Bilateral image subtraction features for multivariate automated classification of breast cancer risk

Jose M. Celaya-Padilla, Juan Rodriguez-Rojas, Jorge I. Galván-Tejada, Antonio Martínez-Torteya, Victor Treviño, José G. Tamez-Peña

Research output: Contribution to conferencePaper

3 Citations (Scopus)

Abstract

Early tumor detection is key in reducing breast cancer deaths and screening mammography is the most widely available method for early detection. However, mammogram interpretation is based on human radiologist, whose radiological skills, experience and workload makes radiological interpretation inconsistent. In an attempt to make mammographic interpretation more consistent, computer aided diagnosis (CADx) systems has been introduced. This paper presents an CADx system aimed to automatically triage normal mammograms form suspicious mammograms. The CADx system co-reregister the left and breast images, then extracts image features from the co-registered mammographic bilateral sets. Finally, an optimal logistic multivariate model is generated by means of an evolutionary search engine. In this study, 440 subjects form the DDSM public data sets were used: 44 normal mammograms, 201 malignant mass mammograms, and 195 mammograms with malignant calci cations. The results showed a cross validation accuracy of 0.88 and an area under receiver operating characteristic (AUC) of 0.89 for the calci cations vs. normal mammograms. The optimal mass vs. normal mammograms model obtained an accuracy of 0.85 and an AUC of 0.88. © 2014 SPIE.
Original languageEnglish
DOIs
Publication statusPublished - 1 Jan 2014
Externally publishedYes
EventProgress in Biomedical Optics and Imaging - Proceedings of SPIE -
Duration: 1 Jan 2014 → …

Conference

ConferenceProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Period1/1/14 → …

Fingerprint

subtraction
breast
Area Under Curve
Cations
cancer
Positive ions
Breast Neoplasms
Computer aided diagnosis
Search Engine
Mammography
Triage
Search engines
Workload
Early Detection of Cancer
ROC Curve
Logistics
Tumors
cations
Screening
Breast

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Atomic and Molecular Physics, and Optics
  • Biomaterials
  • Radiology Nuclear Medicine and imaging

Cite this

Celaya-Padilla, J. M., Rodriguez-Rojas, J., Galván-Tejada, J. I., Martínez-Torteya, A., Treviño, V., & Tamez-Peña, J. G. (2014). Bilateral image subtraction features for multivariate automated classification of breast cancer risk. Paper presented at Progress in Biomedical Optics and Imaging - Proceedings of SPIE, . https://doi.org/10.1117/12.2043870
Celaya-Padilla, Jose M. ; Rodriguez-Rojas, Juan ; Galván-Tejada, Jorge I. ; Martínez-Torteya, Antonio ; Treviño, Victor ; Tamez-Peña, José G. / Bilateral image subtraction features for multivariate automated classification of breast cancer risk. Paper presented at Progress in Biomedical Optics and Imaging - Proceedings of SPIE, .
@conference{0b2eea326d514d2e8495b63b3ce0c7b3,
title = "Bilateral image subtraction features for multivariate automated classification of breast cancer risk",
abstract = "Early tumor detection is key in reducing breast cancer deaths and screening mammography is the most widely available method for early detection. However, mammogram interpretation is based on human radiologist, whose radiological skills, experience and workload makes radiological interpretation inconsistent. In an attempt to make mammographic interpretation more consistent, computer aided diagnosis (CADx) systems has been introduced. This paper presents an CADx system aimed to automatically triage normal mammograms form suspicious mammograms. The CADx system co-reregister the left and breast images, then extracts image features from the co-registered mammographic bilateral sets. Finally, an optimal logistic multivariate model is generated by means of an evolutionary search engine. In this study, 440 subjects form the DDSM public data sets were used: 44 normal mammograms, 201 malignant mass mammograms, and 195 mammograms with malignant calci cations. The results showed a cross validation accuracy of 0.88 and an area under receiver operating characteristic (AUC) of 0.89 for the calci cations vs. normal mammograms. The optimal mass vs. normal mammograms model obtained an accuracy of 0.85 and an AUC of 0.88. {\circledC} 2014 SPIE.",
author = "Celaya-Padilla, {Jose M.} and Juan Rodriguez-Rojas and Galv{\'a}n-Tejada, {Jorge I.} and Antonio Mart{\'i}nez-Torteya and Victor Trevi{\~n}o and Tamez-Pe{\~n}a, {Jos{\'e} G.}",
year = "2014",
month = "1",
day = "1",
doi = "10.1117/12.2043870",
language = "English",
note = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE ; Conference date: 01-01-2014",

