2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) 2015
DOI: 10.1109/embc.2015.7318882
|View full text |Cite
|
Sign up to set email alerts
|

3-dimensional throat region segmentation from MRI data based on fourier interpolation and 3-dimensional level set methods

Abstract: Abstract-A new algorithm for 3D throat region segmentation from magnetic resonance imaging (MRI) is presented. The proposed algorithm initially pre-processes the MRI data to increase the contrast between the throat region and its surrounding tissues and also to reduce artifacts. Isotropic 3D volume is reconstructed using Fast Fourier Transform based interpolation. Furthermore, a cube encompassing the throat region is evolved using level set method to form a smooth 3D boundary of the throat region. The results … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1

Citation Types

0
12
0

Year Published

2016
2016
2021
2021

Publication Types

Select...
3
2

Relationship

2
3

Authors

Journals

citations
Cited by 5 publications
(12 citation statements)
references
References 17 publications
0
12
0
Order By: Relevance
“…The MRI data used in this work has anisotropic voxels, while 3D LSM only works well on isotropic voxels. Original voxels are converted to isotopic voxels through Fourier interpolation, which was introduced in [9]. The volume for LSM segmentation is reconstructed in 3D using both real and interpolated slices.…”
Section: A Image Pre-processingmentioning
confidence: 99%
See 1 more Smart Citation
“…The MRI data used in this work has anisotropic voxels, while 3D LSM only works well on isotropic voxels. Original voxels are converted to isotopic voxels through Fourier interpolation, which was introduced in [9]. The volume for LSM segmentation is reconstructed in 3D using both real and interpolated slices.…”
Section: A Image Pre-processingmentioning
confidence: 99%
“…Our previous work [8] presented an automatic 2D tumour segmentation method, which was tested on real MRI slices. In [9], 3D throat detection was obtained as interpolation of segmented 2D MRI slices. The novel work presented in this paper addresses the automatic extraction of 3D tumour models (with poor contrast difference) from a series of MRI slices, using a new 3D level set method (LSM).…”
Section: Introductionmentioning
confidence: 99%
“…The MRI data used in this work has anisotropic voxels, while 3D LSM only works well on isotropic voxels. Original voxels are converted to isotopic voxels through Fourier interpolation, which was introduced in [11]. The volume for LSM segmentation is reconstructed in 3D using both real and interpolated slices.…”
Section: A Image Pre-processingmentioning
confidence: 99%
“…Introduction: Three-dimensional (3D) level set method (LSM) [1,2] is widely used for the segmentation of anatomical structures from medical imaging volumes with promising results [3][4][5]. In 3D LSM, a closed 3D surface S(t) propagates in time towards the desired boundaries through the iterative evolution of a 4D implicit function known as level set function ϕ(X, t).…”
mentioning
confidence: 99%
“…Therefore, to be able to apply 3D LSM to anisotropic (non-cubic) medical imaging volumes, where the distance between consecutive slices along the z-dimension is significantly greater than the in-plane (x−y) pixel size ( Fig. 1a), interpolation is performed in [3][4][5] to reconstruct isotropic (cubic) volumes before segmentation using 3D LSM. However, no direct numerical comparison is provided in [3][4][5] between segmentation results obtained from 3D LSM only and segmentation results obtained from interpolation before and after 3D LSM, to validate the importance of performing interpolation before 3D LSM.…”
mentioning
confidence: 99%