Deformable image registration by combining uncertainty estimates from supervoxel belief propagation
Discrete optimisation strategies have a number of advantages over their continuous counterparts for deformable registration of medical images. For example: it is not necessary to compute derivatives of the similarity term; dense sampling of the search space reduces the risk of becoming trapped in lo...
Ausführliche Beschreibung
Gespeichert in:
| Autor*in: |
Heinrich, Mattias P [verfasserIn] |
|---|
| Format: |
Artikel |
|---|---|
| Sprache: |
Englisch |
| Erschienen: |
2016 |
|---|
| Rechteinformationen: |
Nutzungsrecht: Copyright © 2015 Elsevier B.V. All rights reserved. |
|---|
| Übergeordnetes Werk: |
Enthalten in: Medical image analysis - Amsterdam [u.a.] : Elsevier, 1996, 27(2016), Seite 57-71 |
|---|---|
| Übergeordnetes Werk: |
volume:27 ; year:2016 ; pages:57-71 |
| Links: |
|---|
| DOI / URN: |
10.1016/j.media.2015.09.005 |
|---|
| Katalog-ID: |
OLC1971383376 |
|---|
| LEADER | 01000caa a2200265 4500 | ||
|---|---|---|---|
| 001 | OLC1971383376 | ||
| 003 | DE-627 | ||
| 005 | 20230714181640.0 | ||
| 007 | tu | ||
| 008 | 160212s2016 xx ||||| 00| ||eng c | ||
| 024 | 7 | |a 10.1016/j.media.2015.09.005 |2 doi | |
| 028 | 5 | 2 | |a PQ20160430 |
| 035 | |a (DE-627)OLC1971383376 | ||
| 035 | |a (DE-599)GBVOLC1971383376 | ||
| 035 | |a (PRQ)c1276-e965d3c9343a1a36eb7b0a97790883bed947e7483d45704b3814e73d300965370 | ||
| 035 | |a (KEY)0392983320160000027000000057deformableimageregistrationbycombininguncertaintye | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 082 | 0 | 4 | |a 004 |q ZDB |
| 100 | 1 | |a Heinrich, Mattias P |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Deformable image registration by combining uncertainty estimates from supervoxel belief propagation |
| 264 | 1 | |c 2016 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a ohne Hilfsmittel zu benutzen |b n |2 rdamedia | ||
| 338 | |a Band |b nc |2 rdacarrier | ||
| 520 | |a Discrete optimisation strategies have a number of advantages over their continuous counterparts for deformable registration of medical images. For example: it is not necessary to compute derivatives of the similarity term; dense sampling of the search space reduces the risk of becoming trapped in local optima; and (in principle) an optimum can be found without resorting to iterative coarse-to-fine warping strategies. However, the large complexity of high-dimensional medical data renders a direct voxel-wise estimation of deformation vectors impractical. For this reason, previous work on medical image registration using graphical models has largely relied on using a parameterised deformation model and on the use of iterative coarse-to-fine optimisation schemes. In this paper, we propose an approach that enables accurate voxel-wise deformable registration of high-resolution 3D images without the need for intermediate image warping or a multi-resolution scheme. This is achieved by representing the image domain as multiple comprehensive supervoxel layers and making use of the full marginal distribution of all probable displacement vectors after inferring regularity of the deformations using belief propagation. The optimisation acts on the coarse scale representation of supervoxels, which provides sufficient spatial context and is robust to noise in low contrast areas. Minimum spanning trees, which connect neighbouring supervoxels, are employed to model pair-wise deformation dependencies. The optimal displacement for each voxel is calculated by considering the probabilities for all displacements over all overlapping supervoxel graphs and subsequently seeking the mode of this distribution. We demonstrate the applicability of this concept for two challenging applications: first, for intra-patient motion estimation in lung CT scans; and second, for atlas-based segmentation propagation of MRI brain scans. For lung registration, the voxel-wise mode of displacements is found using the mean-shift algorithm, which enables us to determine continuous valued sub-voxel motion vectors. Finding the mode of brain segmentation labels is performed using a voxel-wise majority voting weighted by the displacement uncertainty estimates. Our experimental results show significant improvements in registration accuracy when using the additional information provided by the registration uncertainty estimates. The multi-layer approach enables fusion of multiple complementary proposals, extending the popular fusion approaches from multi-image registration to probabilistic one-to-one image registration. | ||
| 540 | |a Nutzungsrecht: Copyright © 2015 Elsevier B.V. All rights reserved. | ||
| 700 | 1 | |a Simpson, Ivor J A |4 oth | |
| 700 | 1 | |a Papież, BartŁomiej W |4 oth | |
| 700 | 1 | |a Brady, Sir Michael |4 oth | |
| 700 | 1 | |a Schnabel, Julia A |4 oth | |
| 773 | 0 | 8 | |i Enthalten in |t Medical image analysis |d Amsterdam [u.a.] : Elsevier, 1996 |g 27(2016), Seite 57-71 |w (DE-627)223260010 |w (DE-600)1356436-5 |w (DE-576)080160034 |x 1361-8415 |7 nnns |
| 773 | 1 | 8 | |g volume:27 |g year:2016 |g pages:57-71 |
| 856 | 4 | 1 | |u http://dx.doi.org/10.1016/j.media.2015.09.005 |3 Volltext |
| 856 | 4 | 2 | |u http://www.ncbi.nlm.nih.gov/pubmed/26545720 |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a SYSFLAG_A | ||
| 912 | |a GBV_OLC | ||
| 912 | |a SSG-OLC-MAT | ||
| 912 | |a SSG-OLC-PHA | ||
| 912 | |a SSG-OLC-DE-84 | ||
| 912 | |a GBV_ILN_4219 | ||
| 951 | |a AR | ||
| 952 | |d 27 |j 2016 |h 57-71 | ||
| author_variant |
m p h mp mph |
|---|---|
| matchkey_str |
article:13618415:2016----::eombemgrgsrtobcmiignetitetmtsrmue |
| hierarchy_sort_str |
2016 |
| publishDate |
2016 |
| allfields |
