Limits...
Robust phase-based texture descriptor for classification of breast ultrasound images.

Cai L, Wang X, Wang Y, Guo Y, Yu J, Wang Y - Biomed Eng Online (2015)

Bottom Line: Then, in order to verify the robustness of the PCBP against illumination variations, we train the SVM classifier on texture features obtained from the original BUS images, and use this classifier to deal with the texture features extracted from BUS images with different illumination conditions (i.e., contrast-improved, gamma-corrected and histogram-equalized).The area under ROC curve (AUC) index is used as the figure of merit to evaluate the classification performances.The proposed PCBP texture descriptor achieves the highest values (i.e. 0.894) and the least variations in respect of the AUC index, regardless of the gray-scale variations.

View Article: PubMed Central - PubMed

Affiliation: Department of Electronic Engineering, Fudan University, Shanghai, 200433, China. 12210720095@fudan.edu.cn.

ABSTRACT

Background: Classification of breast ultrasound (BUS) images is an important step in the computer-aided diagnosis (CAD) system for breast cancer. In this paper, a novel phase-based texture descriptor is proposed for efficient and robust classifiers to discriminate benign and malignant tumors in BUS images.

Method: The proposed descriptor, namely the phased congruency-based binary pattern (PCBP) is an oriented local texture descriptor that combines the phase congruency (PC) approach with the local binary pattern (LBP). The support vector machine (SVM) is further applied for the tumor classification. To verify the efficiency of the proposed PCBP texture descriptor, we compare the PCBP with other three state-of-art texture descriptors, and experiments are carried out on a BUS image database including 138 cases. The receiver operating characteristic (ROC) analysis is firstly performed and seven criteria are utilized to evaluate the classification performance using different texture descriptors. Then, in order to verify the robustness of the PCBP against illumination variations, we train the SVM classifier on texture features obtained from the original BUS images, and use this classifier to deal with the texture features extracted from BUS images with different illumination conditions (i.e., contrast-improved, gamma-corrected and histogram-equalized). The area under ROC curve (AUC) index is used as the figure of merit to evaluate the classification performances.

Results and conclusions: The proposed PCBP texture descriptor achieves the highest values (i.e. 0.894) and the least variations in respect of the AUC index, regardless of the gray-scale variations. It's revealed in the experimental results that classifications of BUS images with the proposed PCBP texture descriptor are efficient and robust, which may be potentially useful for breast ultrasound CADs.

No MeSH data available.


Related in: MedlinePlus

Overall phase congruency results of BUS images. (a) The benign tumor; (b) The overall phase congruency of (a); (c) The malignant tumor; (d) The overall phase congruency of (c).
© Copyright Policy - open-access
Related In: Results  -  Collection

License 1 - License 2
getmorefigures.php?uid=PMC4376500&req=5

Fig4: Overall phase congruency results of BUS images. (a) The benign tumor; (b) The overall phase congruency of (a); (c) The malignant tumor; (d) The overall phase congruency of (c).

Mentions: It is shown in Figure 4 that the overall phase congruency results of both benign and malignant cases in BUS images. Benign tumors often possess the characteristics of regular shape, clearly-defined boundaries and homogeneous internal echoes, whereas malignant tumors appear with irregular shapes, blurry and angular borders, inhomogeneous internal echoes in BUS images. These structural properties can be well reflected on the overall PC image. As shown in Figure 4(b), most of the in-phase points are located around the tumor boundary while the rest remain almost zero, indicating that the tumor has relatively well-defined boundary and smooth foreground/background regions. However, Figure 4(d) shows a different result, where most of the in-phase points are disorganized and dispersed, without a clearly illustration of the tumor location compared with the result in Figure 4(b), which are consistent with the properties of malignant tumors in BUS images. Herein, the phase congruency possesses great potentials and capabilities in depicting differences of benign and malignant tumors in BUS images via structural properties.Figure 4


Robust phase-based texture descriptor for classification of breast ultrasound images.

