Breast Mass Classification on Full-Field Digital Mammography and Screen-Film Mammography

Authors:
Jiazheng Shi;Berkman Sahiner;Heang-Ping Chan;Lubomir M. Hadjiiski;Jun Ge;Jun Wei
Affiliations:
Department of Radiology, University of Michigan, Ann Arbor MI 48109;Department of Radiology, University of Michigan, Ann Arbor MI 48109;Department of Radiology, University of Michigan, Ann Arbor MI 48109;Department of Radiology, University of Michigan, Ann Arbor MI 48109;Department of Radiology, University of Michigan, Ann Arbor MI 48109;Department of Radiology, University of Michigan, Ann Arbor MI 48109
Venue:
IWDM '08 Proceedings of the 9th international workshop on Digital Mammography
Year:
2008

Citing 3
Cited 0

C4.5: programs for machine learning

C4.5: programs for machine learning
An Empirical Comparison of Voting Classification Algorithms: Bagging, Boosting, and Variants

Machine Learning
Bagging, boosting, and C4.S

AAAI'96 Proceedings of the thirteenth national conference on Artificial intelligence - Volume 1

Quantified Score

Hi-index	0.00

Visualization

Abstract

Studies have shown that full-field digital mammography (FFDM) has the potential to alleviate some of the limitations of screen-film mammography (SFM). It is therefore important to develop computer-aided diagnosis (CAD) systems for FFDM or adapt CAD systems developed for SFM to FFDM. The purpose of this study was to evaluate the performance of a CAD system, originally developed for characterization of breast masses on SFM, on a data set of masses acquired with FFDM. The performance on the FFDM set was compared to that on the corresponding masses on SFM of the same patients acquired within six months of the FFDM exam. The CAD system was trained on an SFM data set with 397 biopsy-proven masses (187 malignant and 210 benign) in 868 regions of interest (ROIs) (437 malignant and 431 benign). Four computer-extracted mammographic features and the patient age were selected as input predictor variables to two classification methods: linear discriminant analysis (LDA) and C5.0 decision tree (DT). The trained CAD systems were fixed and tested on an independent FFDM data set with 122 biopsy-proven masses (29 malignant and 93 benign) in 238 ROIs (60 malignant and 178 benign) and on the corresponding SFM data set. Receiver operating characteristic (ROC) analysis indicated that the CAD system using the LDA classifier achieved view-based test Az values of 0.81±0.03 and 0.82±0.03 for SFM and FFDM, respectively. The case-based test Az values with the same classifier were 0.82±0.04 for SFM and 0.88±0.03 for FFDM. The difference in the Az values between the two modalities did not achieve statistical significance (p=0.62 and p=0.13 for view-based and case-based evaluation, respectively). The use of the DT classifier resulted in a slight increase in performance for both modalities, with view-based Az values of 0.82±0.03 and 0.83±0.03 for SFM and FFDM, respectively.