Automatic landmark detection and mapping for 2D/3D registration with BoneNet

The 3D musculoskeletal motion of animals is of interest for various biological studies and can be derived from X-ray fluoroscopy acquisitions by means of image matching or manual landmark annotation and mapping. While the image matching method requires a robust similarity measure (intensity-based) o...
Ausführliche Beschreibung

Gespeichert in:

Autor*in:	Van Nguyen [verfasserIn] Luis F. Alves Pereira [verfasserIn] Zhihua Liang [verfasserIn] Falk Mielke [verfasserIn] Jeroen Van Houtte [verfasserIn] Jan Sijbers [verfasserIn] Jan De Beenhouwer [verfasserIn]

Format:	E-Artikel
Sprache:	Englisch

Erschienen:	2022

Schlagwörter:	2D/3D registration landmark-based registration pose estimation automatic landmark detection deep learning

Übergeordnetes Werk:	In: Frontiers in Veterinary Science - Frontiers Media S.A., 2015, 9(2022)
Übergeordnetes Werk:	volume:9 ; year:2022

Links:	Link aufrufen Link aufrufen Link aufrufen Journal toc

DOI / URN:	10.3389/fvets.2022.923449

Katalog-ID:	DOAJ079061524

Internformat


LEADER	01000naa a22002652 4500
001	DOAJ079061524
003	DE-627
005	20230307012809.0
007	cr uuu---uuuuu
008	230307s2022 xx \|\|\|\|\|o 00\| \|\|eng c
024	7		\|a 10.3389/fvets.2022.923449 \|2 doi
035			\|a (DE-627)DOAJ079061524
035			\|a (DE-599)DOAJ716f03ceb1f14e1bb41676bc3f3f6b61
040			\|a DE-627 \|b ger \|c DE-627 \|e rakwb
041			\|a eng
050		0	\|a SF600-1100
100	0		\|a Van Nguyen \|e verfasserin \|4 aut
245	1	0	\|a Automatic landmark detection and mapping for 2D/3D registration with BoneNet
264		1	\|c 2022
336			\|a Text \|b txt \|2 rdacontent
337			\|a Computermedien \|b c \|2 rdamedia
338			\|a Online-Ressource \|b cr \|2 rdacarrier
520			\|a The 3D musculoskeletal motion of animals is of interest for various biological studies and can be derived from X-ray fluoroscopy acquisitions by means of image matching or manual landmark annotation and mapping. While the image matching method requires a robust similarity measure (intensity-based) or an expensive computation (tomographic reconstruction-based), the manual annotation method depends on the experience of operators. In this paper, we tackle these challenges by a strategic approach that consists of two building blocks: an automated 3D landmark extraction technique and a deep neural network for 2D landmarks detection. For 3D landmark extraction, we propose a technique based on the shortest voxel coordinate variance to extract the 3D landmarks from the 3D tomographic reconstruction of an object. For 2D landmark detection, we propose a customized ResNet18-based neural network, BoneNet, to automatically detect geometrical landmarks on X-ray fluoroscopy images. With a deeper network architecture in comparison to the original ResNet18 