Automatic detection of normal mammograms, as a "first look" for breast cancer, is a new approach to computer-aided diagnosis. This approach may be limited, however, by two main causes. The first problem is the presence of poorly separable "crossed-distributions" in which the correct classification depends upon the value of each feature. The second problem is overlap of the feature distributions that are extracted from digitized mammograms of normal and abnormal patients. Here we introduce a new Support Vector Machine (SVM) based method utilizing with the proposed uncrossing mapping and Local Probability Difference (LPD). Crossed-distribution feature pairs are identified and mapped into a new features that can be separated by a zero-hyperplane of the new axis. The probability density functions of the features of normal and abnormal mammograms are then sampled and the local probability difference functions are estimated to enhance the features. From 1,000 ground-truth-known mammograms, 250 normal and 250 abnormal cases, including spiculated lesions, circumscribed masses or microcalcifications, are used for training a support vector machine. The classification results tested with another 250 normal and 250 abnormal sets show improved testing performances with 90% sensitivity and 89% specificity.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Werapon CHIRACHARIT, Yajie SUN, Pinit KUMHOM, Kosin CHAMNONGTHAI, Charles F. BABBS, Edward J. DELP, "Normal Mammogram Detection Based on Local Probability Difference Transforms and Support Vector Machines" in IEICE TRANSACTIONS on Information,
vol. E90-D, no. 1, pp. 258-270, January 2007, doi: .
Abstract: Automatic detection of normal mammograms, as a "first look" for breast cancer, is a new approach to computer-aided diagnosis. This approach may be limited, however, by two main causes. The first problem is the presence of poorly separable "crossed-distributions" in which the correct classification depends upon the value of each feature. The second problem is overlap of the feature distributions that are extracted from digitized mammograms of normal and abnormal patients. Here we introduce a new Support Vector Machine (SVM) based method utilizing with the proposed uncrossing mapping and Local Probability Difference (LPD). Crossed-distribution feature pairs are identified and mapped into a new features that can be separated by a zero-hyperplane of the new axis. The probability density functions of the features of normal and abnormal mammograms are then sampled and the local probability difference functions are estimated to enhance the features. From 1,000 ground-truth-known mammograms, 250 normal and 250 abnormal cases, including spiculated lesions, circumscribed masses or microcalcifications, are used for training a support vector machine. The classification results tested with another 250 normal and 250 abnormal sets show improved testing performances with 90% sensitivity and 89% specificity.
URL: https://global.ieice.org/en_transactions/information/10.1587/e90-d_1_258/_p
Copy
@ARTICLE{e90-d_1_258,
author={Werapon CHIRACHARIT, Yajie SUN, Pinit KUMHOM, Kosin CHAMNONGTHAI, Charles F. BABBS, Edward J. DELP, },
journal={IEICE TRANSACTIONS on Information},
title={Normal Mammogram Detection Based on Local Probability Difference Transforms and Support Vector Machines},
year={2007},
volume={E90-D},
number={1},
pages={258-270},
abstract={Automatic detection of normal mammograms, as a "first look" for breast cancer, is a new approach to computer-aided diagnosis. This approach may be limited, however, by two main causes. The first problem is the presence of poorly separable "crossed-distributions" in which the correct classification depends upon the value of each feature. The second problem is overlap of the feature distributions that are extracted from digitized mammograms of normal and abnormal patients. Here we introduce a new Support Vector Machine (SVM) based method utilizing with the proposed uncrossing mapping and Local Probability Difference (LPD). Crossed-distribution feature pairs are identified and mapped into a new features that can be separated by a zero-hyperplane of the new axis. The probability density functions of the features of normal and abnormal mammograms are then sampled and the local probability difference functions are estimated to enhance the features. From 1,000 ground-truth-known mammograms, 250 normal and 250 abnormal cases, including spiculated lesions, circumscribed masses or microcalcifications, are used for training a support vector machine. The classification results tested with another 250 normal and 250 abnormal sets show improved testing performances with 90% sensitivity and 89% specificity.},
keywords={},
doi={},
ISSN={1745-1361},
month={January},}
Copy
TY - JOUR
TI - Normal Mammogram Detection Based on Local Probability Difference Transforms and Support Vector Machines
T2 - IEICE TRANSACTIONS on Information
SP - 258
EP - 270
AU - Werapon CHIRACHARIT
AU - Yajie SUN
AU - Pinit KUMHOM
AU - Kosin CHAMNONGTHAI
AU - Charles F. BABBS
AU - Edward J. DELP
PY - 2007
DO -
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E90-D
IS - 1
JA - IEICE TRANSACTIONS on Information
Y1 - January 2007
AB - Automatic detection of normal mammograms, as a "first look" for breast cancer, is a new approach to computer-aided diagnosis. This approach may be limited, however, by two main causes. The first problem is the presence of poorly separable "crossed-distributions" in which the correct classification depends upon the value of each feature. The second problem is overlap of the feature distributions that are extracted from digitized mammograms of normal and abnormal patients. Here we introduce a new Support Vector Machine (SVM) based method utilizing with the proposed uncrossing mapping and Local Probability Difference (LPD). Crossed-distribution feature pairs are identified and mapped into a new features that can be separated by a zero-hyperplane of the new axis. The probability density functions of the features of normal and abnormal mammograms are then sampled and the local probability difference functions are estimated to enhance the features. From 1,000 ground-truth-known mammograms, 250 normal and 250 abnormal cases, including spiculated lesions, circumscribed masses or microcalcifications, are used for training a support vector machine. The classification results tested with another 250 normal and 250 abnormal sets show improved testing performances with 90% sensitivity and 89% specificity.
ER -