Check out the on-demand sessions from the Low-Code/No-Code Summit to learn how to successfully innovate and achieve efficiency by upskilling and scaling citizen developers. Watch now.
Kheiron Medical Technologies (Kheiron), a machine learning startup that’s setting out to help radiologists detect early signs of cancer, has raised $22 million in a series A round of funding led by European VC firm Atomico, with participation from Greycroft, Connect Ventures, Hoxton Ventures, and Exor Seeds.
Founded out of London in 2016, Kheiron offers a breast-screening product called Mia, which serves as a “second reader” to help radiologists decide whether to recall a patient for further evaluation. It’s designed as a supportive tool rather than to replace medical professionals — an automated second opinion, if you like.
Mia’s machine learning and data-processing smarts integrate directly into existing radiology workflows and software and look at areas of interest in full-field digital mammography (FFDM) images from breast cancer screenings, which can be difficult to read with the naked human eye if the tumors are small. This difficulty is often compounded by other distracting “noise” in a scan. Combined with the sheer number of images that a radiologist may have to look at from multiple patients and the shortage of radiologists in some regions, bringing a level of automation to the breast-screening process starts to make a lot of sense.
In fact, Kheiron CEO and cofounder Dr. Peter Kecskemethy said he effectively grew up in a hospital watching his mother work as a radiologist. “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,” he said. “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.”
Intelligent Security Summit
Learn the critical role of AI & ML in cybersecurity and industry specific case studies on December 8. Register for your free pass today.
Kheiron’s algorithms try to “make sense of shades and shapes” in the context of the overall FFDM image and can steer the radiologist toward focusing on certain areas of the scan.
“The power of Kheiron’s deep learning technology is that it can find and learn patterns in large imaging data sets,” Kheiron CTO and cofounder Tobias Rijken told VentureBeat. “We work closely with expert radiologists who understand this complex domain to build the early characteristics of the machine learning models.”
Mia was trained via a variety of data sets encompassing “extensive and diverse clinical samples” that are representative of true screening populations in the U.K., according the company. Kheiron said it is currently working with the U.K.’s National Health Service (NHS) on what it calls “one of the largest deep-learning studies ever conducted,” and is also working with radiologists from across the U.S. and Europe to “help build the early characteristics” of Kheiron’s machine learning models.
Breast cancer is the most common cancer among women globally, with around 2 million new cases diagnosed in 2018 alone — and as with similar diseases, early detection is key to successful treatment. This is why Kheiron plans to use its fresh cash injection to help conduct large-scale clinical trials of its technology globally.
Mia is already certified for use as an independent second reader in Europe and is currently awaiting certification from the U.S. Food and Drug Administration (FDA). Supported by a number of grants, Kheiron will first be deployed in a live testing environment in conjunction with the NHS in early 2020, and it is already carrying out pre-commercial pilots and clinical studies with academic medical centers in the U.S.
“Clinical rigor is at the heart of everything we do,” Rijken continued. “It is one thing to create an algorithm and entirely different to make it useful in clinical practice when patient lives are at stake. 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.”
A number of startups have raised sizable chunks of cash from big-name VCs to use AI and machine learning to help identify new treatments and diagnoses for diseases. Relay Therapeutics, for example, is researching the dynamic nature of proteins in the body to develop new cancer therapies, and last year it raised a substantial $400 million from the likes of Alphabet’s VC arm GV and SoftBank. Elsewhere, Idx — which has developed an AI diagnostic system that analyzes images of the retina for signs of diabetic retinopath — raised $33 million, while a company called Notable recently secured $40 million to personalize cancer drug regimens.
A few months back, IBM scientists also published a paper outlining an AI model they said is capable of predicting the development of malignant breast cancer in patients within a year.
“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,” added Atomico principal (and former surgeon) Irina Haivas, who now joins Kheiron’s board of directors. “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.”
VentureBeat's mission is to be a digital town square for technical decision-makers to gain knowledge about transformative enterprise technology and transact. Discover our Briefings.