Evaluation of machine learning methods with Fourier Transform features for classifying ovarian tumors based on ultrasound images

• Published in: PloS one Vol. 14; no. 7; p. e0219388
• Main Authors: Martínez-Más, José, Bueno-Crespo, Andrés, Khazendar, Shan, Remezal-Solano, Manuel, Martínez-Cendán, Juan-Pedro, Jassim, Sabah, Du, Hongbo, Al Assam, Hisham, Bourne, Tom, Timmerman, Dirk
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 26.07.2019; Public Library of Science (PLoS)
• Subjects: Algorithms; Area Under Curve; Artificial intelligence; Artificial neural networks; Classification; Classifiers; Computer aided medical diagnosis; Computer and Information Sciences; Computer science; Data bases; Diagnosis; Diagnostic imaging; Diagnostic systems; Diagnostic ultrasonography; Evaluation; Extreme values; Feature extraction; Female; Fourier Analysis; Fourier transforms; Gynecology; Humans; Identification and classification; Image classification; Image Processing, Computer-Assisted; International conferences; K nearest neighbour classification tree analysis; K-nearest neighbors algorithm; Learning algorithms; Machine Learning; Medical imaging; Medical research; Medicine and Health Sciences; Methods; Neural networks; Obstetrics; Ovarian cancer; Ovarian Neoplasms - diagnostic imaging; Ovarian tumors; Physical Sciences; Research and Analysis Methods; ROC Curve; Support vector machines; Technology application; Tumors; Ultrasonic imaging; Ultrasonic testing; Ultrasonography; Ultrasound; Ultrasound imaging; Womens health; Spain; New York; United Kingdom > UK; Belgium; United States > US
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0219388

Ovarian 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. We 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). According 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). ML 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.