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

Title: Characterization of masses in digital breast tomosynthesis: Comparison of machine learning in projection views and reconstructed slices

Abstract

Purpose: In digital breast tomosynthesis (DBT), quasi-three-dimensional (3D) structural information is reconstructed from a small number of 2D projection view (PV) mammograms acquired over a limited angular range. The authors developed preliminary computer-aided diagnosis (CADx) methods for classification of malignant and benign masses and compared the effectiveness of analyzing lesion characteristics in the reconstructed DBT slices and in the PVs. Methods: A data set of MLO view DBT of 99 patients containing 107 masses (56 malignant and 51 benign) was collected at the Massachusetts General Hospital with IRB approval. The DBTs were obtained with a GE prototype system which acquired 11 PVs over a 50 deg. arc. The authors reconstructed the DBTs at 1 mm slice interval using a simultaneous algebraic reconstruction technique. The region of interest (ROI) containing the mass was marked by a radiologist in the DBT volume and the corresponding ROIs on the PVs were derived based on the imaging geometry. The subsequent processes were fully automated. For classification of masses using the DBT-slice approach, the mass on each slice was segmented by an active contour model initialized with adaptive k-means clustering. A spiculation likelihood map was generated by analysis of the gradient directions around the massmore » margin and spiculation features were extracted from the map. The rubber band straightening transform (RBST) was applied to a band of pixels around the segmented mass boundary. The RBST image was enhanced by Sobel filtering in the horizontal and vertical directions, from which run-length statistics texture features were extracted. Morphological features including those from the normalized radial length were designed to describe the mass shape. A feature space composed of the spiculation features, texture features, and morphological features extracted from the central slice alone and seven feature spaces obtained by averaging the corresponding features from three to 19 slices centered at the central slice were compared. For classification of masses using the PV approach, a feature extraction process similar to that described above for the DBT approach was performed on the ROIs from the individual PVs. Six feature spaces obtained from the central PV alone and by averaging the corresponding features from three to 11 PVs were formed. In each feature space for either the DBT-slice or the PV approach, a linear discriminant analysis classifier with stepwise feature selection was trained and tested using a two-loop leave-one-case-out resampling procedure. Simplex optimization was used to guide feature selection automatically within the training set in each leave-one-case-out cycle. The performance of the classifiers was evaluated by the area (A{sub z}) under the receiver operating characteristic curve. Results: The test A{sub z} values from the DBT-slice approach ranged from 0.87{+-}0.03 to 0.93{+-}0.02, while those from the PV approach ranged from 0.78{+-}0.04 to 0.84{+-}0.04. The highest test A{sub z} of 0.93{+-}0.02 from the nine-DBT-slice feature space was significantly (p=0.006) better than the highest test A{sub z} of 0.84{+-}0.04 from the nine-PV feature space. Conclusion: The features of breast lesions extracted from the DBT slices consistently provided higher classification accuracy than those extracted from the PV images.« less

Authors:
; ; ; ; ; ; ; ; ;  [1]
  1. Department of Radiology, University of Michigan, Ann Arbor, Michigan 48109 (United States)
Publication Date:
OSTI Identifier:
22096716
Resource Type:
Journal Article
Journal Name:
Medical Physics
Additional Journal Information:
Journal Volume: 37; Journal Issue: 7; Other Information: (c) 2010 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:
60 APPLIED LIFE SCIENCES; ACCURACY; BIOMEDICAL RADIOGRAPHY; CLASSIFICATION; COMPARATIVE EVALUATIONS; COMPUTERIZED TOMOGRAPHY; DIAGNOSIS; IMAGE PROCESSING; IMAGES; MAMMARY GLANDS; OPTIMIZATION; PATIENTS; PERFORMANCE; STATISTICS

