Predicting malignancy from mammography findings and image-guided core biopsies

Pedro Ferreira, Nuno A. Fonseca, Inês Dutra, Ryan Woods, Elizabeth Burnside

Research output: Contribution to journalArticle

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.

Original languageEnglish (US)
Pages (from-to)257-276
Number of pages20
JournalInternational Journal of Data Mining and Bioinformatics
Volume11
Issue number3
DOIs
StatePublished - 2015

Fingerprint

Image-Guided Biopsy
Mammography
Biopsy
Support vector machines
Classifiers
Learning systems
Neoplasms
Breast
expert
Support Vector Machine
learning

Keywords

  • BI-RADS
  • Machine learning
  • Mammography

ASJC Scopus subject areas

  • Library and Information Sciences
  • Information Systems
  • Biochemistry, Genetics and Molecular Biology(all)
  • Medicine(all)

Cite this

Predicting malignancy from mammography findings and image-guided core biopsies. / Ferreira, Pedro; Fonseca, Nuno A.; Dutra, Inês; Woods, Ryan; Burnside, Elizabeth.

In: International Journal of Data Mining and Bioinformatics, Vol. 11, No. 3, 2015, p. 257-276.

Research output: Contribution to journalArticle

Ferreira, Pedro ; Fonseca, Nuno A. ; Dutra, Inês ; Woods, Ryan ; Burnside, Elizabeth. / Predicting malignancy from mammography findings and image-guided core biopsies. In: International Journal of Data Mining and Bioinformatics. 2015 ; Vol. 11, No. 3. pp. 257-276.
@article{86331e50e7bb4f5eb6db844f5ad085c2,
title = "Predicting malignancy from mammography findings and image-guided core biopsies",
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.",
keywords = "BI-RADS, Machine learning, Mammography",
author = "Pedro Ferreira and Fonseca, {Nuno A.} and In{\^e}s Dutra and Ryan Woods and Elizabeth Burnside",
year = "2015",
doi = "10.1504/IJDMB.2015.067319",
language = "English (US)",
volume = "11",
pages = "257--276",
journal = "International Journal of Data Mining and Bioinformatics",
issn = "1748-5673",
publisher = "Inderscience Enterprises Ltd",
number = "3",

}

TY - JOUR

T1 - Predicting malignancy from mammography findings and image-guided core biopsies

AU - Ferreira, Pedro

AU - Fonseca, Nuno A.

AU - Dutra, Inês

AU - Woods, Ryan

AU - Burnside, Elizabeth

PY - 2015

Y1 - 2015

N2 - 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.

AB - 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.

KW - BI-RADS

KW - Machine learning

KW - Mammography

UR - http://www.scopus.com/inward/record.url?scp=84922550454&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84922550454&partnerID=8YFLogxK

U2 - 10.1504/IJDMB.2015.067319

DO - 10.1504/IJDMB.2015.067319

M3 - Article

C2 - 26333262

AN - SCOPUS:84922550454

VL - 11

SP - 257

EP - 276

JO - International Journal of Data Mining and Bioinformatics

JF - International Journal of Data Mining and Bioinformatics

SN - 1748-5673

IS - 3

ER -