model, BoneNet can extract and propagate feature vectors for accurate 2D landmark inference. The 3D poses of the animal are then reconstructed by aligning the extracted 2D landmarks from X-ray radiographs and the corresponding 3D landmarks in a 3D object reference model. Our proposed method is validated on X-ray images, simulated from a real piglet hindlimb 3D computed tomography scan and does not require manual annotation of landmark positions. The simulation results show that BoneNet is able to accurately detect the 2D landmarks in simulated, noisy 2D X-ray images, resulting in promising rigid and articulated parameter estimations.
650		4	\|a 2D/3D registration
650		4	\|a landmark-based registration
650		4	\|a pose estimation
650		4	\|a automatic landmark detection
650		4	\|a deep learning
653		0	\|a Veterinary medicine
700	0		\|a Luis F. Alves Pereira \|e verfasserin \|4 aut
700	0		\|a Luis F. Alves Pereira \|e verfasserin \|4 aut
700	0		\|a Zhihua Liang \|e verfasserin \|4 aut
700	0		\|a Falk Mielke \|e verfasserin \|4 aut
700	0		\|a Falk Mielke \|e verfasserin \|4 aut
700	0		\|a Jeroen Van Houtte \|e verfasserin \|4 aut
700	0		\|a Jan Sijbers \|e verfasserin \|4 aut
700	0		\|a Jan De Beenhouwer \|e verfasserin \|4 aut
773	0	8	\|i In \|t Frontiers in Veterinary Science \|d Frontiers Media S.A., 2015 \|g 9(2022) \|w (DE-627)835029417 \|w (DE-600)2834243-4 \|x 22971769 \|7 nnns
773	1	8	\|g volume:9 \|g year:2022
856	4	0	\|u https://doi.org/10.3389/fvets.2022.923449 \|z kostenfrei
856	4	0	\|u https://doaj.org/article/716f03ceb1f14e1bb41676bc3f3f6b61 \|z kostenfrei
856	4	0	\|u https://www.frontiersin.org/articles/10.3389/fvets.2022.923449/full \|z kostenfrei
856	4	2	\|u https://doaj.org/toc/2297-1769 \|y Journal toc \|z kostenfrei
912			\|a GBV_USEFLAG_A
912			\|a SYSFLAG_A
912			\|a GBV_DOAJ
912			\|a GBV_ILN_11
912			\|a GBV_ILN_20
912			\|a GBV_ILN_22
912			\|a GBV_ILN_24
912			\|a GBV_ILN_31
912			\|a GBV_ILN_39
912			\|a GBV_ILN_40
912			\|a GBV_ILN_60
912			\|a GBV_ILN_62
912			\|a GBV_ILN_63
912			\|a GBV_ILN_65
912			\|a GBV_ILN_69
912			\|a GBV_ILN_70
912			\|a GBV_ILN_73
912			\|a GBV_ILN_95
912			\|a GBV_ILN_105
912			\|a GBV_ILN_110
912			\|a GBV_ILN_151
912			\|a GBV_ILN_161
912			\|a GBV_ILN_213
912			\|a GBV_ILN_230
912			\|a GBV_ILN_285
912			\|a GBV_ILN_293
912			\|a GBV_ILN_602
912			\|a GBV_ILN_2003
912			\|a GBV_ILN_2014
912			\|a GBV_ILN_4012
912			\|a GBV_ILN_4037
912			\|a GBV_ILN_4112
912			\|a GBV_ILN_4125
912			\|a GBV_ILN_4126
912			\|a GBV_ILN_4249
912			\|a GBV_ILN_4305
912			\|a GBV_ILN_4306
912			\|a GBV_ILN_4307
912			\|a GBV_ILN_4313
912			\|a GBV_ILN_4322
912			\|a GBV_ILN_4323
912			\|a GBV_ILN_4324
912			\|a GBV_ILN_4325
912			\|a GBV_ILN_4338
912			\|a GBV_ILN_4367
912			\|a GBV_ILN_4700
951			\|a AR
952			\|d 9 \|j 2022

