A study on several Machine-learning methods for classification of Malignant and benign clustered microcalcifications

• Published in: IEEE transactions on medical imaging Vol. 24; no. 3; pp. 371 - 380
• Main Authors: Liyang Wei, Yongyi Yang, Nishikawa, R.M., Yulei Jiang
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.03.2005; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Artificial Intelligence; Breast cancer; Breast Neoplasms - classification; Breast Neoplasms - diagnostic imaging; Calcinosis - classification; Calcinosis - diagnostic imaging; Clustered microcalcifications; Computer aided diagnosis; Female; Humans; Image databases; Kernel; kernel methods; Learning systems; Mammography; Neural networks; Pattern Recognition, Automated - methods; Precancerous Conditions - classification; Precancerous Conditions - diagnostic imaging; Radiographic Image Enhancement - methods; Radiographic Image Interpretation, Computer-Assisted - methods; relevance vector machine; Reproducibility of Results; Sensitivity and Specificity; Severity of Illness Index; Spatial databases; Statistical learning; Studies; Supervised learning; support vector machine; Support vector machine classification; Support vector machines
• ISSN: 0278-0062; 1558-254X
• DOI: 10.1109/TMI.2004.842457

In this paper, we investigate several state-of-the-art machine-learning methods for automated classification of clustered microcalcifications (MCs). The classifier is part of a computer-aided diagnosis (CADx) scheme that is aimed to assisting radiologists in making more accurate diagnoses of breast cancer on mammograms. The methods we considered were: support vector machine (SVM), kernel Fisher discriminant (KFD), relevance vector machine (RVM), and committee machines (ensemble averaging and AdaBoost), of which most have been developed recently in statistical learning theory. We formulated differentiation of malignant from benign MCs as a supervised learning problem, and applied these learning methods to develop the classification algorithm. As input, these methods used image features automatically extracted from clustered MCs. We tested these methods using a database of 697 clinical mammograms from 386 cases, which included a wide spectrum of difficult-to-classify cases. We analyzed the distribution of the cases in this database using the multidimensional scaling technique, which reveals that in the feature space the malignant cases are not trivially separable from the benign ones. We used receiver operating characteristic (ROC) analysis to evaluate and to compare classification performance by the different methods. In addition, we also investigated how to combine information from multiple-view mammograms of the same case so that the best decision can be made by a classifier. In our experiments, the kernel-based methods (i.e., SVM, KFD, and RVM) yielded the best performance (A/sub z/=0.85, SVM), significantly outperforming a well-established, clinically-proven CADx approach that is based on neural network (A/sub z/=0.80).