Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2017 Mar:63:468-475.
doi: 10.1016/j.patcog.2016.09.027. Epub 2016 Sep 22.

Multi-feature based Benchmark for Cervical Dysplasia Classification Evaluation

Tao Xu  1 , Han Zhang  2 , Cheng Xin  1 , Edward Kim  3 , L Rodney Long  4 , Zhiyun Xue  4 , Sameer Antani  4 , Xiaolei Huang  1
Affiliations

Multi-feature based Benchmark for Cervical Dysplasia Classification Evaluation

Tao Xu et al. Pattern Recognit. 2017 Mar.

Abstract

Cervical cancer is one of the most common types of cancer in women worldwide. Most deaths due to the disease occur in less developed areas of the world. In this work, we introduce a new image dataset along with expert annotated diagnoses for evaluating image-based cervical disease classification algorithms. A large number of Cervigram® images are selected from a database provided by the US National Cancer Institute. For each image, we extract three complementary pyramid features: Pyramid histogram in L*A*B* color space (PLAB), Pyramid Histogram of Oriented Gradients (PHOG), and Pyramid histogram of Local Binary Patterns (PLBP). Other than hand-crafted pyramid features, we investigate the performance of convolutional neural network (CNN) features for cervical disease classification. Our experimental results demonstrate the effectiveness of both our hand-crafted and our deep features. We intend to release this multi-feature dataset and our extensive evaluations using seven classic classifiers can serve as the baseline.

Keywords: Cervical cancer screening; computer aided diagnosis; convolutional neural network; image classification; local binary patterns; pyramid histogram.

PubMed Disclaimer

Figures

Figure 1
Figure 1
Illustration of visual observations in Cervigrams
Figure 2
Figure 2
Image features extraction
Figure 3
Figure 3
Comparison of PLBP-PLAB-PHOG and PLAB-PHOG feature descriptors
Figure 4
Figure 4
Comparison of seven classifiers based on PLBP-PLAB-PHOG feature.
Figure 5
Figure 5
Results of CNN features
Figure 6
Figure 6
False positive (1st row) and true positive (2nd row) examples as diagnosed by the CNN classifier.
See this image and copyright information in PMC

References

    1. WHO. Summary report, ICO Information Centre on HPV and Cancer. Aug, 2014. Human papillomavirus and related cancers in the world.
    1. Kim E, Huang X. A data driven approach to cervigram image analysis and classification. Color Medical Image analysis, Lecture Notes in Computational Vision and Biomechanics. 2013;6:1–13.
    1. Sankaranarayanan R, Gaffikin L, Jacob M, et al. A critical assessment of screening methods for cervical neoplasia. International Journal of Gynecology and Obstetrics. 2005;89:4–12. - PubMed
    1. Biscotti CV, Dawson AE, et al. Assisted primary screening using the automated thinprep imaging system. American Journal of Clinical Pathology. 2005;123(2):281–287. - PubMed
    1. Wilbur DC, Black-Schaffer WS, Luff RD, et al. The becton dickinson focalpoint gs imaging system: Clinical trials demonstrate significantly improved sensitivity for the detection of important cervical lesions. American Journal of Clinical Pathology. 2009;132(5):767–775. - PubMed