Journal of radiological science and technology (대한방사선기술학회지:방사선기술과학)

Korean Society of Radiological Science (대한방사선과학회)
권호 표지
DOI QR코드

DOI QR Code

GLCM Algorithm Image Analysis of Nonalcoholic Fatty Liver and Focal Fat Sparing Zone in the Ultrasonography

초음파검사에서 비알콜성 지방간과 국소지방회피영역에 대한 GLCM Algorithm 영상분석

  • Cho, Jin-Young (Department of Radiological Science, Graduate School of Catholic University of Pusan) ;
  • Ye, Soo-Young (Department of Radiological Science, Catholic University of Pusan)
  • 조진영 (부산가톨릭대학교 대학원 방사선학과) ;
  • 예수영 (부산가톨릭대학교 방사선학과)
  • Received : 2017.02.18
  • Accepted : 2017.04.29
  • Published : 2017.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

There is a need for aggressive diagnosis and treatment in middle-aged and high-risk individuals who are more likely to progress from nonalcoholic fatty liver to hepatitis. In this study, nonalcoholic fatty liver was divided into severe, moderate, and severe, and classified by quantitative method using computer analysis of GLCM algorithm. The purpose of this study was to evaluate the characteristics of ultrasound images in the local fat avoidance region. Normal, mild, moderate, severe fatty liver, and focal fat sparing area, 80 cases, respectively. Among the parameters of the GLCM algorithm, the values of the Autocorrelation, Square of the deviation, Sum of averages and Sum of variances with high recognition rate of the liver ultrasound image were calculated. The average recognition rate of the GLCM algorithm was 97.5%. The result of local fat avoidance image analysis showed the most similar value to the normal parenchyma. Ultrasonography can be easily accessed by primary screening, but there may be differences in the accuracy of the test method or the correspondence of results depending on proficiency. GLCM algorithm was applied to quantitatively classify the degree of fatty liver. Local fat avoidance region was similar to normal parenchyma, so it could be predicted to be homogeneous liver parenchyma without fat deposition. We believe that GLCM computer image analysis will provide important information for differentiating not only fatty liver but also other lesions.

비알콜성 지방간에서 지방 간염으로 진행되는 확률이 높은 중등증 이상에서 적극적인 진단과 치료가 필요하다. 이에 본 연구에서는 비알콜성 지방간을 경도, 중등증, 중증으로 나누어 GLCM 알고리즘의 컴퓨터 분석기법을 이용하여 정량적인 방법으로 분류하였다. 또한 지방간 중에서 국소지방회피영역의 초음파영상의 특징을 알아보고자 하였다. 정상, 경도, 중등도, 중증지방간, 국소적 저지방영역, 각각 80증례를 대상으로 GLCM 알고리즘의 파라미터 중에 간초음파영상의 인식률이 높은 자기상관성, 편차의 제곱, 평균의 합, 분산의 합에 대한 값을 산출하였다. GLCM알고리즘의 파라미터 인식률의 결과는 평균 97.5%로 나타났다. 국소적 저지방 영상분석의 결과는 정상실질과 가장 유사한 값을 나타내었다. 초음파검사는 일차적인 선별검사법으로 쉽게 접근할 수 있지만 숙련도에 따라 검사방법의 정확도나 결과의 일치성 부분에서 차이가 있을 수 있다. GLCM알고리즘을 적용하여 지방간 정도를 정량적으로 분류할 수 있었으며, 국소적 저지방영역은 지방침착이 되지 않은 균질한 간실질임을 예측 가능하였다. 이러한 GLCM 컴퓨터영상분석이 지방간뿐만 아니라 다른 병변의 감별에도 중요한 정보를 제공할 것으로 판단한다.