10.1016/j.media.2015.09.005 doi PQ20160430 (DE-627)OLC1971383376 (DE-599)GBVOLC1971383376 (PRQ)c1276-e965d3c9343a1a36eb7b0a97790883bed947e7483d45704b3814e73d300965370 (KEY)0392983320160000027000000057deformableimageregistrationbycombininguncertaintye DE-627 ger DE-627 rakwb eng 004 ZDB Heinrich, Mattias P verfasserin aut Deformable image registration by combining uncertainty estimates from supervoxel belief propagation 2016 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier Discrete optimisation strategies have a number of advantages over their continuous counterparts for deformable registration of medical images. For example: it is not necessary to compute derivatives of the similarity term; dense sampling of the search space reduces the risk of becoming trapped in local optima; and (in principle) an optimum can be found without resorting to iterative coarse-to-fine warping strategies. However, the large complexity of high-dimensional medical data renders a direct voxel-wise estimation of deformation vectors impractical. For this reason, previous work on medical image registration using graphical models has largely relied on using a parameterised deformation model and on the use of iterative coarse-to-fine optimisation schemes. In this paper, we propose an approach that enables accurate voxel-wise deformable registration of high-resolution 3D images without the need for intermediate image warping or a multi-resolution scheme. This is achieved by representing the image domain as multiple comprehensive supervoxel layers and making use of the full marginal distribution of all probable displacement vectors after inferring regularity of the deformations using belief propagation. The optimisation acts on the coarse scale representation of supervoxels, which provides sufficient spatial context and is robust to noise in low contrast areas. Minimum spanning trees, which connect neighbouring supervoxels, are employed to model pair-wise deformation dependencies. The optimal displacement for each voxel is calculated by considering the probabilities for all displacements over all overlapping supervoxel graphs and subsequently seeking the mode of this distribution. We demonstrate the applicability of this concept for two challenging applications: first, for intra-patient motion estimation in lung CT scans; and second, for atlas-based segmentation propagation of MRI brain scans. For lung registration, the voxel-wise mode of displacements is found using the mean-shift algorithm, which enables us to determine continuous valued sub-voxel motion vectors. Finding the mode of brain segmentation labels is performed using a voxel-wise majority voting weighted by the displacement uncertainty estimates. Our experimental results show significant improvements in registration accuracy when using the additional information provided by the registration uncertainty estimates. The multi-layer approach enables fusion of multiple complementary proposals, extending the popular fusion approaches from multi-image registration to probabilistic one-to-one image registration. Nutzungsrecht: Copyright © 2015 Elsevier B.V. All rights reserved. Simpson, Ivor J A oth Papież, BartŁomiej W oth Brady, Sir Michael oth Schnabel, Julia A oth Enthalten in Medical image analysis Amsterdam [u.a.] : Elsevier, 1996 27(2016), Seite 57-71 (DE-627)223260010 (DE-600)1356436-5 (DE-576)080160034 1361-8415 nnns volume:27 year:2016 pages:57-71 http://dx.doi.org/10.1016/j.media.2015.09.005 Volltext http://www.ncbi.nlm.nih.gov/pubmed/26545720 GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT SSG-OLC-PHA SSG-OLC-DE-84 GBV_ILN_4219 AR 27 2016 57-71 |
| spelling |
10.1016/j.media.2015.09.005 doi PQ20160430 (DE-627)OLC1971383376 (DE-599)GBVOLC1971383376 (PRQ)c1276-e965d3c9343a1a36eb7b0a97790883bed947e7483d45704b3814e73d300965370 (KEY)0392983320160000027000000057deformableimageregistrationbycombininguncertaintye DE-627 ger DE-627 rakwb eng 004 ZDB Heinrich, Mattias P verfasserin aut Deformable image registration by combining uncertainty estimates from supervoxel belief propagation 2016 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier Discrete optimisation strategies have a number of advantages over their continuous counterparts for deformable registration of medical images. For example: it is not necessary to compute derivatives of the similarity term; dense sampling of the search space reduces the risk of becoming trapped in local optima; and (in principle) an optimum can be found without resorting to iterative coarse-to-fine warping strategies. However, the large complexity of high-dimensional medical data renders a direct voxel-wise estimation of deformation vectors impractical. For this reason, previous work on medical image registration using graphical models has largely relied on using a parameterised deformation model and on the use of iterative coarse-to-fine optimisation schemes. In this paper, we propose an approach that enables accurate voxel-wise deformable registration of high-resolution 3D images without the need for intermediate image warping or a multi-resolution scheme. This is achieved by representing the image domain as multiple comprehensive supervoxel layers and making use of the full marginal distribution of all probable displacement vectors after inferring regularity of the deformations using belief propagation. The optimisation acts on the coarse scale representation of supervoxels, which provides sufficient spatial context and is robust to noise in low contrast areas. Minimum spanning trees, which connect neighbouring supervoxels, are employed to model pair-wise deformation dependencies. The optimal displacement for each voxel is calculated by considering the probabilities for all displacements over all overlapping supervoxel graphs and subsequently seeking the mode of this distribution. We demonstrate the applicability of this concept for two challenging applications: first, for intra-patient motion estimation in lung CT scans; and second, for atlas-based segmentation propagation of MRI brain scans. For lung registration, the voxel-wise mode of displacements is found using the mean-shift algorithm, which enables us to determine continuous valued sub-voxel motion vectors. Finding the mode of brain segmentation labels is performed using a voxel-wise majority voting weighted by the displacement