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

Title: Computer aided detection of clusters of microcalcifications on full field digital mammograms

Abstract

We are developing a computer-aided detection (CAD) system to identify microcalcification clusters (MCCs) automatically on full field digital mammograms (FFDMs). The CAD system includes six stages: preprocessing; image enhancement; segmentation of microcalcification candidates; false positive (FP) reduction for individual microcalcifications; regional clustering; and FP reduction for clustered microcalcifications. At the stage of FP reduction for individual microcalcifications, a truncated sum-of-squares error function was used to improve the efficiency and robustness of the training of an artificial neural network in our CAD system for FFDMs. At the stage of FP reduction for clustered microcalcifications, morphological features and features derived from the artificial neural network outputs were extracted from each cluster. Stepwise linear discriminant analysis (LDA) was used to select the features. An LDA classifier was then used to differentiate clustered microcalcifications from FPs. A data set of 96 cases with 192 images was collected at the University of Michigan. This data set contained 96 MCCs, of which 28 clusters were proven by biopsy to be malignant and 68 were proven to be benign. The data set was separated into two independent data sets for training and testing of the CAD system in a cross-validation scheme. When one data set was usedmore » to train and validate the convolution neural network (CNN) in our CAD system, the other data set was used to evaluate the detection performance. With the use of a truncated error metric, the training of CNN could be accelerated and the classification performance was improved. The CNN in combination with an LDA classifier could substantially reduce FPs with a small tradeoff in sensitivity. By using the free-response receiver operating characteristic methodology, it was found that our CAD system can achieve a cluster-based sensitivity of 70, 80, and 90 % at 0.21, 0.61, and 1.49 FPs/image, respectively. For case-based performance evaluation, a sensitivity of 70, 80, and 90 % can be achieved at 0.07, 0.17, and 0.65 FPs/image, respectively. We also used a data set of 216 mammograms negative for clustered microcalcifications to further estimate the FP rate of our CAD system. The corresponding FP rates were 0.15, 0.31, and 0.86 FPs/image for cluster-based detection when negative mammograms were used for estimation of FP rates.« less

Authors:
; ; ; ; ; ;  [1]
  1. Department of Radiology, University of Michigan, Ann Arbor, Michigan 48109-0904 (United States)
Publication Date:
OSTI Identifier:
20853398
Resource Type:
Journal Article
Journal Name:
Medical Physics
Additional Journal Information:
Journal Volume: 33; Journal Issue: 8; Other Information: DOI: 10.1118/1.2211710; (c) 2006 American Association of Physicists in Medicine; Country of input: International Atomic Energy Agency (IAEA); Journal ID: ISSN 0094-2405
Country of Publication:
United States
Language:
English
Subject:
62 RADIOLOGY AND NUCLEAR MEDICINE; BIOMEDICAL RADIOGRAPHY; BIOPSY; CARCINOMAS; CLASSIFICATION; EFFICIENCY; ERRORS; IMAGE PROCESSING; IMAGES; MAMMARY GLANDS; NEURAL NETWORKS; PERFORMANCE; SENSITIVITY; SENSITIVITY ANALYSIS; TRAINING; VALIDATION

Citation Formats

Jun, Ge, Sahiner, Berkman, Hadjiiski, Lubomir M, Chan, H -P, Jun, Wei, Helvie, Mark A, and Chuan, Zhou. Computer aided detection of clusters of microcalcifications on full field digital mammograms. United States: N. p., 2006. Web. doi:10.1118/1.2211710.
Jun, Ge, Sahiner, Berkman, Hadjiiski, Lubomir M, Chan, H -P, Jun, Wei, Helvie, Mark A, & Chuan, Zhou. Computer aided detection of clusters of microcalcifications on full field digital mammograms. United States. doi:10.1118/1.2211710.
Jun, Ge, Sahiner, Berkman, Hadjiiski, Lubomir M, Chan, H -P, Jun, Wei, Helvie, Mark A, and Chuan, Zhou. Tue . "Computer aided detection of clusters of microcalcifications on full field digital mammograms". United States. doi:10.1118/1.2211710.
@article{osti_20853398,
title = {Computer aided detection of clusters of microcalcifications on full field digital mammograms},
author = {Jun, Ge and Sahiner, Berkman and Hadjiiski, Lubomir M and Chan, H -P and Jun, Wei and Helvie, Mark A and Chuan, Zhou},
abstractNote = {We are developing a computer-aided detection (CAD) system to identify microcalcification clusters (MCCs) automatically on full field digital mammograms (FFDMs). The CAD system includes six stages: preprocessing; image enhancement; segmentation of microcalcification candidates; false positive (FP) reduction for individual microcalcifications; regional clustering; and FP reduction for clustered microcalcifications. At the stage of FP reduction for individual microcalcifications, a truncated sum-of-squares error function was used to improve the efficiency and robustness of the training of an artificial neural network in our CAD system for FFDMs. At the stage of FP reduction for clustered microcalcifications, morphological features and features derived from the artificial neural network outputs were extracted from each cluster. Stepwise linear discriminant analysis (LDA) was used to select the features. An LDA classifier was then used to differentiate clustered microcalcifications from FPs. A data set of 96 cases with 192 images was collected at the University of Michigan. This data set contained 96 MCCs, of which 28 clusters were proven by biopsy to be malignant and 68 were proven to be benign. The data set was separated into two independent data sets for training and testing of the CAD system in a cross-validation scheme. When one data set was used to train and validate the convolution neural network (CNN) in our CAD system, the other data set was used to evaluate the detection performance. With the use of a truncated error metric, the training of CNN could be accelerated and the classification performance was improved. The CNN in combination with an LDA classifier could substantially reduce FPs with a small tradeoff in sensitivity. By using the free-response receiver operating characteristic methodology, it was found that our CAD system can achieve a cluster-based sensitivity of 70, 80, and 90 % at 0.21, 0.61, and 1.49 FPs/image, respectively. For case-based performance evaluation, a sensitivity of 70, 80, and 90 % can be achieved at 0.07, 0.17, and 0.65 FPs/image, respectively. We also used a data set of 216 mammograms negative for clustered microcalcifications to further estimate the FP rate of our CAD system. The corresponding FP rates were 0.15, 0.31, and 0.86 FPs/image for cluster-based detection when negative mammograms were used for estimation of FP rates.},
doi = {10.1118/1.2211710},
journal = {Medical Physics},
issn = {0094-2405},
number = 8,
volume = 33,
place = {United States},
year = {2006},
month = {8}
}