A system for detection of cervical precancerous in field emission scanning electron microscope images using texture features

Yessi Jusman,Siew-Cheok Ng,Kean Hooi Teoh,Rahmadi Kurnia,Khairunnisa Hasikin,Noor Azuan Abu Osman

doi:10.1142/s1793545816500450

Yessi Jusman, Siew-Cheok Ng + Show 4 more

Open Access

https://doi.org/10.1142/s1793545816500450

Copy DOI

Abstract

This study develops a novel cervical precancerous detection system by using texture analysis of field emission scanning electron microscopy (FE-SEM) images. The processing scheme adopted in the proposed system focused on two steps. The first step was to enhance cervical cell FE-SEM images in order to show the precancerous characterization indicator. A problem arises from the question of how to extract features which characterize cervical precancerous cells. For the first step, a preprocessing technique called intensity transformation and morphological operation (ITMO) algorithm used to enhance the quality of images was proposed. The algorithm consisted of contrast stretching and morphological opening operations. The second step was to characterize the cervical cells to three classes, namely normal, low grade intra-epithelial squamous lesion (LSIL), and high grade intra-epithelial squamous lesion (HSIL). To differentiate between normal and precancerous cells of the cervical cell FE-SEM images, human papillomavirus (HPV) contained in the surface of cells were used as indicators. In this paper, we investigated the use of texture as a tool in determining precancerous cell images based on the observation that cell images have a distinct visual texture. Gray level co-occurrences matrix (GLCM) technique was used to extract the texture features. To confirm the system’s performance, the system was tested using 150 cervical cell FE-SEM images. The results showed that the accuracy, sensitivity and specificity of the proposed system are 95.7%, 95.7% and 95.8%, respectively.

Highlights

Cervical cancer screening is an important step in preventing cancer through the early detection of abnormal tissue or cancer in the neck of the womb.[1]
The screening is based on cellular-level approach (i.e., pap smear, liquid based cytology (LBC), etc.) and tissue-level approach[2] which were developed based on analysis of the images
The approach is divided into three steps: (1) preprocessing; (2) feature extraction and (3) Linear discriminant analysis (LDA) classication

Summary

Introduction

Cervical cancer screening is an important step in preventing cancer through the early detection of abnormal tissue or cancer in the neck of the womb (i.e., cervix).[1]. The screening is based on cellular-level approach (i.e., pap smear, liquid based cytology (LBC), etc.) and tissue-level approach (i.e., colposcopy, cervicography, etc.)[2] which were developed based on analysis of the images. In the screening of cervical cancer, the abnormality of cells is investigated based on the morphological component of cells such as nucleus and cytoplasm. The pap smear images are produced by a light microscope where cells often overlap. The overlapped cells will complicate analysis of the nucleus and cytoplasm can decrease the accuracy of screening results. Colposcopy and cervicography images are produced by capturing the cervix using camera. Both techniques have produced low resolution images. Examining cells using a microscope and looking for strategic parts by sliding the slide during the acquisition process is tiring and time consuming

Methods

Results

Conclusion