uncertainty estimates. Our experimental results show significant improvements in registration accuracy when using the additional information provided by the registration uncertainty estimates. The multi-layer approach enables fusion of multiple complementary proposals, extending the popular fusion approaches from multi-image registration to probabilistic one-to-one image registration. Nutzungsrecht: Copyright © 2015 Elsevier B.V. All rights reserved. Simpson, Ivor J A oth Papież, BartŁomiej W oth Brady, Sir Michael oth Schnabel, Julia A oth Enthalten in Medical image analysis Amsterdam [u.a.] : Elsevier, 1996 27(2016), Seite 57-71 (DE-627)223260010 (DE-600)1356436-5 (DE-576)080160034 1361-8415 nnns volume:27 year:2016 pages:57-71 http://dx.doi.org/10.1016/j.media.2015.09.005 Volltext http://www.ncbi.nlm.nih.gov/pubmed/26545720 GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT SSG-OLC-PHA SSG-OLC-DE-84 GBV_ILN_4219 AR 27 2016 57-71 |
| allfields_unstemmed |
10.1016/j.media.2015.09.005 doi PQ20160430 (DE-627)OLC1971383376 (DE-599)GBVOLC1971383376 (PRQ)c1276-e965d3c9343a1a36eb7b0a97790883bed947e7483d45704b3814e73d300965370 (KEY)0392983320160000027000000057deformableimageregistrationbycombininguncertaintye DE-627 ger DE-627 rakwb eng 004 ZDB Heinrich, Mattias P verfasserin aut Deformable image registration by combining uncertainty estimates from supervoxel belief propagation 2016 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier Discrete optimisation strategies have a number of advantages over their continuous counterparts for deformable registration of medical images. For example: it is not necessary to compute derivatives of the similarity term; dense sampling of the search space reduces the risk of becoming trapped in local optima; and (in principle) an optimum can be found without resorting to iterative coarse-to-fine warping strategies. However, the large complexity of high-dimensional medical data renders a direct voxel-wise estimation of deformation vectors impractical. For this reason, previous work on medical image registration using graphical models has largely relied on using a parameterised deformation model and on the use of iterative coarse-to-fine optimisation schemes. In this paper, we propose an approach that enables accurate voxel-wise deformable registration of high-resolution 3D images without the need for intermediate image warping or a multi-resolution scheme. This is achieved by representing the image domain as multiple comprehensive supervoxel layers and making use of the full marginal distribution of all probable displacement vectors after inferring regularity of the deformations using belief propagation. The optimisation acts on the coarse scale representation of supervoxels, which provides sufficient spatial context and is robust to noise in low contrast areas. Minimum spanning trees, which connect neighbouring supervoxels, are employed to model pair-wise deformation dependencies. The optimal displacement for each voxel is calculated by considering the probabilities for all displacements over all overlapping supervoxel graphs and subsequently seeking the mode of this distribution. We demonstrate the applicability of this concept for two challenging applications: first, for intra-patient motion estimation in lung CT scans; and second, for atlas-based segmentation propagation of MRI brain scans. For lung registration, the voxel-wise mode of displacements is found using the mean-shift algorithm, which enables us to determine continuous valued sub-voxel motion vectors. Finding the mode of brain segmentation labels is performed using a voxel-wise majority voting weighted by the displacement uncertainty estimates. Our experimental results show significant improvements in registration accuracy when using the additional information provided by the registration uncertainty estimates. The multi-layer approach enables fusion of multiple complementary proposals, extending the popular fusion approaches from multi-image registration to probabilistic one-to-one image registration. Nutzungsrecht: Copyright © 2015 Elsevier B.V. All rights reserved. Simpson, Ivor J A oth Papież, BartŁomiej W oth Brady, Sir Michael oth Schnabel, Julia A oth Enthalten in Medical image analysis Amsterdam [u.a.] : Elsevier, 1996 27(2016), Seite 57-71 (DE-627)223260010 (DE-600)1356436-5 (DE-576)080160034 1361-8415 nnns volume:27 year:2016 pages:57-71 http://dx.doi.org/10.1016/j.media.2015.09.005 Volltext http://www.ncbi.nlm.nih.gov/pubmed/26545720 GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT SSG-OLC-PHA SSG-OLC-DE-84 GBV_ILN_4219 AR 27 2016 57-71 |
| allfieldsGer |
10.1016/j.media.2015.09.005 doi PQ20160430 (DE-627)OLC1971383376 (DE-599)GBVOLC1971383376 (PRQ)c1276-e965d3c9343a1a36eb7b0a97790883bed947e7483d45704b3814e73d300965370 (KEY)0392983320160000027000000057deformableimageregistrationbycombininguncertaintye DE-627 ger DE-627 rakwb eng 004 ZDB Heinrich, Mattias P verfasserin aut Deformable image registration by combining uncertainty estimates from supervoxel belief propagation 2016 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier Discrete optimisation strategies have a number of advantages over their continuous counterparts for deformable registration of medical images. For example: it is not necessary to compute derivatives of the similarity term; dense sampling of the search space reduces the risk of becoming trapped in local optima; and (in principle) an optimum can be found without resorting to iterative coarse-to-fine warping strategies. However, the large complexity of high-dimensional medical data renders a direct voxel-wise estimation of deformation vectors impractical. For this reason, previous work on medical image registration using graphical models has largely relied on using a parameterised deformation model and on the use of iterative coarse-to-fine optimisation schemes. In this paper, we propose an approach that enables accurate voxel-wise deformable registration of high-resolution 3D images without the need