AI Approach Outperformed Human Experts in Identifying Cervical Precancer

A research team led by investigators from the National Institutes of Health and Global Good has developed a computer algorithm that can analyze digital images of a woman's cervix and accurately identify precancerous changes that require medical attention. This artificial intelligence (AI) approach, called automated visual evaluation, has the potential to revolutionize cervical cancer screening, particularly in low-resource settings.

To develop the method, researchers used comprehensive datasets to "train" a deep, or machine, learning algorithm to recognize patterns in complex visual inputs, such as medical images. The approach was created collaboratively by investigators at the National Cancer Institute (NCI) and Global Good, a project of Intellectual Ventures, and the findings were confirmed independently by experts at the National Library of Medicine (NLM). The results appeared in the Journal of the National Cancer Institute on January 10, 2019. NCI and NLM are parts of NIH.

"Our findings show that a deep learning algorithm can use images collected during routine cervical cancer screening to identify precancerous changes that, if left untreated, may develop into cancer," said Mark Schiffman, M.D., M.P.H., of NCI's Division of Cancer Epidemiology and Genetics, and senior author of the study. "In fact, the computer analysis of the images was better at identifying precancer than a human expert reviewer of Pap tests under the microscope (cytology)."

The new method has the potential to be of particular value in low-resource settings. Health care workers in such settings currently use a screening method called visual inspection with acetic acid (VIA). In this approach, a health worker applies dilute acetic acid to the cervix and inspects the cervix with the naked eye, looking for "aceto whitening," which indicates possible disease. Because of its convenience and low cost, VIA is widely used where more advanced screening methods are not available. However, it is known to be inaccurate and needs improvement.

Automated visual evaluation is similarly easy to perform. Health workers can use a cell phone or similar camera device for cervical screening and treatment during a single visit. In addition, this approach can be performed with minimal training, making it ideal for countries with limited health care resources, where cervical cancer is a leading cause of illness and death among women.

To create the algorithm, the research team used more than 60,000 cervical images from an NCI archive of photos collected during a cervical cancer screening study that was carried out in Costa Rica in the 1990s. More than 9,400 women participated in that population study, with follow up that lasted up to 18 years. Because of the prospective nature of the study, the researchers gained nearly complete information on which cervical changes became precancers and which did not. The photos were digitized and then used to train a deep learning algorithm so that it could distinguish cervical conditions requiring treatment from those not requiring treatment.

Overall, the algorithm performed better than all standard screening tests at predicting all cases diagnosed during the Costa Rica study. Automated visual evaluation identified precancer with greater accuracy (AUC=0.91) than a human expert review (AUC=0.69) or conventional cytology (AUC=0.71). An AUC of 0.5 indicates a test that is no better than chance, whereas an AUC of 1.0 represents a test with perfect accuracy in identifying disease.

"When this algorithm is combined with advances in HPV vaccination, emerging HPV detection technologies, and improvements in treatment, it is conceivable that cervical cancer could be brought under control, even in low-resource settings," said Maurizio Vecchione, executive vice president of Global Good.

The researchers plan to further train the algorithm on a sample of representative images of cervical precancers and normal cervical tissue from women in communities around the world, using a variety of cameras and other imaging options. This step is necessary because of subtle variations in the appearance of the cervix among women in different geographic regions. The ultimate goal of the project is to create the best possible algorithm for common, open use.

Liming Hu, David Bell, Sameer Antani, Zhiyun Xue, Kai Yu, Matthew P Horning, Noni Gachuhi, Benjamin Wilson, Mayoore S Jaiswal, Brian Befano, L Rodney Long, Rolando Herrero, Mark H Einstein, Robert D Burk, Maria Demarco, Julia C Gage, Ana Cecilia Rodriguez, Nicolas Wentzensen, Mark Schiffman.
An Observational Study of Deep Learning and Automated Evaluation of Cervical Images for Cancer Screening, JNCI: Journal of the National.
Cancer Institute, doi: 10.1093/jnci/djy225.

Most Popular Now

NHS and Patients to Benefit from New Par…

IMS MAXIMS and Secure Exchange Solutions have announced a partnership to offer mobile, secure and cost-effective provider-to-provider and provider-to-patient communications to NHS organisations, GP practices and patients.

International Master's in Digital Health

The Master of Science (M.Sc.) in Medical Informatics (MMI) at European Campus Rottal-Inn (ECRI) in Pfarrkirchen - a branch of the Deggendorf University of Applied Sciences (THD - Technische Hochschule...

Digital Medicine: The Opportunities and …

9 - 11 April 2019, Berlin, Germany. Be it preventive healthcare for dementia using intuitive apps, anonymous hospital hygiene inspections using IoT sensors, or VR applications that let hemiplegic patients live...

Highland Marketing Forms Alliance with E…

An alliance between Highland Marketing and Experiential HealthTech will be announced at this year's Digital Health Rewired, with both companies exhibiting from stand B14. Highland Marketing is a full-service marketing...

Google Research Shows How AI can Make Op…

As artificial intelligence continues to evolve, diagnosing disease faster and potentially with greater accuracy than physicians, some have suggested that technology may soon replace tasks that physicians currently perform. But...

Virtual Reality could be Used to Treat A…

Playing games in virtual reality (VR) could be a key tool in treating people with neurological disorders such as autism, schizophrenia and Parkinson's disease. The technology, according to a recent...

Open Call SC1-HCC-02-2019: Support for t…

In the past years several open service platforms for Active and Healthy Ageing domains have been developed, originating from the medical, independent living, and IoT domain. These platforms aim at...

Have an Innovative Digital Health Soluti…

G4A Partnerships are a great opportunity to get your solution in front of Bayer executives and decision makers. All the applications will be reviewed by key stakeholders who have global...

The Moore Blatch Silicon Cup Opens for E…

This year's Moore Blatch Silicon Cup has been launched and is now open for IT companies to enter. The event takes place over 26 - 27 September on the Isle...

MEDICA 2019: Clear Focus on Future Topic…

18 - 21 November 2019, Düsseldorf, Germany. As a result of the final phase of exhibitor registrations for the world’s leading medical trade fare MEDICA 2019 in Düsseldorf, one thing is...

Artificial Intelligence Sheds New Light …

What happens inside a cell when it is activated, changing, or responding to variations in its environment? Researchers from the VIB-UGent Center for Inflammation Research have developed a map of...