The development of “automated visual evaluation” for cervical cancer screening: The promise and challenges in adapting deep‐learning for clinical testing

Abstract

There is limited access to effective cervical cancer screening programs in many resource‐limited settings, resulting in continued high cervical cancer burden. Human papillomavirus (HPV) testing is increasingly recognized to be the preferable primary screening approach if affordable due to superior long‐term reassurance when negative and adaptability to self‐sampling. Visual inspection with acetic acid (VIA) is an inexpensive but subjective and inaccurate method widely used in resource‐limited settings, either for primary screening or for triage of HPV‐positive individuals. A deep learning (DL)‐based automated visual evaluation (AVE) of cervical images has been developed to help improve the accuracy and reproducibility of VIA as assistive technology. However, like any new clinical technology, rigorous evaluation and proof of clinical effectiveness are required before AVE is implemented widely. In the current article, we outline essential clinical and technical considerations involved in building a validated DL‐based AVE tool for broad use as a clinical test.

Abstract

What's new?

An emerging option for cervical cancer screening is deep learning‐based automated visual evaluation (AVE) of cervical images. Here, the authors lay out parameters for the successful development of deep learning‐based AVE. For instance, an algorithm should be trained on representative images from each of four distinct biological stages: normal cervix; infection with high‐risk HPV; precancer; and invasive cervical cancer. Characteristics that may lead to erroneous classification, such as cervicitis, should also be considered in the training. Introducing deep learning‐based methods prematurely threatens their eventual acceptance and best use.