Keywords

References

  1. Musso G, Cassader M, Gambino R, Diagnostic accuracy of adipose insulin resistance index and visceral adiposity index for progressive liver histology and cardiovascular risk in nonalcoholic fatty liver disease. HEPATOLOGY, 56(2), 788-789, 2012 https://doi.org/10.1002/hep.25677
  2. Clark JM, B rancati FL, Diehl AM, Nonalcoholic fatty liver disease. Gastroenterology, 122(6), 1649-57, 2002 https://doi.org/10.1053/gast.2002.33573
  3. Dae Won Jun, Practic Guideline for the Diagnosis and Management of Non-alcoholic Fatty Liver Disease. Korean J Gastroenterol, 60(1), 64-66, 2012 https://doi.org/10.4166/kjg.2012.60.1.64
  4. JH Kang, SH Lee, HS Lee, JY Cho, BY Yoo, The Relation of Nonalcoholic Fatty Liver Disease to Metabolic Syndrome. J Korean Acad Fam Med, 25, 746-753, 2004
  5. Youngjae Kim, Jondnam Song, Mineui Kim, Analysis of the Accuray Abdominal Ultrasonography and Clinical Chemical Test with Fatty Liver Patients on the Medical Examination. Journal of the Korean of Radiology, 183-189, 2012
  6. Ji Wook Jeong, Soo Yeol Lee, Seung Hwan Kim, Computer-Assisted Ultrasonic Diagnosis of Fatty Liver, KIISE, 28(2), 337-339, 2001
  7. Size Wu, Rong Tu, Guangqing Liu, Li Huang, Ying Guan, Enhai Zheng, J Ultrasound Med, 33, 1447-1452, 2014 https://doi.org/10.7863/ultra.33.8.1447
  8. Jin Soo Lee, Chang Soo Kim, Image Analysis of Diffuse Liver Disease using Computer-Adided Diagnosis in the Liver US Image. J. Korean Soc. Radiol, 9(4), 227-234, 2015 https://doi.org/10.7742/jksr.2015.9.4.227
  9. Hyunwoo Jang, Kwangbeak Kim, Changwon Kim, Proceeding of KIIS Spring Conference, 23, 151-157, 2013
  10. Wynnson W. Tom, Benjamin M.Yeh, Jonathan C.Cheng, Aliya Qayyum, Bonnie Joe, Fergus V. Coakley, Hepatic Pseudotumor Due to Nodular Fatty Sparig, AJR, 183, 721-724, 2004 https://doi.org/10.2214/ajr.183.3.1830721
  11. Size Wu, Rong Tu, Enhai Zheng, Yusen Shi, Guangqing Liu, Finding and Implications of Focal Fatty Sparing of the Liver at Follow-up, J Ultrasound Med, 32, 1695-1702, 2014
  12. Xiaofeng Yang, Srini Tridandapani, Jonathan J.B, David S.Y, Emi J.Y, Walter J.C, Tian Liu, Ultrasound GLCM texture analysis of radiation-induced parotid-gland injury in head-and-neck cancer radiotherapy, Med Phys, 39(9), 2012
  13. Abou zaid Sayed Abou zaid, Mohamed Waleed Fakhr, Ahmed Farag Ali Mohamed, Automatic Dignosis of Liver Diseases from Ultrasound Images, ICCES, 26, 5-7, 2006
  14. JY Choi, Study on the Quantitative of Gray level of Liver and Kidney Parenchyma with Micro-Ultrasound Histogram Normal and Fatty liver rodent model, 35-55, The grduate school of Korea University, 2013
  15. Nitish Zulpe, Vrushsen Pawan, GLCM Texture Features for Brain Tumor Classification, IJCSI, 9(3), 2012
  16. Diehl AM, Nonalcoholic steatohepatitis, Semin Liver Dis, 19, 221-229, 1999 https://doi.org/10.1055/s-2007-1007111
  17. Joongwon Park, Byungchul Yoo, Pathogenesis of Nonalcoholic Steatohepatitis: Role of Lipid Peroxidation, Mitochondrial Dysfunction and Cytokines. Dep of Medine, Chung-Ang University College of Medicine, Seoul, Korea, 38, 1-8, 2001
  18. J. C. Bamber, M. Tristam, Diagnostic Ultrasound in the Physics of Mwdical Imaging, Institude of Phsics Publishing, 319-388, 1988.
  19. Hyun-Woo Jang, Kang-Beak Kim, Chang-Woo Kim, The Classification of Fatty Liver by Ultrasound Imaging using Computerizing Method, JKIICE, 17(9), 2206-2212, 2013
  20. Nitish Zulpe, Vrushsen Pawan, GLCM Texture Features for Brain Tumor Classification, IJCSI, 9(3), 354-359, 2012