Catherine W. Piccoli

Classification of ultrasonic B-mode images of breast masses using Nakagami distribution

The Nakagami distribution was proposed recently for modeling the echo from tissue. In vivo breast data collected from patients with lesions were studied using this Nakagami model. Chi-square tests showed that the Nakagami distribution is a better fit to the envelope than the Rayleigh distribution. Two parameters, m (effective number) and /spl alpha/ (effective cross section), associated with the Nakagami distribution were used for the classification of breast masses. Data from 52 patients with breast masses/lesions were used in the studies. Receiver operating characteristics were calculated for the classification methods based on these two parameters. The results indicate that these parameters of the Nakagami distribution may be useful in classification of the breast abnormalities. The Nakagami distribution may be a reasonable means to characterize the backscattered echo from breast tissues toward a goal of an automated scheme for separating benign and malignant breast masses.

Use of non-Rayleigh statistics for the identification of tumors in ultrasonic B-scans of the breast

A model for the scattering of ultrasound from breast tissue is proposed. The model is based on the use of non-Rayleigh statistics, specifically the K distribution to describe the backscattered echo from the tissue. A multiparameter test based on this model has been designed to characterize the tissue. The data from the B-scan images of the breasts of 6 different patients were analyzed using this model. The results indicate that the non-Rayleigh statistics seem to be useful in characterizing and identifying malignant, benign, and normal tissue regions.

ULTRASOUND AS A COMPLEMENT TO MAMMOGRAPHY AND BREAST EXAMINATION TO CHARACTERIZE BREAST MASSES

This study was designed to determine if complementary ultrasound (US) imaging and Doppler could decrease the number of biopsies for benign masses. A total of 761 breast masses were sequentially scored on a level of suspicion (LOS) of 1-5, where 1 represented low, and 5 was a high suspicion of malignancy, for mammography, US, and color flow with pulse Doppler (DUS). After biopsy, the results were analyzed using 2 x 2 contingency tables and ROC analysis, for mammography alone and in combination with US and DUS. The addition of US increased the specificity from 51.4% to 66.4% at a prevalence of 31.3% malignancy. ROC analysis showed that the addition of US significantly improved the performance over mammography alone in women < 55 years old (p = 0.049); > 55 years old (p = 0.029); masses < 1 cm (p = 0.016) and masses > 1 cm (p = 0.016). These results show that the addition of US to mammography alone could substantially reduce the number of breast biopsies for benign disease.

TISSUE CLASSIFICATION WITH GENERALIZED SPECTRUM PARAMETERS

This paper presents performance comparisons between breast tumor classifiers based on parameters from a conventional texture analysis (CTA) and the generalized spectrum (GS). The computations of GS-based parameters from radiofrequency (RF) ultrasonic scans and their relationship to underlying scatterer properties are described. Clinical experiments demonstrate classifier performances using 22 benign and 24 malignant breast mass regions taken from 40 patients. Linear classifiers based on parameters from the front edge, back edge and interior tumor regions are examined. Results show significantly better performances for GS-based classifiers, with improvements in empirical receiver operating characteristic (ROC) areas of greater than 10%. The ROC curves show GS-based classifiers achieving a 90% sensitivity level at 50% specificity when applied to the back-edge tumor regions, an 80% sensitivity level at 65% specificity when applied to the front-edge tumor regions, and a 100% sensitivity level at 45% specificity when applied to the interior tumor regions.

Classification of breast masses in ultrasonic B scans using Nakagami and K distributions

Classification of breast masses in greyscale ultrasound images is undertaken using a multiparameter approach. Five parameters reflecting the non-Rayleigh nature of the backscattered echo were used. These parameters, based mostly on the Nakagami and K distributions, were extracted from the envelope of the echoes at the site, boundary, spiculated region and shadow of the mass. They were combined to create a linear discriminant. The performance of this discriminant for the classification of breast masses was studied using a data set consisting of 70 benign and 29 malignant cases. The Az value for the discriminant was 0.96 +/- 0.02, showing great promise in the classification of masses into benign and malignant ones. The discriminant was combined with the level of suspicion values of the radiologist leading to an Az value of 0.97 +/- 0.014. The parameters used here can be calculated with minimal clinical intervention, so the method proposed here may therefore be easily implemented in an automated fashion. These results also support the recent reports suggesting that ultrasound may help as an adjunct to mammography in breast cancer diagnostics to enhance the classification of breast masses.

