News | Digital Pathology | January 10, 2019

AI Approach Outperformed Human Experts in Identifying Cervical Precancer

Artificial intelligence algorithm could revolutionize cervical cancer screening, especially in low-resource settings

AI Approach Outperformed Human Experts in Identifying Cervical Precancer

January 10, 2019 — 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 fund at 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 Jan. 10, 2019.1 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., MPH, 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. Healthcare 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 healthcare 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.

"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.

For more information: www.academic.oup.com/jnci

Reference

1. Hu L., Bell D., Antani S., et al. An Observational Study of Deep Learning and Automated Evaluation of Cervical Images for Cancer Screening. Journal of the National Cancer Institute, Jan. 10, 2019. https://doi.org/10.1093/jnci/djy225

Related Content

Sectra Providing Centralized Regional Solution for Digital Pathology in the U.K.
News | Digital Pathology | June 14, 2019
Sectra has signed a five-year contract with North Tees and Hartlepool National Health System (NHS) Foundation Trust for...
M*Modal and Community Health Network Partner on AI-powered Clinical Documentation
News | PACS Accessories | June 13, 2019
M*Modal announced that the company and Community Health Network (CHNw) are collaborating to transform the patient-...
iCAD Introduces ProFound AI for 2D Mammography in Europe
News | Artificial Intelligence | June 13, 2019
iCAD Inc. announced the launch of ProFound AI for 2D Mammography in Europe. This software is the latest addition to...
A static image drawn from a stack of brain MR images may illustrate the results of a study. But a GIF (or MP4 movie), created by the Cinebot plug-in, can scroll through that stack, providing teaching moments for residents and fellows at Georgetown University

A static image drawn from a stack of brain MR images may illustrate the results of a study. But a GIF (or MP4 movie), created by the Cinebot plug-in, can scroll through that stack, providing teaching moments for residents and fellows at Georgetown University. Image courtesy of MedStar Georgetown University Hospital

Feature | Information Technology | June 13, 2019 | By Greg Freiherr
Editor’s note: This article is the third in a content series by Greg Freiherr covering the Society for Imaging In
Studycast PACS Adds Two-factor Authentication to Improve Data Privacy and Security
News | Cybersecurity | June 12, 2019
Core Sound Imaging announced the addition of two-factor authentication (2FA) to the security measures available for the...
The Current Direction of Healthcare Reform Explained by CMS Administrator Seema Verma
News | Radiology Business | June 11, 2019
June 11, 2019 — Centers for Medicare and Medicaid Services (CMS) Administrator Seema Verma addressed the American Med
Aidoc Earns FDA Approval for AI for C-spine Fractures
Technology | Artificial Intelligence | June 11, 2019
Radiology artificial intelligence (AI) provider Aidoc announced the U.S. Food and Drug Administration (FDA) has cleared...
Medivis SurgicalAR Gets FDA Clearance
Technology | Virtual and Augmented Reality | June 10, 2019
Medivis announced that its augmented reality (AR) technology platform for surgical applications, SurgicalAR, has...
Glassbeam Announces New Clinsights Application Suite for Healthcare Provider Market
Technology | Analytics Software | June 10, 2019
Glassbeam launched Clinsights, a new revitalized application suite powered by artificial intelligence/machine learning...
The DeepAAA algorithm, developed at the MGH & BWH Center for Clinical Data Science, accurately detected and measured an abdominal aortic aneurysm (AAA) in a CT image even though appearance of the AAA was complicated by a blood clot

The DeepAAA algorithm, developed at the MGH & BWH Center for Clinical Data Science, accurately detected and measured an abdominal aortic aneurysm (AAA) in a CT image even though appearance of the AAA was complicated by a blood clot. (The algorithm drew a green circle around the aneurysm.) Image courtesy of Varun Buch, MGH & BWH Center for Clinical Data Science

Feature | Artificial Intelligence | June 10, 2019 | By Greg Freiherr
Editor’s note: This article is the second in a content series by Greg Freiherr covering the ...