Breast tissue characterization using FARMA modeling of ultrasonic RF echo. Export

@article{Alacam2004, abstract = {A number of empirical and analytical studies demonstrated that the ultrasound RF echo reflected from tissue exhibits 1/f characteristics. In this paper, we propose to model 1/f characteristics of the ultrasonic RF echo by a novel parsimonious model, namely the fractional differencing auto regressive moving average (FARMA) process, and evaluated diagnostic value of model parameters for breast cancer malignancy differentiation. FARMA model captures the fractal and long term correlated nature of the backscattered speckle texture and facilitates robust efficient estimation of fractal parameters. In our study, in addition to the computer generated FARMA model parameters, we included patient age and radiologist's prebiopsy level of suspicion (LOS) as potential indicators of malignant and benign masses. We evaluated the performance of the proposed set of features using various classifiers and training methods using 120 in vivo breast images. Our study shows that the area under the receiver operating characteristics (ROC) curve of FARMA model parameters alone is superior to the area under the ROC curve of the radiologist's prebiopsy LOS. The area under the ROC curve of the three sets of features yields a value of 0.87, with a confidence interval of [0.85, 0.89], at a significance level of 0.05. Our results suggest that the proposed method of ultrasound RF echo model leads to parameters that can differentiate breast tumors with a relatively high precision. This set of RF echo features can be incorporated into a comprehensive computer-aided diagnostic system to aid physicians in breast cancer diagnosis.}, author = {Alacam, Burak and Yazici, Birsen and Bilgutay, Nihat and Forsberg, Flemming and Piccoli, Catherine}, citeulike-article-id = {2642918}, citeulike-linkout-0 = {http://dx.doi.org/10.1016/j.ultrasmedbio.2004.08.023}, doi = {10.1016/j.ultrasmedbio.2004.08.023}, journal = {Ultrasound Med Biol}, keywords = {adolescent, adult, age, aged, and, bibtex-import, breast, computer-assisted, curve, drbbibtex-import, factors, female, humans, image, interpretation, mammary, mammography, middle, models, neoplasms, of, reproducibility, results, roc, sensitivity, specificity, statistical, ultrasonography}, month = {Oct}, number = {10}, pages = {1397--1407}, posted-at = {2008-04-08 22:43:37}, priority = {2}, title = {Breast tissue characterization using FARMA modeling of ultrasonic RF echo.}, url = {http://dx.doi.org/10.1016/j.ultrasmedbio.2004.08.023}, volume = {30}, year = {2004} }

TY - JOUR ID - Alacam2004 L3 - citeulike-article-id:2642918 N2 - A number of empirical and analytical studies demonstrated that the ultrasound RF echo reflected from tissue exhibits 1/f characteristics. In this paper, we propose to model 1/f characteristics of the ultrasonic RF echo by a novel parsimonious model, namely the fractional differencing auto regressive moving average (FARMA) process, and evaluated diagnostic value of model parameters for breast cancer malignancy differentiation. FARMA model captures the fractal and long term correlated nature of the backscattered speckle texture and facilitates robust efficient estimation of fractal parameters. In our study, in addition to the computer generated FARMA model parameters, we included patient age and radiologist's prebiopsy level of suspicion (LOS) as potential indicators of malignant and benign masses. We evaluated the performance of the proposed set of features using various classifiers and training methods using 120 in vivo breast images. Our study shows that the area under the receiver operating characteristics (ROC) curve of FARMA model parameters alone is superior to the area under the ROC curve of the radiologist's prebiopsy LOS. The area under the ROC curve of the three sets of features yields a value of 0.87, with a confidence interval of [0.85, 0.89], at a significance level of 0.05. Our results suggest that the proposed method of ultrasound RF echo model leads to parameters that can differentiate breast tumors with a relatively high precision. This set of RF echo features can be incorporated into a comprehensive computer-aided diagnostic system to aid physicians in breast cancer diagnosis. IS - 10 JF - Ultrasound Med Biol EP - 1407 TI - Breast tissue characterization using FARMA modeling of ultrasonic RF echo. VL - 30 SP - 1397 KW - adolescent KW - adult KW - age KW - aged KW - and KW - bibtex-import KW - breast KW - computer-assisted KW - curve KW - drbbibtex-import KW - factors KW - female KW - humans KW - image KW - interpretation KW - mammary KW - mammography KW - middle KW - models KW - neoplasms KW - of KW - reproducibility KW - results KW - roc KW - sensitivity KW - specificity KW - statistical KW - ultrasonography AU - Alacam, Burak AU - Yazici, Birsen AU - Bilgutay, Nihat AU - Forsberg, Flemming AU - Piccoli, Catherine PY - 2004/Oct// UR - http://dx.doi.org/10.1016/j.ultrasmedbio.2004.08.023 ER -