Loading…

Split Bregman method based level set formulations for segmentation and correction with application to MR images and color images

At present, magnetic resonance (MR) images have gradually become a major aid for clinical medicine, which has greatly improved the doctor's diagnosis rate. Accurate and fast segmentation of MR images plays an extremely important role in medical research. However, due to the influence of externa...

Full description

Saved in:
Bibliographic Details
Published in:Magnetic resonance imaging 2019-04, Vol.57, p.50-67
Main Authors: Yang, Yunyun, Tian, Dongcai, Jia, Wenjing, Shu, Xiu, Wu, Boying
Format: Article
Language:English
Subjects:
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c353t-dfe9fc2ceba62bb876c79bd402a52ec985e11c456cb79b91312b9e56a04337123
cites cdi_FETCH-LOGICAL-c353t-dfe9fc2ceba62bb876c79bd402a52ec985e11c456cb79b91312b9e56a04337123
container_end_page 67
container_issue
container_start_page 50
container_title Magnetic resonance imaging
container_volume 57
creator Yang, Yunyun
Tian, Dongcai
Jia, Wenjing
Shu, Xiu
Wu, Boying
description At present, magnetic resonance (MR) images have gradually become a major aid for clinical medicine, which has greatly improved the doctor's diagnosis rate. Accurate and fast segmentation of MR images plays an extremely important role in medical research. However, due to the influence of external factors and the defects of imaging devices, the MR images have severe intensity inhomogeneity, which poses a great challenge to accurately segment MR images. To deal with this problem, this paper presents an improved active contour model by combining the level set evolution model (LSE) and the split Bregman method, and gives the two-phase, the multi-phase and the vector-valued formulations of our model, respectively. The use of the split Bregman method accelerates the minimization process of our model by reducing the computation time and iterative times. A slowly varying bias field is added into the energy functional, which is the key to correct inhomogeneous images. By estimating the bias fields, not only can we get accurate image segmentation results, but also a homogeneous image after correction is provided. Then we apply our model to segment a large amount of synthetic and real MR images, including gray and color images. Experimental results show that our model can provide satisfactory segmentation and correction results for both gray and color images. Besides, compared with the LSE model, our model has higher accuracy and is superior to the LSE model. In addition, experimental results also demonstrate that our model has the advantages of being insensitive to initial contours and robust to noises. •An improved active contour model is proposed, including the two-phase, multi-phase and vector-valued formulation.•The proposed model is applied to accurately segment and correct a total of 67 images with intensity inhomogeneity.•The application of the split Bregman method has made great improvements in the computational efficiency.•The efficiency, higher segmentation accuracy and better correction effects of the proposed model are numerically verified.•Qualitative and quantitative comparisons show the robustness of the proposed model to the initial contours and noises.
doi_str_mv 10.1016/j.mri.2018.10.005
format article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_2121499697</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0730725X18302492</els_id><sourcerecordid>2121499697</sourcerecordid><originalsourceid>FETCH-LOGICAL-c353t-dfe9fc2ceba62bb876c79bd402a52ec985e11c456cb79b91312b9e56a04337123</originalsourceid><addsrcrecordid>eNp9kM1O3DAUhS3UihmmfYBuKi-7yeCfOInFChB_EgiJtlJ3luPcDB4l8WA7IHZ9dBwy7ZKVdY-_e2R_CH2jZE0JLY63697bNSO0SvOaEHGAlrQqeSYqmX9CS1JykpVM_FmgoxC2JBGMi0O04ISzgolqif7-3HU24jMPm14PuIf46Bpc6wAN7uAZOhwg4tb5fux0tG4I05DCTQ9DfE-wHhpsnPdg3scXGx-x3qVeM99Hh-8esO31BsIe7lLHHHxBn1vdBfi6P1fo9-XFr_Pr7Pb-6ub89DYzXPCYNS3I1jADtS5YXVdlYUpZNzlhWjAwshJAqclFYeqUS8opqyWIQpOc85IyvkI_5t6dd08jhKh6Gwx0nR7AjUExymguZSHLhNIZNd6F4KFVO58e618VJWoSr7YqiVeT-ClKWtPO9339WPfQ_N_4ZzoBJzMA6ZPPFrwKxsJgoLGTONU4-0H9G0CIleg</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2121499697</pqid></control><display><type>article</type><title>Split