Bilateral Image Subtraction and Multivariate Models for the Automated Triaging of Screening Mammograms

José Celaya-Padilla, Antonio Martinez-Torteya, Juan Rodriguez-Rojas, Jorge Galvan-Tejada, Victor Treviño, José Tamez-Peña

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

Copyright © 2015 José Celaya-Padilla et al. Mammography is the most common and effective breast cancer screening test. However, the rate of positive findings is very low, making the radiologic interpretation monotonous and biased toward errors. This work presents a computer-aided diagnosis (CADx) method aimed to automatically triage mammogram sets. The method coregisters the left and right mammograms, extracts image features, and classifies the subjects into risk of having malignant calcifications (CS), malignant masses (MS), and healthy subject (HS). In this study, 449 subjects (197 CS, 207 MS, and 45 HS) from a public database were used to train and evaluate the CADx. Percentile-rank (p-rank) and z -normalizations were used. For the p -rank, the CS versus HS model achieved a cross-validation accuracy of 0.797 with an area under the receiver operating characteristic curve (AUC) of 0.882; the MS versus HS model obtained an accuracy of 0.772 and an AUC of 0.842. For the z -normalization, the CS versus HS model achieved an accuracy of 0.825 with an AUC of 0.882 and the MS versus HS model obtained an accuracy of 0.698 and an AUC of 0.807. The proposed method has the potential to rank cases with high probability of malignant findings aiding in the prioritization of radiologists work list.
Original languageEnglish
JournalBioMed Research International
DOIs
Publication statusPublished - 1 Jan 2015
Externally publishedYes

Fingerprint

Healthy Volunteers
Screening
Area Under Curve
Computer aided diagnosis
Mammography
Triage
Early Detection of Cancer
ROC Curve
Databases
Breast Neoplasms

All Science Journal Classification (ASJC) codes

  • Biochemistry, Genetics and Molecular Biology(all)
  • Immunology and Microbiology(all)

Cite this

Celaya-Padilla, José ; Martinez-Torteya, Antonio ; Rodriguez-Rojas, Juan ; Galvan-Tejada, Jorge ; Treviño, Victor ; Tamez-Peña, José. / Bilateral Image Subtraction and Multivariate Models for the Automated Triaging of Screening Mammograms. In: BioMed Research International. 2015.
@article{521e94f57fed4c59989a37c0afd9422b,
title = "Bilateral Image Subtraction and Multivariate Models for the Automated Triaging of Screening Mammograms",
abstract = "Copyright {\circledC} 2015 Jos{\'e} Celaya-Padilla et al. Mammography is the most common and effective breast cancer screening test. However, the rate of positive findings is very low, making the radiologic interpretation monotonous and biased toward errors. This work presents a computer-aided diagnosis (CADx) method aimed to automatically triage mammogram sets. The method coregisters the left and right mammograms, extracts image features, and classifies the subjects into risk of having malignant calcifications (CS), malignant masses (MS), and healthy subject (HS). In this study, 449 subjects (197 CS, 207 MS, and 45 HS) from a public database were used to train and evaluate the CADx. Percentile-rank (p-rank) and z -normalizations were used. For the p -rank, the CS versus HS model achieved a cross-validation accuracy of 0.797 with an area under the receiver operating characteristic curve (AUC) of 0.882; the MS versus HS model obtained an accuracy of 0.772 and an AUC of 0.842. For the z -normalization, the CS versus HS model achieved an accuracy of 0.825 with an AUC of 0.882 and the MS versus HS model obtained an accuracy of 0.698 and an AUC of 0.807. The proposed method has the potential to rank cases with high probability of malignant findings aiding in the prioritization of radiologists work list.",
author = "Jos{\'e} Celaya-Padilla and Antonio Martinez-Torteya and Juan Rodriguez-Rojas and Jorge Galvan-Tejada and Victor Trevi{\~n}o and Jos{\'e} Tamez-Pe{\~n}a",
year = "2015",
month = "1",
day = "1",
doi = "10.1155/2015/231656",
language = "English",
journal = "BioMed Research International",
issn = "2314-6133",
publisher = "Hindawi Publishing Corporation",

}

Bilateral Image Subtraction and Multivariate Models for the Automated Triaging of Screening Mammograms. / Celaya-Padilla, José; Martinez-Torteya, Antonio; Rodriguez-Rojas, Juan; Galvan-Tejada, Jorge; Treviño, Victor; Tamez-Peña, José.

In: BioMed Research International, 01.01.2015.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Bilateral Image Subtraction and Multivariate Models for the Automated Triaging of Screening Mammograms

AU - Celaya-Padilla, José

AU - Martinez-Torteya, Antonio

AU - Rodriguez-Rojas, Juan

AU - Galvan-Tejada, Jorge

AU - Treviño, Victor

AU - Tamez-Peña, José

PY - 2015/1/1

Y1 - 2015/1/1

N2 - Copyright © 2015 José Celaya-Padilla et al. Mammography is the most common and effective breast cancer screening test. However, the rate of positive findings is very low, making the radiologic interpretation monotonous and biased toward errors. This work presents a computer-aided diagnosis (CADx) method aimed to automatically triage mammogram sets. The method coregisters the left and right mammograms, extracts image features, and classifies the subjects into risk of having malignant calcifications (CS), malignant masses (MS), and healthy subject (HS). In this study, 449 subjects (197 CS, 207 MS, and 45 HS) from a public database were used to train and evaluate the CADx. Percentile-rank (p-rank) and z -normalizations were used. For the p -rank, the CS versus HS model achieved a cross-validation accuracy of 0.797 with an area under the receiver operating characteristic curve (AUC) of 0.882; the MS versus HS model obtained an accuracy of 0.772 and an AUC of 0.842. For the z -normalization, the CS versus HS model achieved an accuracy of 0.825 with an AUC of 0.882 and the MS versus HS model obtained an accuracy of 0.698 and an AUC of 0.807. The proposed method has the potential to rank cases with high probability of malignant findings aiding in the prioritization of radiologists work list.

AB - Copyright © 2015 José Celaya-Padilla et al. Mammography is the most common and effective breast cancer screening test. However, the rate of positive findings is very low, making the radiologic interpretation monotonous and biased toward errors. This work presents a computer-aided diagnosis (CADx) method aimed to automatically triage mammogram sets. The method coregisters the left and right mammograms, extracts image features, and classifies the subjects into risk of having malignant calcifications (CS), malignant masses (MS), and healthy subject (HS). In this study, 449 subjects (197 CS, 207 MS, and 45 HS) from a public database were used to train and evaluate the CADx. Percentile-rank (p-rank) and z -normalizations were used. For the p -rank, the CS versus HS model achieved a cross-validation accuracy of 0.797 with an area under the receiver operating characteristic curve (AUC) of 0.882; the MS versus HS model obtained an accuracy of 0.772 and an AUC of 0.842. For the z -normalization, the CS versus HS model achieved an accuracy of 0.825 with an AUC of 0.882 and the MS versus HS model obtained an accuracy of 0.698 and an AUC of 0.807. The proposed method has the potential to rank cases with high probability of malignant findings aiding in the prioritization of radiologists work list.

U2 - 10.1155/2015/231656

DO - 10.1155/2015/231656

M3 - Article

JO - BioMed Research International

JF - BioMed Research International

SN - 2314-6133

ER -