Archives

  • 2019-10
  • 2019-11
  • 2020-03
  • 2020-07
  • 2020-08
  • br Contents lists available at ScienceDirect br Informatics

    2020-08-30


    Contents lists available at ScienceDirect
    Informatics in Medicine Unlocked
    journal homepage: www.elsevier.com/locate/imu
    Cervical cancer classification from Pap-smears using an enhanced fuzzy C- T means algorithm
    Wasswa Williama,∗, Andrew Wareb, Annabella Habinka Basaza-Ejiric, Johnes Obungolocha
    a Department of Biomedical Sciences and Engineering, Mbarara University of Science and Technology, Mbarara, 1410, Uganda b Faculty of Computing, Engineering and Science, University of South Wales, Prifysgol, UK c College of Computing and Engineering, St. Augustine International University, Kampala, Uganda
    Keywords:
    Pap-smear
    Cervical cancer
    Fuzzy-C means 
    Globally, cervical cancer ranks as the fourth most prevalent cancer affecting women. However, it can be suc-cessfully treated if detected at an early stage. The Pap smear is a good tool for initial screening of cervical cancer, but there is the Methoxy-PMS possibility of error due to human mistake. Moreover, the process is tedious and time-consuming. The objective of this study was to mitigate the risk of mistake by automating the process of cervical cancer classification from Pap smear images. In this research, Methoxy-PMS local adaptive histogram equalization was used for image enhancement. Cell segmentation was achieved through a Trainable Weka Segmentation classifier, and a sequential elimination approach was used for debris rejection. Feature selection was achieved using simulated annealing integrated with a wrapper filter, while classification was achieved using a fuzzy c-means algorithm.
    The evaluation of the classifier was carried out on three different datasets (single cell images, multiple cell images and Pap smear slide images from a pathology unit). An overall classification accuracy, sensitivity and specificity of ‘98.88%, 99.28% and 97.47%‘, ‘97.64%, 98.08% and 97.16%’ and ‘96.80%, 98.40% and 95.20%’ were obtained for each dataset respectively. The higher accuracy and sensitivity of the classifier was attributed to the robustness of the feature selection method that was utilized to select cell features that would improve the classification performance, and the number of clusters used during defuzzification and classification. The eva-luation and testing conducted confirmed the rationale of the approach taken, which is based on the premise that the selection of salient features embeds sufficient discriminatory information that leads to an increase in the accuracy of cervical cancer classification. Results show that the method outperforms many of the existing al-gorithms in terms of the false negative rate (0.72%), false positive rate (2.53%), and classification error (1.12%), when applied to the DTU/Herlev benchmark Pap smear dataset. The approach articulated in this paper is ap-plicable to many Pap smear analysis systems, but is particularly pertinent to low-cost systems that should be of significant benefit to developing economies.
    1. Introduction
    Globally, cervical cancer ranks as the fourth most prevalent cancer affecting women with 527,624 women diagnosed with the disease and 265,672 dying from Transduction every year [1]. In sub-Saharan Africa, 34.8 new cases of cervical cancer are diagnosed per 100,000 women annually, and 22.5 per 100,000 women die from the disease, with over 80% of cervical cancers detected in the late stages [2]. Over 85% of cervical cancer cases occur in less developed countries of which the highest incidences are in Africa, with Uganda being ranked seventh among the countries with the highest incidences of cervical cancer. Over 85% of those diagnosed with the disease in Uganda die from it [3]. This is
    attributed to lack of awareness of the disease aggravated by limited access to screening and health services. Regular Pap smear screening is the most successful and effective method in medical practice to facil-itate the early detection and screening of cervical cancer. However, the manual analysis of Pap smear images is time-consuming, laborious and error-prone as hundreds of sub-images within a single slide have to be examined under a microscope by a trained cytopathologist for each patient screened. Human visual grading of microscopic biopsy images tends to be subjective and inconsistent [4]. To overcome the limitations associated with the manual analysis of Pap smear images, computer-assisted Pap smear analysis systems using image processing and ma-chine-learning techniques have been proposed by several researchers
    ∗ Corresponding author.
    Available online 12 February 2019
    1.1. Computer-assisted Pap smear analysis
    Since the 1960's, numerous projects have developed computer-as-sisted Pap smear analysis systems leading to a number of commercial products, such as AutoPap 300 QC (NeoPath, Redmond, WA, USA) [8] and the PapNet (Neuromedical Systems Inc., Suffern, NY, USA) [9] which were approved by the United States Food and Drug Adminis-tration (FDA). However, these have had limited impact on cervical cancer screening in countries with less developed economies. Ever since the first appearance of computers, significant development efforts have been exerted to try to supplement or replace the human visual in-spection of Pap smears with computer-aided analysis. However, the problem turned out to be more difficult than envisaged. Computer-as-sisted Pap smear analysis has proved to be a complex process, which comprises the following stages.