Multimodality CAD: combination of computerized classification techniques based on mammograms and 3D ultrasound volumes for improved accuracy in breast mass characterization

Mammography and ultrasound (US) are two low-cost modalities that are commonly used by radiologists for evaluating breast masses and making biopsy recommendations. The goal of this study was to investigate computerized methods for combining information from these two modalities for mass characterization. Our data set consisted of 3D US images and mammograms of biopsy-proven solid breast masses from 60 patients. Thirty of the masses were malignant and 30 were benign. The US volume was obtained by scanning with an experimental 3D US image acquisition system. After computerized feature extraction from the 3D US images and mammograms, we investigated three methods (A, B and C) for combining the image features or classifier scores from different mammographic views and the US volumes. The classifier scores were analyzed using the receiver operating characteristic (ROC) methodology. The area Az under the ROC curve of the classifier based on US alone was 0.88±0.04 for testing Two classifiers were designed using the mammograms alone, with test Az values of 0.85±0.05 and 0.87±0.05, respectively. The test accuracy of combination methods A, B, and C were 0.89±0.04, 0.92±0.03, and 0.93±0.03, respectively. Our results indicate that combining the image features or classifier scores from the US and mammographic classification methods can improve the accuracy of computerized mass characterization.

[1]  A. Stavros,et al.  Solid breast nodules: use of sonography to distinguish between benign and malignant lesions. , 1995, Radiology.

[2]  D. Chen,et al.  Computer-aided diagnosis applied to US of solid breast nodules by using neural networks. , 1999, Radiology.

[3]  K. Han,et al.  Breast lesions on sonograms: computer-aided diagnosis with nearly setting-independent features and artificial neural networks. , 2003, Radiology.

[4]  N. Estes,et al.  Breast biopsy for nonpalpable lesions: a worthwhile endeavor? , 1993, The American surgeon.

[5]  Yi Zheng,et al.  Reduction of breast biopsies with a modified self-organizing map , 1997, IEEE Trans. Neural Networks.

[6]  G Hermann,et al.  Nonpalpable breast lesions: accuracy of prebiopsy mammographic diagnosis. , 1987, Radiology.

[7]  G L LeCarpentier,et al.  Discrimination of sonographically detected breast masses using frequency shift color Doppler imaging in combination with age and gray scale criteria. , 2001, Journal of ultrasound in medicine : official journal of the American Institute of Ultrasound in Medicine.

[8]  N. Petrick,et al.  Improvement of radiologists' characterization of mammographic masses by using computer-aided diagnosis: an ROC study. , 1999, Radiology.

[9]  Lubomir M. Hadjiiski,et al.  Improvement of mammographic mass characterization using spiculation meausures and morphological features. , 2001, Medical physics.

[10]  M. Giger,et al.  Automated computerized classification of malignant and benign masses on digitized mammograms. , 1998, Academic radiology.

[11]  M. Giger,et al.  Computerized diagnosis of breast lesions on ultrasound. , 2002, Medical physics.

[12]  A. Giuliano,et al.  The prevalence of carcinoma in palpable vs impalpable, mammographically detected lesions. , 1991, AJR. American journal of roentgenology.

[13]  H P Chan,et al.  Image feature selection by a genetic algorithm: application to classification of mass and normal breast tissue. , 1996, Medical physics.

[14]  F. Hall,et al.  Nonpalpable breast lesions: recommendations for biopsy based on suspicion of carcinoma at mammography. , 1988, Radiology.

[15]  Berkman Sahiner,et al.  Three-dimensional active contour model for characterization of solid breast masses on three-dimensional ultrasound images , 2003, SPIE Medical Imaging.