Article

Ovarian Tumor Characterization Using 3D Ultrasound

Department of Electronics and Computer Engineering, Ngee Ann Polytechnic, Singapore. .
Technology in cancer research & treatment (Impact Factor: 1.73). 07/2012; 11(6). DOI: 10.7785/tcrt.2012.500272
Source: PubMed

ABSTRACT

Among gynecological malignancies, ovarian cancer is the most frequent cause of death. _Preoperative determination of whether a tumor is benign or malignant has often been found to be difficult. Because of such inconclusive findings from ultrasound images and other tests, many patients with benign conditions have been offered unnecessary surgeries thereby increasing patient anxiety and healthcare cost. The key objective of our work is to develop an adjunct Computer Aided Diagnostic (CAD) technique that uses ultrasound images of the ovary and image mining algorithms to accurately classify benign and malignant ovarian tumor images. In this algorithm, we extract texture features based on Local Binary Patterns (LBP) and Laws Texture Energy (LTE) and use them to build and train a Support Vector Machine (SVM) classifier. Our technique was validated using 1000 benign and 1000 malignant images, and we obtained a high accuracy of 99.9% using a SVM classifier with a Radial Basis Function (RBF) kernel. The high accuracy can be attributed to the determination of the novel combination of the 16 texture based features that quantify the subtle changes in the images belonging to both classes. The proposed algorithm has the following characteristics: cost-effectiveness, complete automation, easy deployment, and good end-user comprehensibility. We have also developed a novel integrated index, Ovarian Cancer Index (OCI), which is a combination of the texture features, to present the physicians with a more transparent adjunct technique for ovarian tumor classification.

4 Followers
 · 
18 Reads
    • "Local masks can be used to detect various types of textures and then estimate their energy . A set of three 1-D vector convolution masks were used to compute Laws' texture energy (LTE) (Acharya et al. 2012a ). Their names (L3,E3,S3) describe their function , that is, the level, edge and spot features, respectively. "
    [Show abstract] [Hide abstract]
    ABSTRACT: The discrimination between benign and malignant adnexal masses in ultrasound images represents one of the most challenging problems in gynecologic practice. In the study described here, a new method for automatic discrimination of adnexal masses based on a neural networks approach was tested. The proposed method first calculates seven different types of characteristics (local binary pattern, fractal dimension, entropy, invariant moments, gray level co-occurrence matrix, law texture energy and Gabor wavelet) from ultrasound images of the ovary, from which several features are extracted and collected together with the clinical patient age. The proposed technique was validated using 106 benign and 39 malignant images obtained from 145 patients, corresponding to its probability of appearance in general population. On evaluation of the classifier, an accuracy of 98.78%, sensitivity of 98.50%, specificity of 98.90% and area under the curve of 0.997 were calculated.
    No preview · Article · Dec 2015 · Ultrasound in medicine & biology
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Among gynecological malignancies, ovarian cancer is the most frequent cause of death. Image mining algorithms have been predominantly used to give the physicians a more objective, fast, and accurate second opinion on the initial diagnosis made from medical images. The objective of this work is to develop an adjunct computer-aided diagnostic technique that uses 3D ultrasound images of the ovary to accurately characterize and classify benign and malignant ovarian tumors. In this algorithm, we first extract features based on the textural changes and higher-order spectra information. The significant features are then selected and used to train and evaluate the decision tree (DT) classifier. The proposed technique was validated using 1,000 benign and 1,000 malignant images, obtained from ten patients with benign and ten with malignant disease, respectively. On evaluating the classifier with tenfold stratified cross validation, the DT classifier presented a high accuracy of 97 %, sensitivity of 94.3 %, and specificity of 99.7 %. This high accuracy was achieved because of the use of the novel combination of the four features which adequately quantify the subtle changes and the nonlinearities in the pixel intensity variations. The rules output by the DT classifier are comprehensible to the end-user and, hence, allow the physicians to more confidently accept the results. The preliminary results show that the features are discriminative enough to yield good accuracy. Moreover, the proposed technique is completely automated, accurate, and can be easily written as a software application for use in any computer.
    Full-text · Article · Nov 2012 · Journal of Digital Imaging
  • [Show abstract] [Hide abstract]
    ABSTRACT: Among gynecological malignancies, ovarian cancer is the most frequent cause of death. Image mining algorithms have been predominantly used to give the physicians a more objective, fast, and accurate second opinion on the initial diagnosis made from medical images. The objective of this work is to develop an adjunct Computer-Aided Diagnostic (CAD) technique that uses 3D ultrasound images of the ovary to accurately characterize and classify benign and malignant ovarian tumors. In this algorithm, we first extract features based on the textural changes and higher-order spectra (HOS) information. The significant features are then selected and used to train and evaluate the decision tree (DT) classifier. The proposed technique was validated using 1,000 benign and 1,000 malignant images, obtained from ten patients with benign and ten with malignant disease, respectively. On evaluating the classifier with tenfold stratified cross validation, the DT classifier presented a high accuracy of 97 %, sensitivity of 94.3 %, and specificity of 99.7 %. This high accuracy was achieved because of the use of the novel combination of the four features which adequately quantify the subtle changes and the nonlinearities in the pixel intensity variations. The rules output by the DT classifier are comprehensible to the end user and, hence, allow the physicians to more confidently accept the results. The preliminary results show that the features are discriminative enough to yield good accuracy. Moreover, the proposed technique is completely automated and accurate and can be easily written as a software application for use in any computer.
    No preview · Chapter · Jan 2013
Show more