Cai L, Wang X, Wang Y, Guo Y, Yu J, Wang Y - Biomed Eng Online (2015)

Overall phase congruency results of BUS images. (a) The benign tumor; (b) The overall phase congruency of (a); (c) The malignant tumor; (d) The overall phase congruency of (c).
© Copyright Policy - open-access
Related In: Results  -  Collection

License 1 - License 2
Show All Figures
getmorefigures.php?uid=PMC4376500&req=5

Fig4: Overall phase congruency results of BUS images. (a) The benign tumor; (b) The overall phase congruency of (a); (c) The malignant tumor; (d) The overall phase congruency of (c).
Mentions: It is shown in Figure 4 that the overall phase congruency results of both benign and malignant cases in BUS images. Benign tumors often possess the characteristics of regular shape, clearly-defined boundaries and homogeneous internal echoes, whereas malignant tumors appear with irregular shapes, blurry and angular borders, inhomogeneous internal echoes in BUS images. These structural properties can be well reflected on the overall PC image. As shown in Figure 4(b), most of the in-phase points are located around the tumor boundary while the rest remain almost zero, indicating that the tumor has relatively well-defined boundary and smooth foreground/background regions. However, Figure 4(d) shows a different result, where most of the in-phase points are disorganized and dispersed, without a clearly illustration of the tumor location compared with the result in Figure 4(b), which are consistent with the properties of malignant tumors in BUS images. Herein, the phase congruency possesses great potentials and capabilities in depicting differences of benign and malignant tumors in BUS images via structural properties.Figure 4

Bottom Line: Then, in order to verify the robustness of the PCBP against illumination variations, we train the SVM classifier on texture features obtained from the original BUS images, and use this classifier to deal with the texture features extracted from BUS images with different illumination conditions (i.e., contrast-improved, gamma-corrected and histogram-equalized).The area under ROC curve (AUC) index is used as the figure of merit to evaluate the classification performances.The proposed PCBP texture descriptor achieves the highest values (i.e. 0.894) and the least variations in respect of the AUC index, regardless of the gray-scale variations.

View Article: PubMed Central - PubMed

Affiliation: Department of Electronic Engineering, Fudan University, Shanghai, 200433, China. 12210720095@fudan.edu.cn.

ABSTRACT

Background: Classification of breast ultrasound (BUS) images is an important step in the computer-aided diagnosis (CAD) system for breast cancer. In this paper, a novel phase-based texture descriptor is proposed for efficient and robust classifiers to discriminate benign and malignant tumors in BUS images.

Method: The proposed descriptor, namely the phased congruency-based binary pattern (PCBP) is an oriented local texture descriptor that combines the phase congruency (PC) approach with the local binary pattern (LBP). The support vector machine (SVM) is further applied for the tumor classification. To verify the efficiency of the proposed PCBP texture descriptor, we compare the PCBP with other three state-of-art texture descriptors, and experiments are carried out on a BUS image database including 138 cases. The receiver operating characteristic (ROC) analysis is firstly performed and seven criteria are utilized to evaluate the classification performance using different texture descriptors. Then, in order to verify the robustness of the PCBP against illumination variations, we train the SVM classifier on texture features obtained from the original BUS images, and use this classifier to deal with the texture features extracted from BUS images with different illumination conditions (i.e., contrast-improved, gamma-corrected and histogram-equalized). The area under ROC curve (AUC) index is used as the figure of merit to evaluate the classification performances.

Results and conclusions: The proposed PCBP texture descriptor achieves the highest values (i.e. 0.894) and the least variations in respect of the AUC index, regardless of the gray-scale variations. It's revealed in the experimental results that classifications of BUS images with the proposed PCBP texture descriptor are efficient and robust, which may be potentially useful for breast ultrasound CADs.

No MeSH data available.


Related in: MedlinePlus