skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Combining two mammographic projections in a computer aided mass detection method

Abstract

A method is presented to improve computer aided detection (CAD) results for masses in mammograms by fusing information obtained from two views of the same breast. It is based on a previously developed approach to link potentially suspicious regions in mediolateral oblique (MLO) and craniocaudal (CC) views. Using correspondence between regions, we extended our CAD scheme by building a cascaded multiple-classifier system, in which the last stage computes suspiciousness of an initially detected region conditional on the existence and similarity of a linked candidate region in the other view. We compared the two-view detection system with the single-view detection method using free-response receiver operating characteristic (FROC) analysis and cross validation. The dataset used in the evaluation consisted of 948 four-view mammograms, including 412 cancer cases with a mass, architectural distortion, or asymmetry. A statistically significant improvement was found in the lesion based detection performance. At a false positive (FP) rate of 0.1 FP/image, the lesion sensitivity improved from 56% to 61%. Case based sensitivity did not improve.

Authors:
;  [1]
  1. Department of Radiology, Radboud University Medical Centre Nijmegen, Geert Grooteplein Zuid 18, Nijmegen, 6525 GA (Netherlands)
Publication Date:
OSTI Identifier:
20951102
Resource Type:
Journal Article
Resource Relation:
Journal Name: Medical Physics; Journal Volume: 34; Journal Issue: 3; Other Information: DOI: 10.1118/1.2436974; (c) 2007 American Association of Physicists in Medicine; Country of input: International Atomic Energy Agency (IAEA)
Country of Publication:
United States
Language:
English
Subject:
62 RADIOLOGY AND NUCLEAR MEDICINE; ASYMMETRY; BIOMEDICAL RADIOGRAPHY; EVALUATION; IMAGES; MAMMARY GLANDS; PERFORMANCE; SENSITIVITY; SENSITIVITY ANALYSIS; VALIDATION

Citation Formats

Engeland, Saskia van, and Karssemeijer, Nico. Combining two mammographic projections in a computer aided mass detection method. United States: N. p., 2007. Web. doi:10.1118/1.2436974.
Engeland, Saskia van, & Karssemeijer, Nico. Combining two mammographic projections in a computer aided mass detection method. United States. doi:10.1118/1.2436974.
Engeland, Saskia van, and Karssemeijer, Nico. Thu . "Combining two mammographic projections in a computer aided mass detection method". United States. doi:10.1118/1.2436974.
@article{osti_20951102,
title = {Combining two mammographic projections in a computer aided mass detection method},
author = {Engeland, Saskia van and Karssemeijer, Nico},
abstractNote = {A method is presented to improve computer aided detection (CAD) results for masses in mammograms by fusing information obtained from two views of the same breast. It is based on a previously developed approach to link potentially suspicious regions in mediolateral oblique (MLO) and craniocaudal (CC) views. Using correspondence between regions, we extended our CAD scheme by building a cascaded multiple-classifier system, in which the last stage computes suspiciousness of an initially detected region conditional on the existence and similarity of a linked candidate region in the other view. We compared the two-view detection system with the single-view detection method using free-response receiver operating characteristic (FROC) analysis and cross validation. The dataset used in the evaluation consisted of 948 four-view mammograms, including 412 cancer cases with a mass, architectural distortion, or asymmetry. A statistically significant improvement was found in the lesion based detection performance. At a false positive (FP) rate of 0.1 FP/image, the lesion sensitivity improved from 56% to 61%. Case based sensitivity did not improve.},
doi = {10.1118/1.2436974},
journal = {Medical Physics},
number = 3,
volume = 34,
place = {United States},
year = {Thu Mar 15 00:00:00 EDT 2007},
month = {Thu Mar 15 00:00:00 EDT 2007}
}