Segmentation Of Blood Clot MRI Images Using Intuitionistic Fuzzy Set Theory

Nur Lyana Shahfiqa Binti Albashah, Sarat Chandra Dass, Vijanth Sagayan Asirvadam, Fabrice Meriaudeau

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)


This paper presents the segmentation method to differentiate between hard and soft clot regions of blood clots in ischemic stroke patients. This is important in planning treatment options for stroke patients as the nature of the clot determines the type of treatment. The gradient echo sequence is used to produce MRI datasets. The MRI blood clot image consists of hard and soft clot regions which have different intensity values. However, the blood clot regions are adjacent to each other, not homogeneous and have unclear boundaries which are the main problems when segmenting the regions. Intuitionistic fuzzy fusion methodology is used to help enhance the noisy image and is shown to lead good segmentation result while using the spatial version of intuitionistic fuzzy c-mean clustering with dice coefficient of 0.8270 and 0.819 for hard clot region and soft clot region respectively.

Original languageEnglish
Title of host publication2018 IEEE-EMBS Conference on Biomedical Engineering and Sciences (IECBES)
ISBN (Electronic)978-1-5386-2471-5
Publication statusE-pub ahead of print - 28 Jan 2019
Event2018 IEEE EMBS Conference on Biomedical Engineering and Sciences - Sarawak, Malaysia
Duration: 3 Dec 20186 Dec 2018


Conference2018 IEEE EMBS Conference on Biomedical Engineering and Sciences
Abbreviated titleIECBES 2018


  • Image fusion
  • Image segmentation
  • Intuitionistic fuzzy set
  • Ischemic stroke

ASJC Scopus subject areas

  • Biomedical Engineering
  • Medicine (miscellaneous)
  • Health Informatics
  • Instrumentation

Cite this