for intermediate image warping or a multi-resolution scheme. This is achieved by representing the image domain as multiple comprehensive supervoxel layers and making use of the full marginal distribution of all probable displacement vectors after inferring regularity of the deformations using belief propagation. The optimisation acts on the coarse scale representation of supervoxels, which provides sufficient spatial context and is robust to noise in low contrast areas. Minimum spanning trees, which connect neighbouring supervoxels, are employed to model pair-wise deformation dependencies. The optimal displacement for each voxel is calculated by considering the probabilities for all displacements over all overlapping supervoxel graphs and subsequently seeking the mode of this distribution. We demonstrate the applicability of this concept for two challenging applications: first, for intra-patient motion estimation in lung CT scans; and second, for atlas-based segmentation propagation of MRI brain scans. For lung registration, the voxel-wise mode of displacements is found using the mean-shift algorithm, which enables us to determine continuous valued sub-voxel motion vectors. Finding the mode of brain segmentation labels is performed using a voxel-wise majority voting weighted by the displacement uncertainty estimates. Our experimental results show significant improvements in registration accuracy when using the additional information provided by the registration uncertainty estimates. The multi-layer approach enables fusion of multiple complementary proposals, extending the popular fusion approaches from multi-image registration to probabilistic one-to-one image registration. Nutzungsrecht: Copyright © 2015 Elsevier B.V. All rights reserved. Simpson, Ivor J A oth Papież, BartŁomiej W oth Brady, Sir Michael oth Schnabel, Julia A oth Enthalten in Medical image analysis Amsterdam [u.a.] : Elsevier, 1996 27(2016), Seite 57-71 (DE-627)223260010 (DE-600)1356436-5 (DE-576)080160034 1361-8415 nnns volume:27 year:2016 pages:57-71 http://dx.doi.org/10.1016/j.media.2015.09.005 Volltext http://www.ncbi.nlm.nih.gov/pubmed/26545720 GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT SSG-OLC-PHA SSG-OLC-DE-84 GBV_ILN_4219 AR 27 2016 57-71 |
| allfieldsSound |
10.1016/j.media.2015.09.005 doi PQ20160430 (DE-627)OLC1971383376 (DE-599)GBVOLC1971383376 (PRQ)c1276-e965d3c9343a1a36eb7b0a97790883bed947e7483d45704b3814e73d300965370 (KEY)0392983320160000027000000057deformableimageregistrationbycombininguncertaintye DE-627 ger DE-627 rakwb eng 004 ZDB Heinrich, Mattias P verfasserin aut Deformable image registration by combining uncertainty estimates from supervoxel belief propagation 2016 Text txt rdacontent ohne Hilfsmittel zu benutzen n rdamedia Band nc rdacarrier Discrete optimisation strategies have a number of advantages over their continuous counterparts for deformable registration of medical images. For example: it is not necessary to compute derivatives of the similarity term; dense sampling of the search space reduces the risk of becoming trapped in local optima; and (in principle) an optimum can be found without resorting to iterative coarse-to-fine warping strategies. However, the large complexity of high-dimensional medical data renders a direct voxel-wise estimation of deformation vectors impractical. For this reason, previous work on medical image registration using graphical models has largely relied on using a parameterised deformation model and on the use of iterative coarse-to-fine optimisation schemes. In this paper, we propose an approach that enables accurate voxel-wise deformable registration of high-resolution 3D images without the need for intermediate image warping or a multi-resolution scheme. This is achieved by representing the image domain as multiple comprehensive supervoxel layers and making use of the full marginal distribution of all probable displacement vectors after inferring regularity of the deformations using belief propagation. The optimisation acts on the coarse scale representation of supervoxels, which provides sufficient spatial context and is robust to noise in low contrast areas. Minimum spanning trees, which connect neighbouring supervoxels, are employed to model pair-wise deformation dependencies. The optimal displacement for each voxel is calculated by considering the probabilities for all displacements over all overlapping supervoxel graphs and subsequently seeking the mode of this distribution. We demonstrate the applicability of this concept for two challenging applications: first, for intra-patient motion estimation in lung CT scans; and second, for atlas-based segmentation propagation of MRI brain scans. For lung registration, the voxel-wise mode of displacements is found using the mean-shift algorithm, which enables us to determine continuous valued sub-voxel motion vectors. Finding the mode of brain segmentation labels is performed using a voxel-wise majority voting weighted by the displacement uncertainty estimates. Our experimental results show significant improvements in registration accuracy when using the additional information provided by the registration uncertainty estimates. The multi-layer approach enables fusion of multiple complementary proposals, extending the popular fusion approaches from multi-image registration to probabilistic one-to-one image registration. Nutzungsrecht: Copyright © 2015 Elsevier B.V. All rights reserved. Simpson, Ivor J A oth Papież, BartŁomiej W oth Brady, Sir Michael oth Schnabel, Julia A oth Enthalten in Medical image analysis Amsterdam [u.a.] : Elsevier, 1996 27(2016), Seite 57-71 (DE-627)223260010 (DE-600)1356436-5 (DE-576)080160034 1361-8415 nnns volume:27 year:2016 pages:57-71 http://dx.doi.org/10.1016/j.media.2015.09.005 Volltext http://www.ncbi.nlm.nih.gov/pubmed/26545720 GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT SSG-OLC-PHA SSG-OLC-DE-84 GBV_ILN_4219 AR 27 2016 57-71 |
| language |
English |
| source |
Enthalten in Medical image analysis 27(2016), Seite 57-71 volume:27 year:2016 pages:57-71 |
