AI may be better at spotting cervical cancer and precancer after a study found a deep learning algorithm was more accurate at recognizing the disease than human doctors.
“The results support consideration of automated visual evaluation of cervical images from contemporary digital cameras. If achieved, this might permit dissemination of effective point-of-care cervical screening,” Liming Hu, PhD, a project scientist at Intellectual Ventures and lead author of the study, et al. wrote in a study published in the Journal of the National Cancer Institute. The study was funded by National Cancer Institute (NCI), the National Institutes of Health, National Library of Medicine Intramural Research Programs and the Global Good Fund.
For the study, researchers created, trained and validated the deep-learning algorithm using a dataset of more than 60,000 images from more than 9,400 women from a cervical cancer screening study in Costa Rica during the 1990s.
The algorithm identified precancer and cancer cases with a greater accuracy than human experts, according to the study. The algorithm had an area under the curve of 0.91, while expert interpretation of cervical photographs had an AUC of 0.69 and conventional pap smears had a AUC of 0.71 in recognizing cervical cancer and precancer.
“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,” Mark Schiffman, MD, senior study author and senior investigator at NCI’s Division of Cancer Epidemiology and Genetics, said in a statement. “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 study’s promising results could possibly lead to a more reliable way of detecting signs of cervical cancer and precancer at an early stage in low-resource areas. In those areas, visual inspection with acetic acid (VIA) is the current method healthcare workers use to screen for the disease. The method is simple and inexpensive and has been shown to locate some invasive cancers early while it’s still curable, but the method hasn’t been very reliable.
“However, the main goal of screening is to prevent cancer by detection and treatment of precancers, and VIA is not accurate in distinguishing precancer from much more common minor abnormalities, leading to both overtreatment and undertreatment,” the authors wrote. “Increasingly, it is recognized that the visual identification of precancer by health workers, even by experienced nurses and doctors using a colposcope, the reference standard visual tool, is too often unreliable and inaccurate.”
Researchers plan to further train the algorithm on more types of images in hopes to create the “best possible algorithm for common, open use.”
“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,” Maurizio Vecchione, executive vice president of Global Good, said in a statement.
Danielle covers Clinical Innovation & Technology as a senior news writer for TriMed Media. Previously, she worked as a news reporter in northeast Missouri and earned a journalism degree from the University of Illinois at Urbana-Champaign. She's also a huge fan of the Chicago Cubs, Bears and Bulls.