A Review of Computational Methods for Cervical Cells Segmentation and Abnormality Classification

Abstract

Cervical cancer is the one of the most common cancers in women worldwide, affecting around 570,000 new patients each year. Although there have been great improvements over the years, current screening procedures can still suffer from long and tedious workflows and ambiguities. The increasing interest in the development of computer-aided solutions for cervical cancer screening is to aid with these common practical difficulties, which are especially frequent in the low-income countries where most deaths caused by cervical cancer occur. In this review, an overview of the disease and its current screening procedures is firstly introduced. Furthermore, an in-depth analysis of the most relevant computational methods available on the literature for cervical cells analysis is presented. Particularly, this work focuses on topics related to automated quality assessment, segmentation and classification, including an extensive literature review and respective critical discussion. Since the major goal of this timely review is to support the development of new automated tools that can facilitate cervical screening procedures, this work also provides some considerations regarding the next generation of computer-aided diagnosis systems and future research directions.

Point-of-Care Digital Cytology With Artificial Intelligence for Cervical Cancer Screening in a Resource-Limited Setting

“… 15 , 16 Digital methods have been proposed to facilitate the visual analysis of Papanicolaou tests, but the development of fully automated systems has been challenging. 17 , 18 Although semiautomated systems for Papanicolaou test screening have been developed, 19 they are limited by the need for bulky, expensive laboratory equipment 20 , 21 , 22 and are not suitable for use at the POC or in resource-limited settings.…”

Single-cell conventional pap smear image classification using pre-trained deep neural network architectures

“…Researchers have developed systems that either classify single-cell CPS images or detect abnormal cells from full-slide CPS images. A detailed and extended review is found in [ 10 ].…”

Point-of-care digital cytology with artificial intelligence for cervical cancer screening at a peripheral clinic in Kenya

“…15,16 Digital methods have been proposed to facilitate the visual analysis of Pap smears, but the development of fully automated systems has been challenging. 17,18 Although semi-automatic systems for Pap smear screening have been developed, 19 they are limited by the need for bulky, expensive laboratory equipment 20,21 and are not suitable for usage in POC or rural settings. Traditional image analysis methods have relied on the identification of pre-defined cellular features in digitized slides (by methods such as the segmentation of the nucleus and cytoplasm of individual cells), rendering them vulnerable to sample quality problems, such as debris and overlapping cells.…”

“…Traditional image analysis methods have relied on the identification of pre-defined cellular features in digitized slides (by methods such as the segmentation of the nucleus and cytoplasm of individual cells), rendering them vulnerable to sample quality problems, such as debris and overlapping cells. 19,22 Recently, deep learning-based medical AI algorithms have provided efficient tools for medical image analysis applications, with levels of performance that have even surpassed human experts in certain tasks. 23-26 However, deep learning algorithms have been mainly studied for the analysis of cervical cytology smears using cropped images from digital samples with a limited number of cells that have been digitized with high-end equipment; however, to our knowledge, no research has been conducted on the analysis of whole slides prepared in rural clinical environments.…”