Bregman method based level set formulations for segmentation and correction with application to MR images and color images</title><source>ScienceDirect Freedom Collection 2022-2024</source><creator>Yang, Yunyun ; Tian, Dongcai ; Jia, Wenjing ; Shu, Xiu ; Wu, Boying</creator><creatorcontrib>Yang, Yunyun ; Tian, Dongcai ; Jia, Wenjing ; Shu, Xiu ; Wu, Boying</creatorcontrib><description>At present, magnetic resonance (MR) images have gradually become a major aid for clinical medicine, which has greatly improved the doctor's diagnosis rate. Accurate and fast segmentation of MR images plays an extremely important role in medical research. However, due to the influence of external factors and the defects of imaging devices, the MR images have severe intensity inhomogeneity, which poses a great challenge to accurately segment MR images. To deal with this problem, this paper presents an improved active contour model by combining the level set evolution model (LSE) and the split Bregman method, and gives the two-phase, the multi-phase and the vector-valued formulations of our model, respectively. The use of the split Bregman method accelerates the minimization process of our model by reducing the computation time and iterative times. A slowly varying bias field is added into the energy functional, which is the key to correct inhomogeneous images. By estimating the bias fields, not only can we get accurate image segmentation results, but also a homogeneous image after correction is provided. Then we apply our model to segment a large amount of synthetic and real MR images, including gray and color images. Experimental results show that our model can provide satisfactory segmentation and correction results for both gray and color images. Besides, compared with the LSE model, our model has higher accuracy and is superior to the LSE model. In addition, experimental results also demonstrate that our model has the advantages of being insensitive to initial contours and robust to noises. •An improved active contour model is proposed, including the two-phase, multi-phase and vector-valued formulation.•The proposed model is applied to accurately segment and correct a total of 67 images with intensity inhomogeneity.•The application of the split Bregman method has made great improvements in the computational efficiency.•The efficiency, higher segmentation accuracy and better correction effects of the proposed model are numerically verified.•Qualitative and quantitative comparisons show the robustness of the proposed model to the initial contours and noises.</description><identifier>ISSN: 0730-725X</identifier><identifier>EISSN: 1873-5894</identifier><identifier>DOI: 10.1016/j.mri.2018.10.005</identifier><identifier>PMID: 30326258</identifier><language>eng</language><publisher>Netherlands: Elsevier Inc</publisher><subject>Bias correction ; Color images ; Image segmentation ; Intensity inhomogeneity ; MR images ; Split Bregman method</subject><ispartof>Magnetic resonance imaging, 2019-04, Vol.57, p.50-67</ispartof><rights>2018 Elsevier Inc.</rights><rights>Copyright © 2018 Elsevier Inc. All rights reserved.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c353t-dfe9fc2ceba62bb876c79bd402a52ec985e11c456cb79b91312b9e56a04337123</citedby><cites>FETCH-LOGICAL-c353t-dfe9fc2ceba62bb876c79bd402a52ec985e11c456cb79b91312b9e56a04337123</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27924,27925</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/30326258$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Yang, Yunyun</creatorcontrib><creatorcontrib>Tian, Dongcai</creatorcontrib><creatorcontrib>Jia, Wenjing</creatorcontrib><creatorcontrib>Shu, Xiu</creatorcontrib><creatorcontrib>Wu, Boying</creatorcontrib><title>Split Bregman method based level set formulations for segmentation and correction with application to MR images and color images</title><title>Magnetic resonance imaging</title><addtitle>Magn Reson Imaging</addtitle><description>At present, magnetic resonance (MR) images have gradually become a major aid for clinical medicine, which has greatly improved the doctor's