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.

Comparisons of the Rayleigh and K-distribution models using in vivo breast and liver tissue

There is a strong interest in finding out which statistical model is the most appropriate for describing the envelope of the backscattered ultrasonic echoes from different types of tissues. The Rayleigh model is commonly employed, but this requires conditions, such as the presence of large number of randomly located scatterers with fairly uniform cross-sections, that are not always met. However, our research indicates that a model based on the K-distribution may provide a better fit to empirical data over a range of scattering conditions than the standard Rayleigh model. In this study, we looked at the K-distribution as a descriptor of the backscattered envelope of the breast and liver tissues (in vivo). By examining data from various tissue regions, a goodness-of-fit test (a least squares error method) was used to determine whether a Rayleigh or K-distribution model is more appropriate. From a large group of patients and volunteer scans (a total of 72 subjects), the fit between the K-distribution and the data is shown to have a much smaller error than the Rayleigh model.

Analysis and classification of tissue with scatterer structure templates

Back-scattered ultrasonic signals provide scatterer structure information. Large-scale structures, such as tissue and tumor boundaries, typically create significant amplitude differences that reveal boundaries in conventional intensity images. Small-scale structures typically result in textures observed over regions of the intensity image. This paper describes the generalized spectrum (GS) for characterizing small-scale scatterer structures and applies it to analyze scatterer structures in a class of malignant and benign breast masses. Methods are presented for scaling and normalizing the GS to reduce effects from system response, overlaying tissue, and variability from noncritical structures. Results from a limited clinical study demonstrate an application of using the GS to discriminate between benign and malignant breast masses that contain internal echoes. Sections of rf A-scans in 41 breast mass regions were taken from 26 patients. A GS analysis was applied to determine critical structural properties between a class of fibroadenoma and carcinoma masses. Classifiers designed using significant structure differences identified by the GS analysis achieved approximately 82% true-positive and 10% false-positive rates.

Use of the K-distribution for classification of breast masses

The K-distribution had been introduced as a valid model to represent the statistics of the envelope of the backscattered echo from phantom and tissue. This paper investigates the efficacy of the parameters of this statistical model; namely, the effective number and the effective cross-section, to characterize breast lesions as benign or malignant. Based on the normalized values of the effective number and the effective scattering cross-section, images containing benign and malignant masses were classified for a data set from 52 patients having breast masses/lesions. The receiver operating characteristic (ROC) curves were then obtained to test the classification based on these two parameters. The results indicate that the parameters of the K-distribution may be useful in classification of the breast lesions as benign and malignant.

Tissue characterization using the continuous wavelet transform. II. Application on breast RF data

For pt.I see ibid., vol.48, no.2, p.356-63 (2001). In the first part of this work (Georgiou and Cohen 2000), a wavelet-based decomposition algorithm of the RF echo into its coherent and diffuse components was introduced. In this paper, the proposed algorithm is used to estimate structural parameters of the breast tissue such as the number and energy of coherent scatterers, the energy of the diffuse scatterers, and the correlation between them. Based on these individual parameters, breast tissue characterization is performed. The database used consists of 155 breast scans from 42 patients. The results are presented in terms of empirical receiver operating characteristics (ROC) curves. The results of this study are discussed in relation to the tissue microstructure. Individual estimated parameters are able to differentiate reliably between normal and fibroadenoma or fibrocystic or cancerous tissue (area under the ROC A/sub z/>0.93). Also, the differentiation between malignant and benign (normal, fibrocystic, and fibroadenoma) tissue was possible (A/sub z/>0.89).