Characterizing the major sonographic textural difference between metastatic and common benign lymph nodes using support vector machine with histopathologic correlation

Shao Jer Chen, Chun Hung Lin, Chuan Yu Chang, Ku Yaw Chang, Hsu Chueh Ho, Shih Hsuan Hsiao, Chih Wen Lin, Jeh En Tzeng, Yen Ting Chen, Hong-Ming Tsai

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

Sonographic texture analysis can reflect histopathological components and their arrangement in metastatic and common benign lymph nodes. It is helpful in differentiation between metastatic and benign lymph node lesions for target selection during biopsy of multiple lymph nodes and the strategy of the management. Two ultrasound systems, 107 sonographic regions of interest (ROIs) of metastases and 174 sonographic ROIs of common benign lymph nodes, were recruited in the study. Thirteen texture features derived from co-occurrence matrix were used in characterization of above ROI ultrasound images. Support vector machine (SVM) was used as a classifier and a feature selector. The experimental results show that the entropy gains the best cross-validation accuracy of 94.66% and 87.73% in both ultrasound systems 1 and 2 for the classification of metastatic and benign lymph nodes disease. The accuracy can be further increased to 97.86% and 100% by the combination of the sum average in the study. There are significantly higher entropy and sum average values of the metastatic lymph nodes than of the benign lymph nodes, which are due to the heterogeneous compositions and arrangement of larger cancer cells, lymphocytes, and stroma in metastatic lymph nodes that contrast with simple inflammatory cells infiltration in common benign lymph nodes.

Original languageEnglish
JournalClinical Imaging
Volume36
Issue number4
DOIs
Publication statusPublished - 2012 Jan 1

Fingerprint

Lymph Nodes
Entropy
Support Vector Machine
Lymphocytes
Neoplasm Metastasis
Biopsy
Neoplasms

All Science Journal Classification (ASJC) codes

  • Radiology Nuclear Medicine and imaging

Cite this

Chen, Shao Jer ; Lin, Chun Hung ; Chang, Chuan Yu ; Chang, Ku Yaw ; Ho, Hsu Chueh ; Hsiao, Shih Hsuan ; Lin, Chih Wen ; Tzeng, Jeh En ; Chen, Yen Ting ; Tsai, Hong-Ming. / Characterizing the major sonographic textural difference between metastatic and common benign lymph nodes using support vector machine with histopathologic correlation. In: Clinical Imaging. 2012 ; Vol. 36, No. 4.
@article{90f9c09a081d42bdb752317176ae0bb0,
title = "Characterizing the major sonographic textural difference between metastatic and common benign lymph nodes using support vector machine with histopathologic correlation",
abstract = "Sonographic texture analysis can reflect histopathological components and their arrangement in metastatic and common benign lymph nodes. It is helpful in differentiation between metastatic and benign lymph node lesions for target selection during biopsy of multiple lymph nodes and the strategy of the management. Two ultrasound systems, 107 sonographic regions of interest (ROIs) of metastases and 174 sonographic ROIs of common benign lymph nodes, were recruited in the study. Thirteen texture features derived from co-occurrence matrix were used in characterization of above ROI ultrasound images. Support vector machine (SVM) was used as a classifier and a feature selector. The experimental results show that the entropy gains the best cross-validation accuracy of 94.66{\%} and 87.73{\%} in both ultrasound systems 1 and 2 for the classification of metastatic and benign lymph nodes disease. The accuracy can be further increased to 97.86{\%} and 100{\%} by the combination of the sum average in the study. There are significantly higher entropy and sum average values of the metastatic lymph nodes than of the benign lymph nodes, which are due to the heterogeneous compositions and arrangement of larger cancer cells, lymphocytes, and stroma in metastatic lymph nodes that contrast with simple inflammatory cells infiltration in common benign lymph nodes.",
author = "Chen, {Shao Jer} and Lin, {Chun Hung} and Chang, {Chuan Yu} and Chang, {Ku Yaw} and Ho, {Hsu Chueh} and Hsiao, {Shih Hsuan} and Lin, {Chih Wen} and Tzeng, {Jeh En} and Chen, {Yen Ting} and Hong-Ming Tsai",
year = "2012",
month = "1",
day = "1",
doi = "10.1016/j.clinimag.2011.10.018",
language = "English",
volume = "36",
journal = "Clinical Imaging",
issn = "0899-7071",
publisher = "Elsevier Inc.",
number = "4",