diagnosis rate. Accurate and fast segmentation of MR images plays an extremely important role in medical research. However, due to the influence of external factors and the defects of imaging devices, the MR images have severe intensity inhomogeneity, which poses a great challenge to accurately segment MR images. To deal with this problem, this paper presents an improved active contour model by combining the level set evolution model (LSE) and the split Bregman method, and gives the two-phase, the multi-phase and the vector-valued formulations of our model, respectively. The use of the split Bregman method accelerates the minimization process of our model by reducing the computation time and iterative times. A slowly varying bias field is added into the energy functional, which is the key to correct inhomogeneous images. By estimating the bias fields, not only can we get accurate image segmentation results, but also a homogeneous image after correction is provided. Then we apply our model to segment a large amount of synthetic and real MR images, including gray and color images. Experimental results show that our model can provide satisfactory segmentation and correction results for both gray and color images. Besides, compared with the LSE model, our model has higher accuracy and is superior to the LSE model. In addition, experimental results also demonstrate that our model has the advantages of being insensitive to initial contours and robust to noises. •An improved active contour model is proposed, including the two-phase, multi-phase and vector-valued formulation.•The proposed model is applied to accurately segment and correct a total of 67 images with intensity inhomogeneity.•The application of the split Bregman method has made great improvements in the computational efficiency.•The efficiency, higher segmentation accuracy and better correction effects of the proposed model are numerically verified.•Qualitative and quantitative comparisons show the robustness of the proposed model to the initial contours and noises.</description><subject>Bias correction</subject><subject>Color images</subject><subject>Image segmentation</subject><subject>Intensity inhomogeneity</subject><subject>MR images</subject><subject>Split Bregman method</subject><issn>0730-725X</issn><issn>1873-5894</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><recordid>eNp9kM1O3DAUhS3UihmmfYBuKi-7yeCfOInFChB_EgiJtlJ3luPcDB4l8WA7IHZ9dBwy7ZKVdY-_e2R_CH2jZE0JLY63697bNSO0SvOaEHGAlrQqeSYqmX9CS1JykpVM_FmgoxC2JBGMi0O04ISzgolqif7-3HU24jMPm14PuIf46Bpc6wAN7uAZOhwg4tb5fux0tG4I05DCTQ9DfE-wHhpsnPdg3scXGx-x3qVeM99Hh-8esO31BsIe7lLHHHxBn1vdBfi6P1fo9-XFr_Pr7Pb-6ub89DYzXPCYNS3I1jADtS5YXVdlYUpZNzlhWjAwshJAqclFYeqUS8opqyWIQpOc85IyvkI_5t6dd08jhKh6Gwx0nR7AjUExymguZSHLhNIZNd6F4KFVO58e618VJWoSr7YqiVeT-ClKWtPO9339WPfQ_N_4ZzoBJzMA6ZPPFrwKxsJgoLGTONU4-0H9G0CIleg</recordid><startdate>20190401</startdate><enddate>20190401</enddate><creator>Yang, Yunyun</creator><creator>Tian, Dongcai</creator><creator>Jia, Wenjing</creator><creator>Shu, Xiu</creator><creator>Wu, Boying</creator><general>Elsevier Inc</general><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7X8</scope></search><sort><creationdate>20190401</creationdate><title>Split Bregman method based level set formulations for segmentation and correction with application to MR images and color images</title><author>Yang, Yunyun ; Tian, Dongcai ; Jia, Wenjing ; Shu, Xiu ; Wu, Boying</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c353t-dfe9fc2ceba62bb876c79bd402a52ec985e11c456cb79b91312b9e56a04337123</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Bias correction</topic><topic>Color images</topic><topic>Image segmentation</topic><topic>Intensity inhomogeneity</topic><topic>MR images</topic><topic>Split Bregman method</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Yang, Yunyun</creatorcontrib><creatorcontrib>Tian, Dongcai</creatorcontrib><creatorcontrib>Jia, Wenjing</creatorcontrib><creatorcontrib>Shu, Xiu</creatorcontrib><creatorcontrib>Wu, Boying</creatorcontrib><collection>PubMed</collection><collection>CrossRef</collection><collection>MEDLINE - Academic</collection><jtitle>Magnetic resonance