Journal of the European Society for Gynaecological Endoscopy

esge_logo

Automated characterisation of ultrasound images of ovarian tumours: the diagnostic accuracy of a support vector machine and image processing with a local binary pattern operator

S. Khazendar1, A. Sayasneh2, H. Al-Assam1, H. Du1, J. Kaijser3, L. Ferrara4, D. Timmerman3, S. Jassim1, T. Bourne2, 3, 4

1Department of Applied Computing, University of Buckingham, Buckingham MK18 1EG, UK.

2Department of Cancer and Surgery, Queen Charlotte’s and Chelsea Hospital, Imperial College, London W12 0HS, UK.

3KU Leuven Department of Development and Regeneration; Obstetrics and Gynaecology, University Hospitals KU Leuven, Leuven, Belgium.

4Queen Charlotte’s and Chelsea Hospital, Imperial College, London W12 0HS, UK.

Correspondence at: Dr Ahmad Sayasneh MRCOG. Department of Cancer and Surgery, Imperial College London, Hammersmith Campus, Du Cane Road, W12 0HS London, UK. E-mail: a.sayasneh@imperial.ac.uk

Keywords:

Decision support techniques, ovarian cancer, ovarian neoplasm, Support Vector Machines, ultrasonography


Published online: Mar 31 2015

Abstract

Introduction: Preoperative characterisation of ovarian masses into benign or malignant is of paramount importance to optimise patient management. Objectives: In this study, we developed and validated a computerised model to characterise ovarian masses as benign or malignant.
Materials and methods: Transvaginal 2D B mode static ultrasound images of 187 ovarian masses with known histological diagnosis were included. Images were first pre-processed and enhanced, and Local Binary Pattern Histograms were then extracted from 2 × 2 blocks of each image. A Support Vector Machine (SVM) was trained using stratified cross validation with randomised sampling. The process was repeated 15 times and in each round 100 images were randomly selected.
Results: The SVM classified the original non-treated static images as benign or malignant masses with an average accuracy of 0.62 (95% CI: 0.59-0.65). This performance significantly improved to an average accuracy of 0.77 (95% CI: 0.75-0.79) when images were pre-processed, enhanced and treated with a Local Binary Pattern operator (mean difference 0.15: 95% 0.11-0.19, p < 0.0001, two-tailed t test).
Conclusion: We have shown that an SVM can classify static 2D B mode ultrasound images of ovarian masses into benign and malignant categories. The accuracy improves if texture related LBP features extracted from the images are considered.