Imperial College London
Alternate

Professor Tom Bourne

Faculty of Medicine, Department of Metabolism, Digestion and Reproduction

Chair in Gynaecology
 
 
 
//

Contact

 

+44 (0)20 3313 5131t.bourne Website

 
 
//

Location

 

Early pregnancy and acute gynaecologyInstitute of Reproductive and Developmental BiologyHammersmith Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Martínez-Más:2019:10.1371/journal.pone.0219388,
author = {Martínez-Más, J and Bueno-Crespo, A and Khazendar, S and Remezal-Solano, M and Martínez-Cendán, J-P and Jassim, S and Du, H and Al, Assam H and Bourne, T and Timmerman, D},
doi = {10.1371/journal.pone.0219388},
journal = {PLoS ONE},
pages = {1--14},
title = {Evaluation of machine learning methods with Fourier Transform features for classifying ovarian tumors based on ultrasound images},
url = {http://dx.doi.org/10.1371/journal.pone.0219388},
volume = {14},
year = {2019}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - IntroductionOvarian tumors are the most common diagnostic challenge for gynecologists and ultrasound examination has become the main technique for assessment of ovarian pathology and for preoperative distinction between malignant and benign ovarian tumors. However, ultrasonography is highly examiner-dependent and there may be an important variability between two different specialists when examining the same case. The objective of this work is the evaluation of different well-known Machine Learning (ML) systems to perform the automatic categorization of ovarian tumors from ultrasound images.MethodsWe have used a real patient database whose input features have been extracted from 348 images, from the IOTA tumor images database, holding together with the class labels of the images. For each patient case and ultrasound image, its input features have been previously extracted using Fourier descriptors computed on the Region Of Interest (ROI). Then, four ML techniques are considered for performing the classification stage: K-Nearest Neighbors (KNN), Linear Discriminant (LD), Support Vector Machine (SVM) and Extreme Learning Machine (ELM).ResultsAccording to our obtained results, the KNN classifier provides inaccurate predictions (less than 60% of accuracy) independently of the size of the local approximation, whereas the classifiers based on LD, SVM and ELM are robust in this biomedical classification (more than 85% of accuracy).ConclusionsML methods can be efficiently used for developing the classification stage in computer-aided diagnosis systems of ovarian tumor from ultrasound images. These approaches are able to provide automatic classification with a high rate of accuracy. Future work should aim at enhancing the classifier design using ensemble techniques. Another ongoing work is to exploit different kind of features extracted from ultrasound images.
AU  - Martínez-Más,J
AU  - Bueno-Crespo,A
AU  - Khazendar,S
AU  - Remezal-Solano,M
AU  - Martínez-Cendán,J-P
AU  - Jassim,S
AU  - Du,H
AU  - Al,Assam H
AU  - Bourne,T
AU  - Timmerman,D
DO  - 10.1371/journal.pone.0219388
EP  - 14
PY  - 2019///
SN  - 1932-6203
SP  - 1
TI  - Evaluation of machine learning methods with Fourier Transform features for classifying ovarian tumors based on ultrasound images
T2  - PLoS ONE
UR  - http://dx.doi.org/10.1371/journal.pone.0219388
UR  - https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0219388
UR  - http://hdl.handle.net/10044/1/72309
VL  - 14
ER  -
Download