imaging</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Yang, Yunyun</au><au>Tian, Dongcai</au><au>Jia, Wenjing</au><au>Shu, Xiu</au><au>Wu, Boying</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Split Bregman method based level set formulations for segmentation and correction with application to MR images and color images</atitle><jtitle>Magnetic resonance imaging</jtitle><addtitle>Magn Reson Imaging</addtitle><date>2019-04-01</date><risdate>2019</risdate><volume>57</volume><spage>50</spage><epage>67</epage><pages>50-67</pages><issn>0730-725X</issn><eissn>1873-5894</eissn><abstract>At present, magnetic resonance (MR) images have gradually become a major aid for clinical medicine, which has greatly improved the doctor's diagnosis rate. Accurate and fast segmentation of MR images plays an extremely important role in medical research. However, due to the influence of external factors and the defects of imaging devices, the MR images have severe intensity inhomogeneity, which poses a great challenge to accurately segment MR images. To deal with this problem, this paper presents an improved active contour model by combining the level set evolution model (LSE) and the split Bregman method, and gives the two-phase, the multi-phase and the vector-valued formulations of our model, respectively. The use of the split Bregman method accelerates the minimization process of our model by reducing the computation time and iterative times. A slowly varying bias field is added into the energy functional, which is the key to correct inhomogeneous images. By estimating the bias fields, not only can we get accurate image segmentation results, but also a homogeneous image after correction is provided. Then we apply our model to segment a large amount of synthetic and real MR images, including gray and color images. Experimental results show that our model can provide satisfactory segmentation and correction results for both gray and color images. Besides, compared with the LSE model, our model has higher accuracy and is superior to the LSE model. In addition, experimental results also demonstrate that our model has the advantages of being insensitive to initial contours and robust to noises. •An improved active contour model is proposed, including the two-phase, multi-phase and vector-valued formulation.•The proposed model is applied to accurately segment and correct a total of 67 images with intensity inhomogeneity.•The application of the split Bregman method has made great improvements in the computational efficiency.•The efficiency, higher segmentation accuracy and better correction effects of the proposed model are numerically verified.•Qualitative and quantitative comparisons show the robustness of the proposed model to the initial contours and noises.</abstract><cop>Netherlands</cop><pub>Elsevier Inc</pub><pmid>30326258</pmid><doi>10.1016/j.mri.2018.10.005</doi><tpages>18</tpages></addata></record>
fulltext fulltext
identifier ISSN: 0730-725X
ispartof Magnetic resonance imaging, 2019-04, Vol.57, p.50-67
issn 0730-725X
1873-5894
language eng
recordid cdi_proquest_miscellaneous_2121499697
source ScienceDirect Freedom Collection 2022-2024
subjects Bias correction
Color images
Image segmentation
Intensity inhomogeneity
MR images
Split Bregman method
title Split Bregman method based level set formulations for segmentation and correction with application to MR images and color images
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-23T15%3A37%3A59IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Split%20Bregman%20method%20based%20level%20set%20formulations%20for%20segmentation%20and%20correction%20with%20application%20to%20MR%20images%20and%20color%20images&rft.jtitle=Magnetic%20resonance%20imaging&rft.au=Yang,%20Yunyun&rft.date=2019-04-01&rft.volume=57&rft.spage=50&rft.epage=67&rft.pages=50-67&rft.issn=0730-725X&rft.eissn=1873-5894&rft_id=info:doi/10.1016/j.mri.2018.10.005&rft_dat=%3Cproquest_cross%3E2121499697%3C/proquest_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c353t-dfe9fc2ceba62bb876c79bd402a52ec985e11c456cb79b91312b9e56a04337123%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2121499697&rft_id=info:pmid/30326258&rfr_iscdi=true