腹部MR画像における肝硬変の自動識別法の開発 Development of an Automated Method for Differentiation of Cirrhotic Liver in Abdominal MR Images

この論文にアクセスする

この論文をさがす

著者

    • 李 文光 LI Wenguang
    • 岐阜大学大学院工学研究科応用情報学専攻 Department of Information Science, Graduate School of Engineering, Gifu University
    • 張 学軍 ZHANG Xuejun
    • 岐阜大学大学院工学研究科応用情報学専攻 Department of Information Science, Graduate School of Engineering, Gifu University
    • 原 武史 HARA Takeshi
    • 岐阜大学大学院医学研究科知能イメージ情報部門 Department of Intelligent Image Information, Graduate School of Medicine, Gifu University
    • 周 向栄 ZHOU Xiangrong
    • 岐阜大学大学院医学研究科知能イメージ情報部門 Department of Intelligent Image Information, Graduate School of Medicine, Gifu University
    • 藤田 広志 FUJITA Hiroshi
    • 岐阜大学大学院医学研究科知能イメージ情報部門 Department of Intelligent Image Information, Graduate School of Medicine, Gifu University
    • 加藤 博基 KATO Hiroki
    • 岐阜大学医学部放射線・腫瘍・画像医学 Department of Radiology, Gifu University School of Medicine
    • 星 博昭 HOSHI Hiroaki
    • 岐阜大学医学部放射線・腫瘍・画像医学 Department of Radiology, Gifu University School of Medicine

抄録

Cirrhosis of liver is a late stage of progressive liver disease defined as structural distortion of entire liver by fibrosis and parenchymal nodules. As the liver regenerates, fibrous connective tissue forms that may cause gross and microscopic distortion of normal hepatic morphology. In MR images, shape and texture analysis is regarded as an important and useful tool to differentiate cirrhosis from normal liver. In this paper, we propose a method to calculate the shape features from the segmented liver regions on MR image. Meanwhile, the texture features are quantified by using gray-level difference method (GLDM) within the small ROIs (regions of interest) selected in the liver region. The degree of liver cirrhosis is derived from integrating the shape and texture features of liver into a three-layer feed-forward artificial neural network (ANN). A liver is finally regarded as cirrhosis if the percentage of the ROIs with the degree over 0.5 is greater than 50%. The initial result showed that the ANN based method classified liver cirrhosis with a training accuracy of 100% on the 100 ROIs in the training set and that 82% liver cirrhosis and 100% normal cases were correctly differentiated from 18 test cases, which demonstrates the effectiveness of our proposed method.

収録刊行物

  • 医用画像情報学会雑誌 = Japanese journal of imaging and information sciences in medicine

    医用画像情報学会雑誌 = Japanese journal of imaging and information sciences in medicine 21(2), 194-200, 2004-05-01

    医用画像情報学会

参考文献:  7件中 1-7件 を表示

被引用文献:  1件中 1-1件 を表示

各種コード

  • NII論文ID(NAID)
    10013041965
  • NII書誌ID(NCID)
    AN10156808
  • 本文言語コード
    JPN
  • 資料種別
    SHO
  • ISSN
    09101543
  • データ提供元
    CJP書誌  CJP引用  IR  J-STAGE 
ページトップへ