}

Characterizing the major sonographic textural difference between metastatic and common benign lymph nodes using support vector machine with histopathologic correlation. / Chen, Shao Jer; Lin, Chun Hung; Chang, Chuan Yu; Chang, Ku Yaw; Ho, Hsu Chueh; Hsiao, Shih Hsuan; Lin, Chih Wen; Tzeng, Jeh En; Chen, Yen Ting; Tsai, Hong-Ming.

In: Clinical Imaging, Vol. 36, No. 4, 01.01.2012.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Characterizing the major sonographic textural difference between metastatic and common benign lymph nodes using support vector machine with histopathologic correlation

AU - Chen, Shao Jer

AU - Lin, Chun Hung

AU - Chang, Chuan Yu

AU - Chang, Ku Yaw

AU - Ho, Hsu Chueh

AU - Hsiao, Shih Hsuan

AU - Lin, Chih Wen

AU - Tzeng, Jeh En

AU - Chen, Yen Ting

AU - Tsai, Hong-Ming

PY - 2012/1/1

Y1 - 2012/1/1

N2 - Sonographic texture analysis can reflect histopathological components and their arrangement in metastatic and common benign lymph nodes. It is helpful in differentiation between metastatic and benign lymph node lesions for target selection during biopsy of multiple lymph nodes and the strategy of the management. Two ultrasound systems, 107 sonographic regions of interest (ROIs) of metastases and 174 sonographic ROIs of common benign lymph nodes, were recruited in the study. Thirteen texture features derived from co-occurrence matrix were used in characterization of above ROI ultrasound images. Support vector machine (SVM) was used as a classifier and a feature selector. The experimental results show that the entropy gains the best cross-validation accuracy of 94.66% and 87.73% in both ultrasound systems 1 and 2 for the classification of metastatic and benign lymph nodes disease. The accuracy can be further increased to 97.86% and 100% by the combination of the sum average in the study. There are significantly higher entropy and sum average values of the metastatic lymph nodes than of the benign lymph nodes, which are due to the heterogeneous compositions and arrangement of larger cancer cells, lymphocytes, and stroma in metastatic lymph nodes that contrast with simple inflammatory cells infiltration in common benign lymph nodes.

AB - Sonographic texture analysis can reflect histopathological components and their arrangement in metastatic and common benign lymph nodes. It is helpful in differentiation between metastatic and benign lymph node lesions for target selection during biopsy of multiple lymph nodes and the strategy of the management. Two ultrasound systems, 107 sonographic regions of interest (ROIs) of metastases and 174 sonographic ROIs of common benign lymph nodes, were recruited in the study. Thirteen texture features derived from co-occurrence matrix were used in characterization of above ROI ultrasound images. Support vector machine (SVM) was used as a classifier and a feature selector. The experimental results show that the entropy gains the best cross-validation accuracy of 94.66% and 87.73% in both ultrasound systems 1 and 2 for the classification of metastatic and benign lymph nodes disease. The accuracy can be further increased to 97.86% and 100% by the combination of the sum average in the study. There are significantly higher entropy and sum average values of the metastatic lymph nodes than of the benign lymph nodes, which are due to the heterogeneous compositions and arrangement of larger cancer cells, lymphocytes, and stroma in metastatic lymph nodes that contrast with simple inflammatory cells infiltration in common benign lymph nodes.

UR - http://www.scopus.com/inward/record.url?scp=84862659876&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84862659876&partnerID=8YFLogxK

U2 - 10.1016/j.clinimag.2011.10.018

DO - 10.1016/j.clinimag.2011.10.018

M3 - Article

VL - 36

JO - Clinical Imaging

JF - Clinical Imaging

SN - 0899-7071

IS - 4

ER -