| sourceStr |
Enthalten in Medical image analysis 27(2016), Seite 57-71 volume:27 year:2016 pages:57-71 |
| format_phy_str_mv |
Article |
| institution |
findex.gbv.de |
| dewey-raw |
004 |
| isfreeaccess_bool |
false |
| container_title |
Medical image analysis |
| authorswithroles_txt_mv |
Heinrich, Mattias P @@aut@@ Simpson, Ivor J A @@oth@@ Papież, BartŁomiej W @@oth@@ Brady, Sir Michael @@oth@@ Schnabel, Julia A @@oth@@ |
| publishDateDaySort_date |
2016-01-01T00:00:00Z |
| hierarchy_top_id |
223260010 |
| dewey-sort |
14 |
| id |
OLC1971383376 |
| language_de |
englisch |
| fullrecord |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a2200265 4500</leader><controlfield tag="001">OLC1971383376</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230714181640.0</controlfield><controlfield tag="007">tu</controlfield><controlfield tag="008">160212s2016 xx ||||| 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1016/j.media.2015.09.005</subfield><subfield code="2">doi</subfield></datafield><datafield tag="028" ind1="5" ind2="2"><subfield code="a">PQ20160430</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)OLC1971383376</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)GBVOLC1971383376</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(PRQ)c1276-e965d3c9343a1a36eb7b0a97790883bed947e7483d45704b3814e73d300965370</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(KEY)0392983320160000027000000057deformableimageregistrationbycombininguncertaintye</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">004</subfield><subfield code="q">ZDB</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Heinrich, Mattias P</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Deformable image registration by combining uncertainty estimates from supervoxel belief propagation</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2016</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">ohne Hilfsmittel zu benutzen</subfield><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Band</subfield><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Discrete optimisation strategies have a number of advantages over their continuous counterparts for deformable registration of medical images. For example: it is not necessary to compute derivatives of the similarity term; dense sampling of the search space reduces the risk of becoming trapped in local optima; and (in principle) an optimum can be found without resorting to iterative coarse-to-fine warping strategies. However, the large complexity of high-dimensional medical data renders a direct voxel-wise estimation of deformation vectors impractical. For this reason, previous work on medical image registration using graphical models has largely relied on using a parameterised deformation model and on the use of iterative coarse-to-fine optimisation schemes. In this paper, we propose an approach that enables accurate voxel-wise deformable registration of high-resolution 3D images without the need for intermediate image warping or a multi-resolution scheme. This is achieved by representing the image domain as multiple comprehensive supervoxel layers and making use of the full marginal distribution of all probable displacement vectors after inferring regularity of the deformations using belief propagation. The optimisation acts on the coarse scale representation of supervoxels, which provides sufficient spatial context and is robust to noise in low contrast areas. Minimum spanning trees, which connect neighbouring supervoxels, are employed to model pair-wise deformation dependencies. The optimal displacement for each voxel is calculated by considering the probabilities for all displacements over all overlapping supervoxel graphs and subsequently seeking the mode of this distribution. We demonstrate the applicability of this concept for two challenging applications: first, for intra-patient motion estimation in lung CT scans; and second, for atlas-based segmentation propagation of MRI brain scans. For lung registration, the voxel-wise mode of displacements is found using the mean-shift algorithm, which enables us to determine continuous valued sub-voxel motion vectors. Finding the mode of brain segmentation labels is performed using a voxel-wise majority voting weighted by the displacement uncertainty estimates. Our experimental results show significant improvements in registration accuracy when using the additional information provided by the registration uncertainty estimates. The multi-layer approach enables fusion of multiple complementary proposals, extending the popular fusion approaches from multi-image registration to probabilistic one-to-one image registration.</subfield></datafield><datafield tag="540" ind1=" " ind2=" "><subfield code="a">Nutzungsrecht: Copyright © 2015 Elsevier B.V. All rights reserved.</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Simpson, Ivor J A</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Papież, BartŁomiej W</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Brady, Sir Michael</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Schnabel, Julia A</subfield><subfield code="4">oth</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Medical image analysis</subfield><subfield code="d">Amsterdam [u.a.] : Elsevier, 1996</subfield><subfield code="g">27(2016), Seite 57-71</subfield><subfield code="w">(DE-627)223260010</subfield><subfield code="w">(DE-600)1356436-5</subfield><subfield code="w">(DE-576)080160034</subfield><subfield code="x">1361-8415</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:27</subfield><subfield code="g">year:2016</subfield><subfield code="g">pages:57-71</subfield></datafield><datafield tag="856" ind1="4" ind2="1"><subfield code="u">http://dx.doi.org/10.1016/j.media.2015.09.005</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="u">http://www.ncbi.nlm.nih.gov/pubmed/26545720</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_OLC</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-MAT</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-PHA</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-DE-84</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4219</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">27</subfield><subfield code="j">2016</subfield><subfield code="h">57-71</subfield></datafield></record></collection>