Indexfelder

author_variant	v n vn l f a p lfap l f a p lfap z l zl f m fm f m fm j v h jvh j s js j d b jdb
matchkey_str	article:22971769:2022----::uoailnmrdtcinnmpigo23rgs
hierarchy_sort_str	2022
callnumber-subject-code	SF
publishDate	2022
allfields	10.3389/fvets.2022.923449 doi (DE-627)DOAJ079061524 (DE-599)DOAJ716f03ceb1f14e1bb41676bc3f3f6b61 DE-627 ger DE-627 rakwb eng SF600-1100 Van Nguyen verfasserin aut Automatic landmark detection and mapping for 2D/3D registration with BoneNet 2022 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier The 3D musculoskeletal motion of animals is of interest for various biological studies and can be derived from X-ray fluoroscopy acquisitions by means of image matching or manual landmark annotation and mapping. While the image matching method requires a robust similarity measure (intensity-based) or an expensive computation (tomographic reconstruction-based), the manual annotation method depends on the experience of operators. In this paper, we tackle these challenges by a strategic approach that consists of two building blocks: an automated 3D landmark extraction technique and a deep neural network for 2D landmarks detection. For 3D landmark extraction, we propose a technique based on the shortest voxel coordinate variance to extract the 3D landmarks from the 3D tomographic reconstruction of an object. For 2D landmark detection, we propose a customized ResNet18-based neural network, BoneNet, to automatically detect geometrical landmarks on X-ray fluoroscopy images. With a deeper network architecture in comparison to the original ResNet18 model, BoneNet can extract and propagate feature vectors for accurate 2D landmark inference. The 3D poses of the animal are then reconstructed by aligning the extracted 2D landmarks from X-ray radiographs and the corresponding 3D landmarks in a 3D object reference model. Our proposed method is validated on X-ray images, simulated from a real piglet hindlimb 3D computed tomography scan and does not require manual annotation of landmark positions. The simulation results show that BoneNet is able to accurately detect the 2D landmarks in simulated, noisy 2D X-ray images, resulting in promising rigid and articulated parameter estimations. 2D/3D registration landmark-based registration pose estimation automatic landmark detection deep learning Veterinary medicine Luis F. Alves Pereira verfasserin aut Luis F. Alves Pereira verfasserin aut Zhihua Liang verfasserin aut Falk Mielke verfasserin aut Falk Mielke verfasserin aut Jeroen Van Houtte verfasserin aut Jan Sijbers verfasserin aut Jan De Beenhouwer verfasserin aut In Frontiers in Veterinary Science Frontiers Media S.A., 2015 9(2022) (DE-627)835029417 (DE-600)2834243-4 22971769 nnns volume:9 year:2022 https://doi.org/10.3389/fvets.2022.923449 kostenfrei https://doaj.org/article/716f03ceb1f14e1bb41676bc3f3f6b61 kostenfrei https://www.frontiersin.org/articles/10.3389/fvets.2022.923449/full kostenfrei https://doaj.org/toc/2297-1769 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_24 GBV_ILN_31 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_602 GBV_ILN_2003 GBV_ILN_2014 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 9 2022
spelling	10.3389/fvets.2022.923449 doi (DE-627)DOAJ079061524 (DE-599)DOAJ716f03ceb1f14e1bb41676bc3f3f6b61 DE-627 ger DE-627 rakwb eng SF600-1100 Van Nguyen verfasserin aut Automatic landmark detection and mapping for 2D/3D registration with BoneNet 2022 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier The 3D musculoskeletal motion of animals is of interest for various biological studies and can be derived from X-ray fluoroscopy acquisitions by means of image matching or manual landmark annotation and mapping. While the image matching method requires a robust similarity measure (intensity-based) or an expensive computation (tomographic reconstruction-based), the manual annotation method depends on the experience of operators. In this paper, we tackle these challenges by a strategic approach that consists of two building blocks: an automated 3D landmark extraction technique and a deep neural network for 2D landmarks detection. For 3D landmark extraction, we propose a technique based on the shortest voxel coordinate variance to extract the 3D landmarks from the 3D tomographic reconstruction of an object. For 2D landmark detection, we propose a customized ResNet18-based neural