Clustered Redundant Keypoint Elimination SURF method in MRI Image Registration based on Alpha-Trimmed Relationship
The process of MRI image registration is one of the important branches in MRI image analysis, which is a necessary preprocessing to the use of information in these images. The Clustered Adaptive Keypoint Elimination method-SIFT (CRKEM-SIFT) algorithm has recently been introduced to eliminate redund...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
Tehran University of Medical Sciences
2023-03-01
|
Series: | Frontiers in Biomedical Technologies |
Subjects: | |
Online Access: | https://fbt.tums.ac.ir/index.php/fbt/article/view/459 |
_version_ | 1797840388116971520 |
---|---|
author | Zahra Hossein-Nejad Mehdi Nasri |
author_facet | Zahra Hossein-Nejad Mehdi Nasri |
author_sort | Zahra Hossein-Nejad |
collection | DOAJ |
description |
The process of MRI image registration is one of the important branches in MRI image analysis, which is a necessary preprocessing to the use of information in these images. The Clustered Adaptive Keypoint Elimination method-SIFT (CRKEM-SIFT) algorithm has recently been introduced to eliminate redundancies and upgrade the precision corresponding. The disadvantages of this algorithm are the high execution time and the number of incorrect correspondences. In this paper, to increase the accuracy and speed of MRI image registration, first, the CRKEM method is used on the SURF algorithm. Then, Spatial Relations Correspondence (SRC) and Alpha-Trimmed Spatial Relations Correspondence (ATSRC) methods are suggested to improve correspondences. These suggested methods, unlike conventional methods such as RANSAC, which only eliminates incorrect correspondences, in these suggested methods based on spatial relationships, detect incorrect correspondences and turn them into correct correspondences. Converting incorrect correspondences to correct ones can increase the number of correct correspondences and ultimately increase the precision correspondences. The simulation results confirm the suggested approaches' superiority on standard brain databases compared to classic methods in terms of Maximum error (MAE) and precision.
|
first_indexed | 2024-04-09T16:14:14Z |
format | Article |
id | doaj.art-1b13456ad78442e981dfdd931d18a990 |
institution | Directory Open Access Journal |
issn | 2345-5837 |
language | English |
last_indexed | 2024-04-09T16:14:14Z |
publishDate | 2023-03-01 |
publisher | Tehran University of Medical Sciences |
record_format | Article |
series | Frontiers in Biomedical Technologies |
spelling | doaj.art-1b13456ad78442e981dfdd931d18a9902023-04-24T06:46:08ZengTehran University of Medical SciencesFrontiers in Biomedical Technologies2345-58372023-03-0110210.18502/fbt.v10i2.12216Clustered Redundant Keypoint Elimination SURF method in MRI Image Registration based on Alpha-Trimmed RelationshipZahra Hossein-Nejad0Mehdi Nasri1Islamic Azad University, Sirjan branchIslamic Azad University, Khomeinishar branch The process of MRI image registration is one of the important branches in MRI image analysis, which is a necessary preprocessing to the use of information in these images. The Clustered Adaptive Keypoint Elimination method-SIFT (CRKEM-SIFT) algorithm has recently been introduced to eliminate redundancies and upgrade the precision corresponding. The disadvantages of this algorithm are the high execution time and the number of incorrect correspondences. In this paper, to increase the accuracy and speed of MRI image registration, first, the CRKEM method is used on the SURF algorithm. Then, Spatial Relations Correspondence (SRC) and Alpha-Trimmed Spatial Relations Correspondence (ATSRC) methods are suggested to improve correspondences. These suggested methods, unlike conventional methods such as RANSAC, which only eliminates incorrect correspondences, in these suggested methods based on spatial relationships, detect incorrect correspondences and turn them into correct correspondences. Converting incorrect correspondences to correct ones can increase the number of correct correspondences and ultimately increase the precision correspondences. The simulation results confirm the suggested approaches' superiority on standard brain databases compared to classic methods in terms of Maximum error (MAE) and precision. https://fbt.tums.ac.ir/index.php/fbt/article/view/459brain image registrationCRKEM-SIFTspatial relationsredundant keypointsMRI |
spellingShingle | Zahra Hossein-Nejad Mehdi Nasri Clustered Redundant Keypoint Elimination SURF method in MRI Image Registration based on Alpha-Trimmed Relationship Frontiers in Biomedical Technologies brain image registration CRKEM-SIFT spatial relations redundant keypoints MRI |
title | Clustered Redundant Keypoint Elimination SURF method in MRI Image Registration based on Alpha-Trimmed Relationship |
title_full | Clustered Redundant Keypoint Elimination SURF method in MRI Image Registration based on Alpha-Trimmed Relationship |
title_fullStr | Clustered Redundant Keypoint Elimination SURF method in MRI Image Registration based on Alpha-Trimmed Relationship |
title_full_unstemmed | Clustered Redundant Keypoint Elimination SURF method in MRI Image Registration based on Alpha-Trimmed Relationship |
title_short | Clustered Redundant Keypoint Elimination SURF method in MRI Image Registration based on Alpha-Trimmed Relationship |
title_sort | clustered redundant keypoint elimination surf method in mri image registration based on alpha trimmed relationship |
topic | brain image registration CRKEM-SIFT spatial relations redundant keypoints MRI |
url | https://fbt.tums.ac.ir/index.php/fbt/article/view/459 |
work_keys_str_mv | AT zahrahosseinnejad clusteredredundantkeypointeliminationsurfmethodinmriimageregistrationbasedonalphatrimmedrelationship AT mehdinasri clusteredredundantkeypointeliminationsurfmethodinmriimageregistrationbasedonalphatrimmedrelationship |