Mr image volume segmentation using neuro-fuzzy method / Ahmad Safwan Mohamed Makki
Segmentation is in many cases the bottleneck when trying to use radiological image data in many clinically important applications as radiological diagnosis, monitoring, radiotherapy and surgical planning. While manual segmentation is often regarded as a gold standard, its usage is not acceptable in...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Published: |
2003
|
| Subjects: | |
| Online Access: | http://studentsrepo.um.edu.my/10318/1/Ahmad_safwan_Mohamed_Makki.pdf http://studentsrepo.um.edu.my/10318/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Segmentation is in many cases the bottleneck when trying to use radiological image data in many clinically important applications as radiological diagnosis, monitoring, radiotherapy and surgical planning. While manual segmentation is often regarded as a gold standard, its usage is not acceptable in some clinical situations.
A new breed of methodologies improves on the shortcoming of the traditional methods. These new solution are describing as intelligent and encompass fuzzy logic and neural network. Fuzzy logic and Neural network are complimentary and can be combined to form a neuro-fuzzy approach. This overcomes the shortcoming of both and can provide a robust and intelligent methodology for image analysis. This documentation is about the implementation of neuro-fuzzy approach using Fuzzy Hopfield Neural Network (FHNN) algorithm for the segmentation process of MR image data sets. |
|---|