network, BoneNet, to automatically detect geometrical landmarks on X-ray fluoroscopy images. With a deeper network architecture in comparison to the original ResNet18 model, BoneNet can extract and propagate feature vectors for accurate 2D landmark inference. The 3D poses of the animal are then reconstructed by aligning the extracted 2D landmarks from X-ray radiographs and the corresponding 3D landmarks in a 3D object reference model. Our proposed method is validated on X-ray images, simulated from a real piglet hindlimb 3D computed tomography scan and does not require manual annotation of landmark positions. The simulation results show that BoneNet is able to accurately detect the 2D landmarks in simulated, noisy 2D X-ray images, resulting in promising rigid and articulated parameter estimations. 2D/3D registration landmark-based registration pose estimation automatic landmark detection deep learning Veterinary medicine Luis F. Alves Pereira verfasserin aut Luis F. Alves Pereira verfasserin aut Zhihua Liang verfasserin aut Falk Mielke verfasserin aut Falk Mielke verfasserin aut Jeroen Van Houtte verfasserin aut Jan Sijbers verfasserin aut Jan De Beenhouwer verfasserin aut In Frontiers in Veterinary Science Frontiers Media S.A., 2015 9(2022) (DE-627)835029417 (DE-600)2834243-4 22971769 nnns volume:9 year:2022 https://doi.org/10.3389/fvets.2022.923449 kostenfrei https://doaj.org/article/716f03ceb1f14e1bb41676bc3f3f6b61 kostenfrei https://www.frontiersin.org/articles/10.3389/fvets.2022.923449/full kostenfrei https://doaj.org/toc/2297-1769 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_24 GBV_ILN_31 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_602 GBV_ILN_2003 GBV_ILN_2014 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 9 2022
allfields_unstemmed	10.3389/fvets.2022.923449 doi (DE-627)DOAJ079061524 (DE-599)DOAJ716f03ceb1f14e1bb41676bc3f3f6b61 DE-627 ger DE-627 rakwb eng SF600-1100 Van Nguyen verfasserin aut Automatic landmark detection and mapping for 2D/3D registration with BoneNet 2022 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier The 3D musculoskeletal motion of animals is of interest for various biological studies and can be derived from X-ray fluoroscopy acquisitions by means of image matching or manual landmark annotation and mapping. While the image matching method requires a robust similarity measure (intensity-based) or an expensive computation (tomographic reconstruction-based), the manual annotation method depends on the experience of operators. In this paper, we tackle these challenges by a strategic approach that consists of two building blocks: an automated 3D landmark extraction technique and a deep neural network for 2D landmarks detection. For 3D landmark extraction, we propose a technique based on the shortest voxel coordinate variance to extract the 3D landmarks from the 3D tomographic reconstruction of an object. For 2D landmark detection, we propose a customized ResNet18-based neural network, BoneNet, to automatically detect geometrical landmarks on X-ray fluoroscopy images. With a deeper network architecture in comparison to the original ResNet18 model, BoneNet can extract and propagate feature vectors for accurate 2D landmark inference. The 3D poses of the animal are then reconstructed by aligning the extracted 2D landmarks from X-ray radiographs and the corresponding 3D landmarks in a 3D object reference model. Our proposed method is validated on X-ray images, simulated from a real piglet hindlimb 3D computed tomography scan and does not require manual annotation of landmark positions. The simulation results show that BoneNet is able to accurately detect the 2D landmarks in simulated, noisy 2D X-ray images, resulting in promising rigid and articulated parameter estimations. 2D/3D registration landmark-based registration pose estimation automatic landmark detection deep learning Veterinary medicine Luis F. Alves Pereira verfasserin aut Luis F. Alves Pereira verfasserin aut Zhihua Liang verfasserin aut Falk Mielke verfasserin aut Falk Mielke verfasserin aut Jeroen Van Houtte verfasserin aut Jan Sijbers verfasserin aut Jan De Beenhouwer verfasserin aut In Frontiers in Veterinary Science Frontiers Media S.A., 2015 9(2022) (DE-627)835029417 (DE-600)2834243-4 22971769 nnns volume:9 year:2022 https://doi.org/10.3389/fvets.2022.923449 kostenfrei https://doaj.org/article/716f03ceb1f14e1bb41676bc3f3f6b61 kostenfrei https://www.frontiersin.org/articles/10.3389/fvets.2022.923449/full kostenfrei https://doaj.org/toc/2297-1769 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_24 GBV_ILN_31 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_602 GBV_ILN_2003 GBV_ILN_2014 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 9 2022
