Fuzzy segmentation of endorrhachis in magnetic resonance images and its fuzzy maximum intensity projection

Authors:
Yutaka Hata;Syoji Kobashi
Affiliations:
Division of Computer Engineering, Department of Electrical Engineering and Computer Sciences, Graduate School of Engineering, University of Hyogo, 2167 Shosha, Himeji 671-2280, Japan;Division of Computer Engineering, Department of Electrical Engineering and Computer Sciences, Graduate School of Engineering, University of Hyogo, 2167 Shosha, Himeji 671-2280, Japan
Venue:
Applied Soft Computing
Year:
2009

Citing 9
Cited 1

Fast sliding thin slab volume visualization

Proceedings of the 1996 symposium on Volume visualization
Fuzzy Models and Algorithms for Pattern Recognition and Image Processing

Fuzzy Models and Algorithms for Pattern Recognition and Image Processing
Level set segmentation from multiple non-uniform volume datasets

Proceedings of the conference on Visualization '02
Blobworld: Image Segmentation Using Expectation-Maximization and Its Application to Image Querying

IEEE Transactions on Pattern Analysis and Machine Intelligence
Retrospective Correction of MR Intensity Inhomogeneity by Information Minimization

MICCAI '00 Proceedings of the Third International Conference on Medical Image Computing and Computer-Assisted Intervention
Segmentation of tissue boundary evolution from brain MR image sequences using multi-phase level sets

Computer Vision and Image Understanding
A new segmentation system for brain MR images based on fuzzy techniques

Applied Soft Computing
Automated segmentation of human brain MR images aided by fuzzy information granulation and fuzzy inference

IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews
A 3-D Active Shape Model Driven by Fuzzy Inference: Application to Cardiac CT and MR

IEEE Transactions on Information Technology in Biomedicine

Modified local entropy-based transition region extraction and thresholding

Applied Soft Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper describes a fuzzy segmentation approach and the rendering technique called fuzzy maximum intensity projection (FMIP) for the endorrhachis in magnetic resonance images. First, we propose a fuzzy segmentation procedure, which assigns the high fuzzy degree for the high possibility to the endorrhachis. Second, we describe FMIP, which projects higher fuzzy membership degrees to brighter values in the 2D plane for every voxel in the volume dataset. This enables us to visualize regions of interest with higher accuracy after the fuzzy segmentation is done in the dataset. The applicability of them is tested in the visualization of the endorrhachis in magnetic resonance images. A comparison between FMIP and MIP shows that FMIP visualizes it more effectively.