|
| author |
Heinrich, Mattias P |
| spellingShingle |
Heinrich, Mattias P ddc 004 Deformable image registration by combining uncertainty estimates from supervoxel belief propagation |
| authorStr |
Heinrich, Mattias P |
| ppnlink_with_tag_str_mv |
@@773@@(DE-627)223260010 |
| format |
Article |
| dewey-ones |
004 - Data processing & computer science |
| delete_txt_mv |
keep |
| author_role |
aut |
| collection |
OLC |
| remote_str |
false |
| illustrated |
Not Illustrated |
| issn |
1361-8415 |
| topic_title |
004 ZDB Deformable image registration by combining uncertainty estimates from supervoxel belief propagation |
| topic |
ddc 004 |
| topic_unstemmed |
ddc 004 |
| topic_browse |
ddc 004 |
| format_facet |
Aufsätze Gedruckte Aufsätze |
| format_main_str_mv |
Text Zeitschrift/Artikel |
| carriertype_str_mv |
nc |
| author2_variant |
i j a s ija ijas b w p bw bwp s m b sm smb j a s ja jas |
| hierarchy_parent_title |
Medical image analysis |
| hierarchy_parent_id |
223260010 |
| dewey-tens |
000 - Computer science, knowledge & systems |
| hierarchy_top_title |
Medical image analysis |
| isfreeaccess_txt |
false |
| familylinks_str_mv |
(DE-627)223260010 (DE-600)1356436-5 (DE-576)080160034 |
| title |
Deformable image registration by combining uncertainty estimates from supervoxel belief propagation |
| ctrlnum |
(DE-627)OLC1971383376 (DE-599)GBVOLC1971383376 (PRQ)c1276-e965d3c9343a1a36eb7b0a97790883bed947e7483d45704b3814e73d300965370 (KEY)0392983320160000027000000057deformableimageregistrationbycombininguncertaintye |
| title_full |
Deformable image registration by combining uncertainty estimates from supervoxel belief propagation |
| author_sort |
Heinrich, Mattias P |
| journal |
Medical image analysis |
| journalStr |
Medical image analysis |
| lang_code |
eng |
| isOA_bool |
false |
| dewey-hundreds |
000 - Computer science, information & general works |
| recordtype |
marc |
| publishDateSort |
2016 |
| contenttype_str_mv |
txt |
| container_start_page |
57 |
| author_browse |
Heinrich, Mattias P |
| container_volume |
27 |
| class |
004 ZDB |
| format_se |
Aufsätze |
| author-letter |
Heinrich, Mattias P |
| doi_str_mv |
10.1016/j.media.2015.09.005 |
| dewey-full |
004 |
| title_sort |
deformable image registration by combining uncertainty estimates from supervoxel belief propagation |
| title_auth |
Deformable image registration by combining uncertainty estimates from supervoxel belief propagation |
| abstract |
Discrete optimisation strategies have a number of advantages over their continuous counterparts for deformable registration of medical images. For example: it is not necessary to compute derivatives of the similarity term; dense sampling of the search space reduces the risk of becoming trapped in local optima; and (in principle) an optimum can be found without resorting to iterative coarse-to-fine warping strategies. However, the large complexity of high-dimensional medical data renders a direct voxel-wise estimation of deformation vectors impractical. For this reason, previous work on medical image registration using graphical models has largely relied on using a parameterised deformation model and on the use of iterative coarse-to-fine optimisation schemes. In this paper, we propose an approach that enables accurate voxel-wise deformable registration of high-resolution 3D images without the need for intermediate image warping or a multi-resolution scheme. This is achieved by representing the image domain as multiple comprehensive supervoxel layers and making use of the full marginal distribution of all probable displacement vectors after inferring regularity of the deformations using belief propagation. The optimisation acts on the coarse scale representation of supervoxels, which provides sufficient spatial context and is robust to noise in low contrast areas. Minimum spanning trees, which connect neighbouring supervoxels, are employed to model pair-wise deformation dependencies. The optimal displacement for each voxel is calculated by considering the probabilities for all displacements over all overlapping supervoxel graphs and subsequently seeking the mode of this distribution. We demonstrate the applicability of this concept for two challenging applications: first, for intra-patient motion estimation in lung CT scans; and second, for atlas-based segmentation propagation of MRI brain scans. For lung registration, the voxel-wise mode of displacements is found using the mean-shift algorithm, which enables us to determine continuous valued sub-voxel motion vectors. Finding the mode of brain segmentation labels is performed using a voxel-wise majority voting weighted by the displacement uncertainty estimates. Our experimental results show significant improvements in registration accuracy when using the additional information provided by the registration uncertainty estimates. The multi-layer approach enables fusion of multiple complementary proposals, extending the popular fusion approaches from multi-image registration to probabilistic one-to-one image registration. |
| abstractGer |
