Library Subscription: Guest
Begell Digital Portal Begell Digital Library eBooks Journals References & Proceedings Research Collections
Critical Reviews™ in Biomedical Engineering
SJR: 0.207 SNIP: 0.376 CiteScore™: 0.79

ISSN Print: 0278-940X
ISSN Online: 1943-619X

Critical Reviews™ in Biomedical Engineering

DOI: 10.1615/CritRevBiomedEng.2018026019
pages 135-145

Automation of Detection of Cervical Cancer Using Convolutional Neural Networks

Vidya Kudva
School of Information Sciences, Manipal Academy of Higher Education, Manipal, India -576104; Nitte Mahalinga Adyanthaya Memorial Institute of Technology, Nitte, India - 574110
Keerthana Prasad
Department of School of Information Science, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, Karnataka, India
Shyamala Guruvare
Department of Obstetrics and Gynecology, Kasturba Medical College, Manipal, India - 576104


Classification of digital cervical images acquired during visual inspection with acetic acid (VIA) is an important step in automated image-based cervical cancer detection. Many algorithms have been developed for classification of cervical images based on extracting mathematical features and classifying these images. Deciding the suitability of a feature and learning the algorithm is a complex task. On the other hand, convolutional neural networks (CNNs) self-learn most suitable hierarchical features from the raw input image. In this paper, we demonstrate the feasibility of using a shallow layer CNN for classification of image patches of cervical images as cancerous or not cancerous. We used cervix images acquired after the application of 3%−5% acetic acid using an Android device in 102 women. Of these, 42 cervix images belonged in the VIA-positive category (pathologic) and 60 in the VIA-negative category (healthy controls). A total of 275 image patches of 15 × 15 pixels were manually extracted from VIA-positive areas, and we considered these patches as positive examples. Similarly, 409 image patches were extracted from VIA-negative areas and were labeled as VIA negative. These image patches were classified using a shallow layer CNN composed of a layer each of convolutional, rectified linear unit, pooling, and two fully connected layers. A classification accuracy of 100% is achieved using shallow CNN.

Articles with similar content:

Normative Forecasting and Optimal Control of Multidimensional Objects Using a Self-Organization of a System of Non-Physical Models
Journal of Automation and Information Sciences, Vol.29, 1997, issue 4-5
Grigoriy A. Ivakhnenko, Alexey G. Ivakhnenko
Analysis of Parallel Algorithm of Empirical Models Synthesis on Principles of Genetic Algorithms
Journal of Automation and Information Sciences, Vol.48, 2016, issue 2
Alla N. Lazoriv , Vera M. Medvedchuk , Mikhail I. Gorbiychuk
Pattern Classification of Images from Acetic Acid–Based Cervical Cancer Screening: A Review
Critical Reviews™ in Biomedical Engineering, Vol.46, 2018, issue 2
Keerthana Prasad, Vidya Kudva
Jae Hwa Lee, Hyung Jin Sung
Dietary Turmeric Post-Treatment Decreases DMBA-Induced Hamster Buccal Pouch Tumor Growth by Altering Cell Proliferation and Apoptosis-Related Markers
Journal of Environmental Pathology, Toxicology and Oncology, Vol.31, 2012, issue 4
Pooja Tajpara, Gaurav Kumar, Girish Maru