ROC analysis of ultrasound tissue characterization classifiers for breast cancer diagnosis

Breast cancer diagnosis through ultrasound tissue characterization was studied using receiver operating characteristic (ROC) analysis of combinations of acoustic features, patient age, and radiological findings. A feature fusion method was devised that operates even if only partial diagnostic data are available. The ROC methodology uses ordinal dominance theory and bootstrap resampling to evaluate A/sub z/ and confidence intervals in simple as well as paired data analyses. The combined diagnostic feature had an A/sub z/ of 0.96 with a confidence interval of [0.93, 0.99] at a significance level of 0.05. The combined features show statistically significant improvement over prebiopsy radiological findings. These results indicate that ultrasound tissue characterization, in combination with patient record and clinical findings, may greatly reduce the need to perform biopsies of benign breast lesions.

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

[2]  F. Forsberg,et al.  Analysis and classification of tissue with scatterer structure templates , 1999, IEEE Transactions on Ultrasonics, Ferroelectrics and Frequency Control.

[3]  M. A. Kutay,et al.  On modeling biomedical ultrasound RF echoes using a power-law shot-noise model , 2001, IEEE Transactions on Ultrasonics, Ferroelectrics and Frequency Control.

[4]  C W Piccoli,et al.  Tissue classification with generalized spectrum parameters. , 2001, Ultrasound in medicine & biology.

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

[6]  C. Metz.  ROC Methodology in Radiologic Imaging , 1986, Investigative radiology.

[7]  R. F. Wagner,et al.  Quantitative Ultrasonic Detection of Parenchymal Structural Change in Diffuse Renal Disease , 1994, Investigative radiology.

[8]  Athina P. Petropulu,et al.  Breast tissue characterization based on modeling of ultrasonic echoes using the power-law shot noise model , 2003, Pattern Recognit. Lett..

[9]  C A Roe,et al.  Statistical Comparison of Two ROC-curve Estimates Obtained from Partially-paired Datasets , 1998, Medical decision making : an international journal of the Society for Medical Decision Making.

[10]  Athina P. Petropulu,et al.  Power-law shot noise and its application on modeling of ultrasound echoes , 1998, Proceedings of the IEEE-SP International Symposium on Time-Frequency and Time-Scale Analysis (Cat. No.98TH8380).

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

[12]  J.M. Reid,et al.  Classification of ultrasonic B mode images of the breast using frequency diversity and Nakagami statistics , 2002, IEEE Transactions on Ultrasonics, Ferroelectrics and Frequency Control.

[13]  L. Huang,et al.  Duct Detection and Wall Spacing Estimation in Breast Tissue , 2000, Ultrasonic imaging.

[14]  C. Metz,et al.  Statistical significance tests for binormal ROC curves , 1980 .

[15]  David B. Fogel,et al.  Linear and neural models for classifying breast masses , 1998, IEEE Transactions on Medical Imaging.

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

[17]  B. Goldberg,et al.  Classification of ultrasonic B-mode images of breast masses using Nakagami distribution , 2001, IEEE Transactions on Ultrasonics, Ferroelectrics and Frequency Control.

[18]  B. Ripley,et al.  Pattern Recognition , 1968, Nature.

[19]  D. Bamber.  The area above the ordinal dominance graph and the area below the receiver operating characteristic graph , 1975 .