Discrete optimisation strategies have a number of advantages over their continuous counterparts for deformable registration of medical images. For example: it is not necessary to compute derivatives of the similarity term; dense sampling of the search space reduces the risk of becoming trapped in local optima; and (in principle) an optimum can be found without resorting to iterative coarse-to-fine warping strategies. However, the large complexity of high-dimensional medical data renders a direct voxel-wise estimation of deformation vectors impractical. For this reason, previous work on medical image registration using graphical models has largely relied on using a parameterised deformation model and on the use of iterative coarse-to-fine optimisation schemes. In this paper, we propose an approach that enables accurate voxel-wise deformable registration of high-resolution 3D images without the need for intermediate image warping or a multi-resolution scheme. This is achieved by representing the image domain as multiple comprehensive supervoxel layers and making use of the full marginal distribution of all probable displacement vectors after inferring regularity of the deformations using belief propagation. The optimisation acts on the coarse scale representation of supervoxels, which provides sufficient spatial context and is robust to noise in low contrast areas. Minimum spanning trees, which connect neighbouring supervoxels, are employed to model pair-wise deformation dependencies. The optimal displacement for each voxel is calculated by considering the probabilities for all displacements over all overlapping supervoxel graphs and subsequently seeking the mode of this distribution. We demonstrate the applicability of this concept for two challenging applications: first, for intra-patient motion estimation in lung CT scans; and second, for atlas-based segmentation propagation of MRI brain scans. For lung registration, the voxel-wise mode of displacements is found using the mean-shift algorithm, which enables us to determine continuous valued sub-voxel motion vectors. Finding the mode of brain segmentation labels is performed using a voxel-wise majority voting weighted by the displacement uncertainty estimates. Our experimental results show significant improvements in registration accuracy when using the additional information provided by the registration uncertainty estimates. The multi-layer approach enables fusion of multiple complementary proposals, extending the popular fusion approaches from multi-image registration to probabilistic one-to-one image registration. |
| abstract_unstemmed |
Discrete optimisation strategies have a number of advantages over their continuous counterparts for deformable registration of medical images. For example: it is not necessary to compute derivatives of the similarity term; dense sampling of the search space reduces the risk of becoming trapped in local optima; and (in principle) an optimum can be found without resorting to iterative coarse-to-fine warping strategies. However, the large complexity of high-dimensional medical data renders a direct voxel-wise estimation of deformation vectors impractical. For this reason, previous work on medical image registration using graphical models has largely relied on using a parameterised deformation model and on the use of iterative coarse-to-fine optimisation schemes. In this paper, we propose an approach that enables accurate voxel-wise deformable registration of high-resolution 3D images without the need for intermediate image warping or a multi-resolution scheme. This is achieved by representing the image domain as multiple comprehensive supervoxel layers and making use of the full marginal distribution of all probable displacement vectors after inferring regularity of the deformations using belief propagation. The optimisation acts on the coarse scale representation of supervoxels, which provides sufficient spatial context and is robust to noise in low contrast areas. Minimum spanning trees, which connect neighbouring supervoxels, are employed to model pair-wise deformation dependencies. The optimal displacement for each voxel is calculated by considering the probabilities for all displacements over all overlapping supervoxel graphs and subsequently seeking the mode of this distribution. We demonstrate the applicability of this concept for two challenging applications: first, for intra-patient motion estimation in lung CT scans; and second, for atlas-based segmentation propagation of MRI brain scans. For lung registration, the voxel-wise mode of displacements is found using the mean-shift algorithm, which enables us to determine continuous valued sub-voxel motion vectors. Finding the mode of brain segmentation labels is performed using a voxel-wise majority voting weighted by the displacement uncertainty estimates. Our experimental results show significant improvements in registration accuracy when using the additional information provided by the registration uncertainty estimates. The multi-layer approach enables fusion of multiple complementary proposals, extending the popular fusion approaches from multi-image registration to probabilistic one-to-one image registration. |
| collection_details |
GBV_USEFLAG_A SYSFLAG_A GBV_OLC SSG-OLC-MAT SSG-OLC-PHA SSG-OLC-DE-84 GBV_ILN_4219 |
| title_short |
Deformable image registration by combining uncertainty estimates from supervoxel belief propagation |
| url |
http://dx.doi.org/10.1016/j.media.2015.09.005 http://www.ncbi.nlm.nih.gov/pubmed/26545720 |
| remote_bool |
false |
| author2 |
Simpson, Ivor J A Papież, BartŁomiej W Brady, Sir Michael Schnabel, Julia A |
| author2Str |
Simpson, Ivor J A Papież, BartŁomiej W Brady, Sir Michael Schnabel, Julia A |
| ppnlink |
223260010 |
| mediatype_str_mv |
n |
| isOA_txt |
false |
| hochschulschrift_bool |
false |
| author2_role |
oth oth oth oth |
| doi_str |
10.1016/j.media.2015.09.005 |
| up_date |
2024-07-03T19:17:10.418Z |
| _version_ |
1803586613195833344 |
| fullrecord_marcxml |
