Computer-Aided Diagnosis for 3-Dimensional Breast Ultrasonography | Breast Cancer | JAMA Surgery | JAMA Network
[Skip to Navigation]
Access to paid content on this site is currently suspended due to excessive activity being detected from your IP address 18.204.227.34. Please contact the publisher to request reinstatement.
1.
Raymond  HW Letter from the editor.  Semin Ultrasound CT MR. 2000;21285Google ScholarCrossref
2.
Stavors  ATThickman  DRapp  CL  et al.  Solid breast nodules: use of sonography to distinguish between benign and malignant lesions.  Radiology. 1995;196123- 134Google ScholarCrossref
3.
Chen  DRChang  RFHuang  YL Computer-aided diagnosis applied to US of solid breast nodules by using neural networks.  Radiology. 1999;213407- 412Google ScholarCrossref
4.
Chen  DRChang  RFHuang  YL  et al.  Texture analysis of breast tumors on sonograms.  Semin Ultrasound CT MR. 2000;21308- 316Google ScholarCrossref
5.
Chen  DRChang  RFHuang  YL Breast cancer diagnosis using self-organizing map for sonography.  Ultrasound Med Biol. 2000;26405- 411Google ScholarCrossref
6.
Garra  BSKrasner  BHHorii  SCAscher  SMuk  SKZeman  RK Improving the distinction between benign and malignant breast lesions: the value of sonographic texture analysis.  Ultrason Imaging. 1993;15267- 285Google ScholarCrossref
7.
Rotten  DLevaillant  J-MZerat  L Use of three-dimensional ultrasound mammography to analyze normal breast tissue and solid breast masses. Merz  Eed. 3-D Ultrasonography in Obstetric and Gynecology. Philadelphia, Pa Lippincott Williams & Wilkins Inc1998;73- 78Google Scholar
8.
Cheng  XYAkiyama  IItoh  K  et al.  Breast tumor diagnosis system using three-dimensional ultrasonic echography.  Proceedings of the19th International Conference on IEEE Engineering in Medicine and Biology Society Oct 30-Nov 2, 1997 Chicago, IL, USA Storrs, Conn: IEEE Standard Office1997;517- 520Google Scholar
9.
Fenster  ACardinal  NTong  SDowney  DB Development and evaluation of a 3D ultrasound imaging system.  Proceedings of the IEEE Instrumentation and Measurement Technology Conference May 18-21, 1998 St Paul, Minn. Vol 1. Storrs, Conn IEEE Standard Office1998;562- 565Google Scholar
10.
Cheng  XYAkiyama  IItoh  KWang  YTaniguchi  NNakajima  M Automated detection of breast tumors ultrasonic images using fuzzy reasoning.  Proceedings of the IEEE International Conference on Image Processing October 26-29, 1997 Washington, DC.Vol 3.Storrs, Conn: IEEE Standard Office; 199:420-423.
11.
Gonzalez  RCWoods  RE Digital Image Processing.  Reading, Mass Addison-Wesley Publishing Co1992;312- 315
12.
Sahiner  BChan  HPPetrick  N  et al.  Classification of mass and normal breast tissue: a convolution neural network classifier with spatial domain and texture images.  IEEE Trans Med Imaging. 1996;15598- 610Google ScholarCrossref
13.
Cristianini  NShawe-Taylor  J An Introduction to Support Vector Machine and Other Kernel-Based Learning Methods.  Cambridge, England Cambridge University Press2000;
14.
Giger  MLHallaq  HAHuo  Z  et al.  Computerized analysis of lesions in US images of the breast.  Acad Radiol. 1999;6665- 674Google ScholarCrossref
15.
Rotten  DLevaillant  JMZerat  L Analysis of normal breast tissue and of solid breast masses using three-dimensional ultrasound mammography.  Ultrasound Obstet Gynecol. 1999;14114- 124Google ScholarCrossref
Original Article
March 2003

Computer-Aided Diagnosis for 3-Dimensional Breast Ultrasonography

Author Affiliations

From the Department of General Surgery, China Medical College and Hospital, Taichung, Taiwan (Dr D.-R. Chen), and Department of Computer Science and Information Engineering, National Chung Cheng University, Chiayi, Taiwan (Drs Chang and Ms W.-M. Chen); and the Department of Diagnostic Radiology, Seoul National University Hospital, Seoul, South Korea (Dr Moon).

Arch Surg. 2003;138(3):296-302. doi:10.1001/archsurg.138.3.296
Abstract

Hypothesis  Using 3-dimensional (3-D) over 2-dimensional (2-D) ultrasonographic (US) images of the breast represents a potentially significant advantage for computer-aided diagnosis (CAD).

Background  Although conventional 2-D US images of the breast are increasingly used in surgical clinical practice, 3-D US imaging of the breast, a newly introduced technique, can offer more information than 2-D US images do.

Design  This study deals with a CAD method for use with the proposed 3-D US images of the breast and compares its performance with conventional 2-D US versions.

Methods  The test databases included 3-D US images of 107 benign and 54 malignant breast tumors for a total of 161 US images. All solid nodules at US belong to categories above C3 (ie, probably benign). The 3-D US imaging was performed using a scanner (Voluson 530; Kretz Technik, Zipf, Austria). New 3-D autocorrelation coefficients extended from the traditional 2-D autocorrelations were developed to extract the texture characteristics of the 3-D US images. The extracted texture features of the 3-D US images were used to classify the tumor as benign or malignant using the neural network.

Results  At the receiver operating characteristic analysis, 3-D and 2-D autocorrelation calculating schemes yielded Az values (ie, area under the receiver operating characteristic curve) of 0.97 and 0.85 in distinguishing between benign and malignant lesions, respectively. Accuracy, sensitivity, specificity, positive predictive value, and negative predictive value are statistically significantly improved using 3-D instead of 2-D US images for CAD.

Conclusions  The proposed system (for 3-D and 2-D CAD) is expected to be a useful computer-aided diagnostic tool for classifying benign and malignant tumors on ultrasonograms and can provide a second reading to help reduce misdiagnosis. Findings from this study suggest that using 3-D over 2-D US images for CAD represents a potentially significant advantage.

×