Predicting malignancy from mammography findings and image–guided core biopsies. (1st January 2015)

• Record Type: Journal Article
• Authors: Ferreira, Pedro; Fonseca, Nuno A.; Dutra, Inês; Woods, Ryan; Burnside, Elizabeth
• Is Part Of: International journal of data mining and bioinformatics. Volume 11:Number 3(2015)
• Page Start: 257
• Page End: 276
• Publication Date: 2015-01-01
• Subjects: machine learning -- mammography -- BI–RADS -- malignancy prediction -- mammograms -- image–guided core biopsies -- mass density predictor -- breast cancer -- support vector machines -- SVM -- bioinformatics; Data mining -- Periodicals; Bioinformatics -- Periodicals; 006.312
• DOI: 10.1504/IJDMB.2015.067319
• Languages: English
• ISSNs: 1748-5673

Abstract

The main goal of this work is to produce machine learning models that predict the outcome of a mammography from a reduced set of annotated mammography findings. In the study we used a dataset consisting of 348 consecutive breast masses that underwent image guided core biopsy performed between October 2005 and December 2007 on 328 female subjects. We applied various algorithms with parameter variation to learn from the data. The tasks were to predict mass density and to predict malignancy. The best classifier that predicts mass density is based on a support vector machine and has accuracy of 81.3%. The expert correctly annotated 70% of the mass densities. The best classifier that predicts malignancy is also based on a support vector machine and has accuracy of 85.6%, with a positive predictive value of 85%. One important contribution of this work is that our model can predict malignancy in the absence of the mass density attribute, since we can fill up this attribute using our mass density predictor.