Citation Formats

Chan, Heang-Ping, Yita, Wu, Sahiner, Berkman, Wei, Jun, Helvie, Mark A., Yiheng, Zhang, Moore, Richard H., Kopans, Daniel B., Hadjiiski, Lubomir, Way, Ted, Department of Radiology, Massachusetts General Hospital, Boston, Massachusetts 02114, and Department of Radiology, University of Michigan, Ann Arbor, Michigan 48109. Characterization of masses in digital breast tomosynthesis: Comparison of machine learning in projection views and reconstructed slices. United States: N. p., 2010. Web. doi:10.1118/1.3432570.
Chan, Heang-Ping, Yita, Wu, Sahiner, Berkman, Wei, Jun, Helvie, Mark A., Yiheng, Zhang, Moore, Richard H., Kopans, Daniel B., Hadjiiski, Lubomir, Way, Ted, Department of Radiology, Massachusetts General Hospital, Boston, Massachusetts 02114, & Department of Radiology, University of Michigan, Ann Arbor, Michigan 48109. Characterization of masses in digital breast tomosynthesis: Comparison of machine learning in projection views and reconstructed slices. United States. https://doi.org/10.1118/1.3432570
Chan, Heang-Ping, Yita, Wu, Sahiner, Berkman, Wei, Jun, Helvie, Mark A., Yiheng, Zhang, Moore, Richard H., Kopans, Daniel B., Hadjiiski, Lubomir, Way, Ted, Department of Radiology, Massachusetts General Hospital, Boston, Massachusetts 02114, and Department of Radiology, University of Michigan, Ann Arbor, Michigan 48109. Thu . "Characterization of masses in digital breast tomosynthesis: Comparison of machine learning in projection views and reconstructed slices". United States. https://doi.org/10.1118/1.3432570.
@article{osti_22096716,
title = {Characterization of masses in digital breast tomosynthesis: Comparison of machine learning in projection views and reconstructed slices},
author = {Chan, Heang-Ping and Yita, Wu and Sahiner, Berkman and Wei, Jun and Helvie, Mark A. and Yiheng, Zhang and Moore, Richard H. and Kopans, Daniel B. and Hadjiiski, Lubomir and Way, Ted and Department of Radiology, Massachusetts General Hospital, Boston, Massachusetts 02114 and Department of Radiology, University of Michigan, Ann Arbor, Michigan 48109},
abstractNote = {Purpose: In digital breast tomosynthesis (DBT), quasi-three-dimensional (3D) structural information is reconstructed from a small number of 2D projection view (PV) mammograms acquired over a limited angular range. The authors developed preliminary computer-aided diagnosis (CADx) methods for classification of malignant and benign masses and compared the effectiveness of analyzing lesion characteristics in the reconstructed DBT slices and in the PVs. Methods: A data set of MLO view DBT of 99 patients containing 107 masses (56 malignant and 51 benign) was collected at the Massachusetts General Hospital with IRB approval. The DBTs were obtained with a GE prototype system which acquired 11 PVs over a 50 deg. arc. The authors reconstructed the DBTs at 1 mm slice interval using a simultaneous algebraic reconstruction technique. The region of interest (ROI) containing the mass was marked by a radiologist in the DBT volume and the corresponding ROIs on the PVs were derived based on the imaging geometry. The subsequent processes were fully automated. For classification of masses using the DBT-slice approach, the mass on each slice was segmented by an active contour model initialized with adaptive k-means clustering. A spiculation likelihood map was generated by analysis of the gradient directions around the mass margin and spiculation features were extracted from the map. The rubber band straightening transform (RBST) was applied to a band of pixels around the segmented mass boundary. The RBST image was enhanced by Sobel filtering in the horizontal and vertical directions, from which run-length statistics texture features were extracted. Morphological features including those from the normalized radial length were designed to describe the mass shape. A feature space composed of the spiculation features, texture features, and morphological features extracted from the central slice alone and seven feature spaces obtained by averaging the corresponding features from three to 19 slices centered at the central slice were compared. For classification of masses using the PV approach, a feature extraction process similar to that described above for the DBT approach was performed on the ROIs from the individual PVs. Six feature spaces obtained from the central PV alone and by averaging the corresponding features from three to 11 PVs were formed. In each feature space for either the DBT-slice or the PV approach, a linear discriminant analysis classifier with stepwise feature selection was trained and tested using a two-loop leave-one-case-out resampling procedure. Simplex optimization was used to guide feature selection automatically within the training set in each leave-one-case-out cycle. The performance of the classifiers was evaluated by the area (A{sub z}) under the receiver operating characteristic curve. Results: The test A{sub z} values from the DBT-slice approach ranged from 0.87{+-}0.03 to 0.93{+-}0.02, while those from the PV approach ranged from 0.78{+-}0.04 to 0.84{+-}0.04. The highest test A{sub z} of 0.93{+-}0.02 from the nine-DBT-slice feature space was significantly (p=0.006) better than the highest test A{sub z} of 0.84{+-}0.04 from the nine-PV feature space. Conclusion: The features of breast lesions extracted from the DBT slices consistently provided higher classification accuracy than those extracted from the PV images.},
doi = {10.1118/1.3432570},
url = {https://www.osti.gov/biblio/22096716}, journal = {Medical Physics},
issn = {0094-2405},
number = 7,
volume = 37,
place = {United States},
year = {2010},
month = {7}
}