<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000caa a2200265 4500</leader><controlfield tag="001">OLC1971383376</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230714181640.0</controlfield><controlfield tag="007">tu</controlfield><controlfield tag="008">160212s2016 xx ||||| 00| ||eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.1016/j.media.2015.09.005</subfield><subfield code="2">doi</subfield></datafield><datafield tag="028" ind1="5" ind2="2"><subfield code="a">PQ20160430</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)OLC1971383376</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)GBVOLC1971383376</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(PRQ)c1276-e965d3c9343a1a36eb7b0a97790883bed947e7483d45704b3814e73d300965370</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(KEY)0392983320160000027000000057deformableimageregistrationbycombininguncertaintye</subfield></datafield><datafield tag="040" ind1=" " ind2=" "><subfield code="a">DE-627</subfield><subfield code="b">ger</subfield><subfield code="c">DE-627</subfield><subfield code="e">rakwb</subfield></datafield><datafield tag="041" ind1=" " ind2=" "><subfield code="a">eng</subfield></datafield><datafield tag="082" ind1="0" ind2="4"><subfield code="a">004</subfield><subfield code="q">ZDB</subfield></datafield><datafield tag="100" ind1="1" ind2=" "><subfield code="a">Heinrich, Mattias P</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Deformable image registration by combining uncertainty estimates from supervoxel belief propagation</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2016</subfield></datafield><datafield tag="336" ind1=" " ind2=" "><subfield code="a">Text</subfield><subfield code="b">txt</subfield><subfield code="2">rdacontent</subfield></datafield><datafield tag="337" ind1=" " ind2=" "><subfield code="a">ohne Hilfsmittel zu benutzen</subfield><subfield code="b">n</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Band</subfield><subfield code="b">nc</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">Discrete optimisation strategies have a number of advantages over their continuous counterparts for deformable registration of medical images. For example: it is not necessary to compute derivatives of the similarity term; dense sampling of the search space reduces the risk of becoming trapped in local optima; and (in principle) an optimum can be found without resorting to iterative coarse-to-fine warping strategies. However, the large complexity of high-dimensional medical data renders a direct voxel-wise estimation of deformation vectors impractical. For this reason, previous work on medical image registration using graphical models has largely relied on using a parameterised deformation model and on the use of iterative coarse-to-fine optimisation schemes. In this paper, we propose an approach that enables accurate voxel-wise deformable registration of high-resolution 3D images without the need for intermediate image warping or a multi-resolution scheme. This is achieved by representing the image domain as multiple comprehensive supervoxel layers and making use of the full marginal distribution of all probable displacement vectors after inferring regularity of the deformations using belief propagation. The optimisation acts on the coarse scale representation of supervoxels, which provides sufficient spatial context and is robust to noise in low contrast areas. Minimum spanning trees, which connect neighbouring supervoxels, are employed to model pair-wise deformation dependencies. The optimal displacement for each voxel is calculated by considering the probabilities for all displacements over all overlapping supervoxel graphs and subsequently seeking the mode of this distribution. We demonstrate the applicability of this concept for two challenging applications: first, for intra-patient motion estimation in lung CT scans; and second, for atlas-based segmentation propagation of MRI brain scans. For lung registration, the voxel-wise mode of displacements is found using the mean-shift algorithm, which enables us to determine continuous valued sub-voxel motion vectors. Finding the mode of brain segmentation labels is performed using a voxel-wise majority voting weighted by the displacement uncertainty estimates. Our experimental results show significant improvements in registration accuracy when using the additional information provided by the registration uncertainty estimates. The multi-layer approach enables fusion of multiple complementary proposals, extending the popular fusion approaches from multi-image registration to probabilistic one-to-one image registration.</subfield></datafield><datafield tag="540" ind1=" " ind2=" "><subfield code="a">Nutzungsrecht: Copyright © 2015 Elsevier B.V. All rights reserved.</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Simpson, Ivor J A</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Papież, BartŁomiej W</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Brady, Sir Michael</subfield><subfield code="4">oth</subfield></datafield><datafield tag="700" ind1="1" ind2=" "><subfield code="a">Schnabel, Julia A</subfield><subfield code="4">oth</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">Enthalten in</subfield><subfield code="t">Medical image analysis</subfield><subfield code="d">Amsterdam [u.a.] : Elsevier, 1996</subfield><subfield code="g">27(2016), Seite 57-71</subfield><subfield code="w">(DE-627)223260010</subfield><subfield code="w">(DE-600)1356436-5</subfield><subfield code="w">(DE-576)080160034</subfield><subfield code="x">1361-8415</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:27</subfield><subfield code="g">year:2016</subfield><subfield code="g">pages:57-71</subfield></datafield><datafield tag="856" ind1="4" ind2="1"><subfield code="u">http://dx.doi.org/10.1016/j.media.2015.09.005</subfield><subfield code="3">Volltext</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="u">http://www.ncbi.nlm.nih.gov/pubmed/26545720</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_USEFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SYSFLAG_A</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_OLC</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-MAT</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-PHA</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">SSG-OLC-DE-84</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4219</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">27</subfield><subfield code="j">2016</subfield><subfield code="h">57-71</subfield></datafield></record></collection>
|
| score |
7.4012938 |