A demonstration of automated visual evaluation of cervical images taken with a smartphone camera. Issue 9 (19th May 2020)

• Record Type: Journal Article
• Authors: Xue, Zhiyun; Novetsky, Akiva P.; Einstein, Mark H.; Marcus, Jenna Z.; Befano, Brian; Guo, Peng; Demarco, Maria; Wentzensen, Nicolas; Long, Leonard Rodney; Schiffman, Mark; Antani, Sameer
• Is Part Of: International journal of cancer. Volume 147:Issue 9(2020)
• Page Start: 2416
• Page End: 2423
• Publication Date: 2020-05-19
• Subjects: automated visual evaluation -- cervical cancer screening -- deep learning -- smartphone camera; Cancer -- Periodicals; Cancer -- Prevention -- Periodicals; 616.994
• DOI: 10.1002/ijc.33029
• Languages: English
• ISSNs: 0020-7136

Abstract

Abstract: We examined whether automated visual evaluation (AVE), a deep learning computer application for cervical cancer screening, can be used on cervix images taken by a contemporary smartphone camera. A large number of cervix images acquired by the commercial MobileODT EVA system were filtered for acceptable visual quality and then 7587 filtered images from 3221 women were annotated by a group of gynecologic oncologists (so the gold standard is an expert impression, not histopathology). We tested and analyzed on multiple random splits of the images using two deep learning, object detection networks. For all the receiver operating characteristics curves, the area under the curve values for the discrimination of the most likely precancer cases from least likely cases (most likely controls) were above 0.90. These results showed that AVE can classify cervix images with confidence scores that are strongly associated with expert evaluations of severity for the same images. The results on a small subset of images that have histopathologic diagnoses further supported the capability of AVE for predicting cervical precancer. We examined the associations of AVE severity score with gynecologic oncologist impression at all regions where we had a sufficient number of cases and controls, and the influence of a woman's age. The method was found generally resilient to regional variation in the appearance of the cervix. This work suggests that using AVE on smartphones could be a useful adjunct to health‐worker visual assessment with acetic acid, a cervical cancer screening method commonly used in low‐ and middle‐resource settings. Abstract : What's new? Visual inspection with acetic acid (VIA) is an inexpensive method for cervical cancer screening but is associated with a high false‐positive rate. In this study, the authors investigated a promising adjunct to VIA known as automated visual evaluation (AVE), in which a deep learning algorithm is employed to analyze cervix images captured using smartphone‐housed cameras. Probabilities generated by AVE were strongly associated with evaluation of the same cervix images by experienced oncologists. The findings mark an important step toward practical deployment of AVE as a low‐cost adjunct to VIA, with potential benefits particularly in low‐ to medium‐resource settings.