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

China to Take on Leading Role in Medical…

Asia, in particular China, has been advancing significantly on its way to a key role in geopolitics, says correspondent Frank Sieren - and towards spearheading developments in medical technologies. At...

Artificial Intelligence Algorithm can Le…

Artificial Intelligence can be used to predict molecular wave functions and the electronic properties of molecules. This innovative AI method developed by a team of researchers at the University of...

Preventive Health Care Via App

Demand for apps for preventive health care is growing all the time. Particularly popular are diagnostic assistants that record physiological and fitness data. However, there are data protection concerns with...

Artificial Intelligence-Based Algorithm …

Traumatic brain injury (TBI) is a significant global cause of mortality and morbidity with an increasing incidence, especially in low-and-middle income countries. The most severe TBIs are treated in intensive...

Bittium Exhibits its Innovative High-Tec…

Bittium exhibits its innovative products and solutions for cardiology and neurology at Medica 2019, the leading international trade fair for the medical sector, on November 18 - 21 in Dusseldorf...

MEDICA 2019 + COMPAMED 2019 Due to Launc…

18 - 21 November 2019, Düsseldorf, Germany. From Monday until Thursday, the entire medical world and health care sector will once again meet in Düsseldorf. With a record participation of a...

A Mobile App for Managing Mobile Medical…

Beginning of March 2019, Merci Charity Boutique association based in Bucharest, Romania started testing the "Mobile app for mobile medical units and cabinets", which helps the mobile dental practice to...

MEDICA and COMPAMED Hold their Own in a …

18 - 21 November 2019, Düsseldorf, Germany. The demand market for medical technology and medical products is becoming increasingly challenging and discriminating worldwide. Providers are adapting to this on a flexible...

GE Healthcare Expands Intelligent Health…

GE Healthcare launched the Edison Developer Program to accelerate the adoption and impact of intelligent applications and developer services across health systems. The program is based on Edison, GE Healthcare's...

Learning Platform to Improve Health Tech…

ANCILE Solutions is bringing its content creation and in-app learning tool, uPerform, to the UK health sectorto support NHS organisations with the deployment and adoption of major IT systems. ANCILE Solutions...

State of Health in the EU: Companion Rep…

Europe is a Union of and for citizens. What matters to Europeans matters to the EU. It should come as no surprise that regular surveys and debates across the continent...

XPOMET© Medicinale Presented Current and…

10 - 12 October 2019, Berlin, Germany. Research and practice of medicine, education, and management concepts - powerful statements and presentations at XPOMET Medicinale enable sustainable healthcare in the future. This...