1887
banner image
No data available.
Please log in to see this content.
You have no subscription access to this content.
No metrics data to plot.
The attempt to load metrics for this article has failed.
The attempt to plot a graph for these metrics has failed.
Classification of scattering media within benign and malignant breast tumors based on ultrasound texture-feature-based and Nakagami-parameter images
Rent:
Rent this article for
USD
10.1118/1.3566064
/content/aapm/journal/medphys/38/4/10.1118/1.3566064
http://aip.metastore.ingenta.com/content/aapm/journal/medphys/38/4/10.1118/1.3566064

Figures

Image of FIG. 1.
FIG. 1.

A general model of biological tissues can be derived from three kinds of information from ultrasonic tissue characterization.

Image of FIG. 2.
FIG. 2.

Images from texture-feature parametric imaging of a fibroadenoma. (a) B-scan image (the tumor contour is indicated by a manually drawn white solid line). (b) Texture-feature parametric images using the HOM, CON, ENE, and VAR. (c) Total number of pixels inside the tumor on the texture-feature parametric image.

Image of FIG. 3.
FIG. 3.

Images from texture-feature parametric imaging of an invasive ductal carcinoma. (a) B-scan image (the tumor contour is indicated by a manually drawn white solid line). (b) Texture-feature parametric images using HOM, CON, ENE, and VAR. (c) Total number of pixels inside the tumor on the texture-feature parametric image.

Image of FIG. 4.
FIG. 4.

Images from Nakagami parametric imaging of a fibroadenoma. (a) The envelope image with an adjusted dynamic range. (b) Nakagami parametric image. (c) Total number of pixels inside the tumor on the Nakagami parametric image.

Image of FIG. 5.
FIG. 5.

Images from Nakagami parametric imaging of an invasive ductal carcinoma. (a) The envelope image with an adjusted dynamic range. (b) Nakagami parametric image. (c) Total number of pixels inside the tumor on the Nakagami parametric image.

Image of FIG. 6.
FIG. 6.

Box plots showing the distributions of the five parameters for benign and malignant breast tumors. Asterisks indicate .

Image of FIG. 7.
FIG. 7.

Scatter graphs of pairs of features for all benign (○) and malignant (×) breast tumors: (a) CON vs HOM, (b) ENE vs HOM, (c) CON vs VAR, and (d) ENE vs VAR.

Image of FIG. 8.
FIG. 8.

ROC curves when using the best set of texture features (i.e., CON, ENE, and VAR) and when also including the Nakagami parameter (i.e., , CON, ENE, and VAR) to classify benign and malignant breast tumors.

Image of FIG. 9.
FIG. 9.

Scatter graphs of pairs of features for all benign (○) and malignant (×) breast tumors: (a) CON vs the Nakagami parameter , (b) ENE vs , and (c) VAR vs .

Tables

Generic image for table
TABLE I.

Individual performances assessed by values ( error and 95% confidence interval), accuracy, specificity, sensitivity, PPV, NPV, MCC, and the value of each parameter in classifying benign and malignant breast tumors.

Generic image for table
TABLE II.

Performances of the different sets of parameters assessed by values ( error and 95% confidence interval), accuracy, specificity, sensitivity, PPV, NPV, and MCC.

Loading

Article metrics loading...

/content/aapm/journal/medphys/38/4/10.1118/1.3566064
2011-03-29
2014-04-20
Loading

Full text loading...

This is a required field
Please enter a valid email address
752b84549af89a08dbdd7fdb8b9568b5 journal.articlezxybnytfddd
Scitation: Classification of scattering media within benign and malignant breast tumors based on ultrasound texture-feature-based and Nakagami-parameter images
http://aip.metastore.ingenta.com/content/aapm/journal/medphys/38/4/10.1118/1.3566064
10.1118/1.3566064
SEARCH_EXPAND_ITEM