}

Celaya-Padilla, JM, Rodriguez-Rojas, J, Galván-Tejada, JI, Martínez-Torteya, A, Treviño, V & Tamez-Peña, JG 2014, 'Bilateral image subtraction features for multivariate automated classification of breast cancer risk' Paper presented at Progress in Biomedical Optics and Imaging - Proceedings of SPIE, 1/1/14, . https://doi.org/10.1117/12.2043870

Bilateral image subtraction features for multivariate automated classification of breast cancer risk. / Celaya-Padilla, Jose M.; Rodriguez-Rojas, Juan; Galván-Tejada, Jorge I.; Martínez-Torteya, Antonio; Treviño, Victor; Tamez-Peña, José G.

2014. Paper presented at Progress in Biomedical Optics and Imaging - Proceedings of SPIE, .

Research output: Contribution to conferencePaper

TY - CONF

T1 - Bilateral image subtraction features for multivariate automated classification of breast cancer risk

AU - Celaya-Padilla, Jose M.

AU - Rodriguez-Rojas, Juan

AU - Galván-Tejada, Jorge I.

AU - Martínez-Torteya, Antonio

AU - Treviño, Victor

AU - Tamez-Peña, José G.

PY - 2014/1/1

Y1 - 2014/1/1

N2 - Early tumor detection is key in reducing breast cancer deaths and screening mammography is the most widely available method for early detection. However, mammogram interpretation is based on human radiologist, whose radiological skills, experience and workload makes radiological interpretation inconsistent. In an attempt to make mammographic interpretation more consistent, computer aided diagnosis (CADx) systems has been introduced. This paper presents an CADx system aimed to automatically triage normal mammograms form suspicious mammograms. The CADx system co-reregister the left and breast images, then extracts image features from the co-registered mammographic bilateral sets. Finally, an optimal logistic multivariate model is generated by means of an evolutionary search engine. In this study, 440 subjects form the DDSM public data sets were used: 44 normal mammograms, 201 malignant mass mammograms, and 195 mammograms with malignant calci cations. The results showed a cross validation accuracy of 0.88 and an area under receiver operating characteristic (AUC) of 0.89 for the calci cations vs. normal mammograms. The optimal mass vs. normal mammograms model obtained an accuracy of 0.85 and an AUC of 0.88. © 2014 SPIE.

AB - Early tumor detection is key in reducing breast cancer deaths and screening mammography is the most widely available method for early detection. However, mammogram interpretation is based on human radiologist, whose radiological skills, experience and workload makes radiological interpretation inconsistent. In an attempt to make mammographic interpretation more consistent, computer aided diagnosis (CADx) systems has been introduced. This paper presents an CADx system aimed to automatically triage normal mammograms form suspicious mammograms. The CADx system co-reregister the left and breast images, then extracts image features from the co-registered mammographic bilateral sets. Finally, an optimal logistic multivariate model is generated by means of an evolutionary search engine. In this study, 440 subjects form the DDSM public data sets were used: 44 normal mammograms, 201 malignant mass mammograms, and 195 mammograms with malignant calci cations. The results showed a cross validation accuracy of 0.88 and an area under receiver operating characteristic (AUC) of 0.89 for the calci cations vs. normal mammograms. The optimal mass vs. normal mammograms model obtained an accuracy of 0.85 and an AUC of 0.88. © 2014 SPIE.

U2 - 10.1117/12.2043870

DO - 10.1117/12.2043870

M3 - Paper

ER -

Celaya-Padilla JM, Rodriguez-Rojas J, Galván-Tejada JI, Martínez-Torteya A, Treviño V, Tamez-Peña JG. Bilateral image subtraction features for multivariate automated classification of breast cancer risk. 2014. Paper presented at Progress in Biomedical Optics and Imaging - Proceedings of SPIE, . https://doi.org/10.1117/12.2043870