Histogram and gray level co-occurrence matrix on gray-scale ultrasound images for diagnosing lymphocytic thyroiditis

Young Gyung Shin, Jaeheung Yoo, Hyeong Ju Kwon, Jung Hwa Hong, Hye Sun Lee, Jung Hyun Yoon, Eun Kyung Kim, Hee Jung Moon, Kyunghwa Han, Jin Young Kwak

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

The objective of the study was to evaluate whether texture analysis using histogram and gray level co-occurrence matrix (GLCM) parameters can help clinicians diagnose lymphocytic thyroiditis (LT) and differentiate LT according to pathologic grade. The background thyroid pathology of 441 patients was classified into no evidence of LT, chronic LT (CLT), and Hashimoto's thyroiditis (HT). Histogram and GLCM parameters were extracted from the regions of interest on ultrasound. The diagnostic performances of the parameters for diagnosing and differentiating LT were calculated. Of the histogram and GLCM parameters, the mean on histogram had the highest Az (0.63) and VUS (0.303). As the degrees of LT increased, the mean decreased and the standard deviation and entropy increased. The mean on histogram from gray-scale ultrasound showed the best diagnostic performance as a single parameter in differentiating LT according to pathologic grade as well as in diagnosing LT.

Original languageEnglish
Pages (from-to)257-266
Number of pages10
JournalComputers in Biology and Medicine
Volume75
DOIs
Publication statusPublished - 2016 Aug 1

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Health Informatics

Fingerprint Dive into the research topics of 'Histogram and gray level co-occurrence matrix on gray-scale ultrasound images for diagnosing lymphocytic thyroiditis'. Together they form a unique fingerprint.

  • Cite this