A new automated method for the segmentation and characterization of breast masses on ultrasound images.

Segmentation is one of the first steps in most computer-aided diagnosis systems for characterization of masses as malignant or benign. In this study, the authors designed an automated method for segmentation of breast masses on ultrasound (US) images. The method automatically estimated an initial contour based on a manually identified point approximately at the mass center. A two-stage active contour method iteratively refined the initial contour and performed self-examination and correction on the segmentation result. To evaluate the method, the authors compared it with manual segmentation by two experienced radiologists (R1 and R2) on a data set of 488 US images from 250 biopsy-proven masses (100 malignant and 150 benign). Two area overlap ratios (AOR1 and AOR2) and an area error measure were used as performance measures to evaluate the segmentation accuracy. Values for AOR1, defined as the ratio of the intersection of the computer and the reference segmented areas to the reference segmented area, were 0.82 +/- 0.16 and 0.84 +/- 0.18, respectively, when manually segmented mass regions by R1 and R2 were used as the reference. Although this indicated a high agreement between the computer and manual segmentations, the two radiologists' manual segmentation results were significantly (p < 0.03) more consistent, with AOR1 = 0.84 +/- 0.16 and 0.91 +/- 0.12, respectively, when the segmented regions by R1 and R2 were used as the reference. To evaluate the segmentation method in terms of lesion classification accuracy, feature spaces were formed by extracting texture, width-to-height, and posterior shadowing features based on either automated computer segmentation or the radiologists' manual segmentation. A linear discriminant analysis classifier was designed using stepwise feature selection and two-fold cross validation to characterize the mass as malignant or benign. For features extracted from computer segmentation, the case-based test A(z) values ranged from 0.88 +/- 0.03 to 0.92 +/- 0.02, indicating a comparable performance to those extracted from manual segmentation by radiologists (A(z) value range: 0.87 +/- 0.03 to 0.90 +/- 0.03).

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

[2]  Dimitris N. Metaxas,et al.  Combining low-, high-level and empirical domain knowledge for automated segmentation of ultrasonic breast lesions , 2003, IEEE Transactions on Medical Imaging.

[3]  J W Sayre,et al.  Benign versus malignant solid breast masses: US differentiation. , 1999, Radiology.

[4]  Susan M. Schultz,et al.  Computer‐Based Margin Analysis of Breast Sonography for Differentiating Malignant and Benign Masses , 2004, Journal of ultrasound in medicine : official journal of the American Institute of Ultrasound in Medicine.

[5]  Hee Chan Kim,et al.  Computer-aided diagnosis of solid breast nodules: use of an artificial neural network based on multiple sonographic features , 2004, IEEE Transactions on Medical Imaging.

[6]  C. Metz,et al.  Maximum likelihood estimation of receiver operating characteristic (ROC) curves from continuously-distributed data. , 1998, Statistics in medicine.

[7]  M. Giger,et al.  Automatic segmentation of breast lesions on ultrasound. , 2001, Medical physics.

[8]  Lubomir M. Hadjiiski,et al.  Computer-aided diagnosis of pulmonary nodules on CT scans: segmentation and classification using 3D active contours. , 2006, Medical physics.

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

[10]  Demetri Terzopoulos,et al.  Snakes: Active contour models , 2004, International Journal of Computer Vision.

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

[12]  M. Giger,et al.  Breast cancer: effectiveness of computer-aided diagnosis observer study with independent database of mammograms. , 2002, Radiology.

[13]  Mubarak Shah,et al.  A Fast algorithm for active contours and curvature estimation , 1992, CVGIP Image Underst..

[14]  Tommy W. S. Chow,et al.  Estimating optimal feature subsets using efficient estimation of high-dimensional mutual information , 2005, IEEE Transactions on Neural Networks.

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

[16]  Berkman Sahiner,et al.  Quasi-continuous and discrete confidence rating scales for observer performance studies: Effects on ROC analysis. , 2007, Academic radiology.

[17]  N. Petrick,et al.  Improvement in radiologists' characterization of malignant and benign breast masses on serial mammograms with computer-aided diagnosis: an ROC study. , 2004, Radiology.

[18]  B. Goldberg,et al.  Ultrasound as a complement to mammography and breast examination to characterize breast masses. , 2002, Ultrasound in Medicine and Biology.

[19]  J. Baker,et al.  BI-RADS for sonography: positive and negative predictive values of sonographic features. , 2005, AJR. American journal of roentgenology.

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

[21]  Lubomir M. Hadjiiski,et al.  Computerized characterization of breast masses on three-dimensional ultrasound volumes. , 2004, Medical physics.

[22]  Berkman Sahiner,et al.  Dual system approach to computer-aided detection of breast masses on mammograms. , 2006, Medical physics.

[23]  Berkman Sahiner,et al.  Computer-aided characterization of mammographic masses: accuracy of mass segmentation and its effects on characterization , 2001, IEEE Transactions on Medical Imaging.

[24]  Lubomir M. Hadjiiski,et al.  Malignant and benign breast masses on 3D US volumetric images: effect of computer-aided diagnosis on radiologist accuracy. , 2007, Radiology.