO, Dr. Peter Kecskemethy. “In my childhood I spent many hours in my mother’s radiology department watching her carefully read and report imaging studies and struggling with workloads and working conditions. I know first-hand the stress, inefficiencies and extreme pressures that she and other radiologists face every day, and the uncertainty, especially the worry, when deciding if a patient’s image suggests cancer or not.”
Mia is designed to analyse standard Full Field Digital mammography (FFDM) images in a breast cancer screening setting, and to assist radiologists in making a vital clinical decision: to recall a woman for further evaluation or not. The software has demonstrated state-of-the-art performance in a multi-centre clinical study and was voted Best New Radiology Software 2019 by leading radiology publisher AuntMinnie. Mia’s first deployments for live testing and further trials are affiliated with the UK’s National Health Service (NHS) and leading academic medical centers in the US.
Mia has been developed by Kheiron’s world-class team of machine learning specialists, radiologists and imaging industry experts with backgrounds at leading institutions such as Imperial College, The Royal Marsden, University College London, Edinburgh, Oxford, GE and Philips.
“Clinical rigor is at the heart of everything we do. It is one thing to create an algorithm, and entirely different to make it useful in clinical practice when patient lives are at stake,” said Kheiron CTO and Co-Founder Tobias Rijken. “The key to helping radiologists diagnose breast cancer more accurately for the benefit of women everywhere was finding investors who understood how to safely validate and scale products for global impact. The team at Atomico has a wealth of experience doing this at companies such as Skype, Uber, Spotify and Virgin and we could not be more pleased to be working with them on this important problem.”
“Cancer care today is defined by fear and uncertainty but we believe we are on the cusp of a new age when AI-supported approaches to diagnostics will enable earlier and more accurate detection, tracking, and as a result better treatment outcomes,” said Irina Haivas, Atomico. “We invested in Kheiron because we believe they have one of the best machine learning teams in the world but also because they have such a deep understanding of radiology and the clinical validation required in order to usher in this new era of cancer diagnosis and care.”