allfieldsGer	10.3389/fvets.2022.923449 doi (DE-627)DOAJ079061524 (DE-599)DOAJ716f03ceb1f14e1bb41676bc3f3f6b61 DE-627 ger DE-627 rakwb eng SF600-1100 Van Nguyen verfasserin aut Automatic landmark detection and mapping for 2D/3D registration with BoneNet 2022 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier The 3D musculoskeletal motion of animals is of interest for various biological studies and can be derived from X-ray fluoroscopy acquisitions by means of image matching or manual landmark annotation and mapping. While the image matching method requires a robust similarity measure (intensity-based) or an expensive computation (tomographic reconstruction-based), the manual annotation method depends on the experience of operators. In this paper, we tackle these challenges by a strategic approach that consists of two building blocks: an automated 3D landmark extraction technique and a deep neural network for 2D landmarks detection. For 3D landmark extraction, we propose a technique based on the shortest voxel coordinate variance to extract the 3D landmarks from the 3D tomographic reconstruction of an object. For 2D landmark detection, we propose a customized ResNet18-based neural network, BoneNet, to automatically detect geometrical landmarks on X-ray fluoroscopy images. With a deeper network architecture in comparison to the original ResNet18 model, BoneNet can extract and propagate feature vectors for accurate 2D landmark inference. The 3D poses of the animal are then reconstructed by aligning the extracted 2D landmarks from X-ray radiographs and the corresponding 3D landmarks in a 3D object reference model. Our proposed method is validated on X-ray images, simulated from a real piglet hindlimb 3D computed tomography scan and does not require manual annotation of landmark positions. The simulation results show that BoneNet is able to accurately detect the 2D landmarks in simulated, noisy 2D X-ray images, resulting in promising rigid and articulated parameter estimations. 2D/3D registration landmark-based registration pose estimation automatic landmark detection deep learning Veterinary medicine Luis F. Alves Pereira verfasserin aut Luis F. Alves Pereira verfasserin aut Zhihua Liang verfasserin aut Falk Mielke verfasserin aut Falk Mielke verfasserin aut Jeroen Van Houtte verfasserin aut Jan Sijbers verfasserin aut Jan De Beenhouwer verfasserin aut In Frontiers in Veterinary Science Frontiers Media S.A., 2015 9(2022) (DE-627)835029417 (DE-600)2834243-4 22971769 nnns volume:9 year:2022 https://doi.org/10.3389/fvets.2022.923449 kostenfrei https://doaj.org/article/716f03ceb1f14e1bb41676bc3f3f6b61 kostenfrei https://www.frontiersin.org/articles/10.3389/fvets.2022.923449/full kostenfrei https://doaj.org/toc/2297-1769 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_24 GBV_ILN_31 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_602 GBV_ILN_2003 GBV_ILN_2014 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 9 2022
allfieldsSound	10.3389/fvets.2022.923449 doi (DE-627)DOAJ079061524 (DE-599)DOAJ716f03ceb1f14e1bb41676bc3f3f6b61 DE-627 ger DE-627 rakwb eng SF600-1100 Van Nguyen verfasserin aut Automatic landmark detection and mapping for 2D/3D registration with BoneNet 2022 Text txt rdacontent Computermedien c rdamedia Online-Ressource cr rdacarrier The 3D musculoskeletal motion of animals is of interest for various biological studies and can be derived from X-ray fluoroscopy acquisitions by means of image matching or manual landmark annotation and mapping. While the image matching method requires a robust similarity measure (intensity-based) or an expensive computation (tomographic reconstruction-based), the manual annotation method depends on the experience of operators. In this paper, we tackle these challenges by a strategic approach that consists of two building blocks: an automated 3D landmark extraction technique and a deep neural network for 2D landmarks detection. For 3D landmark extraction, we propose a technique based on the shortest voxel coordinate variance to extract the 3D landmarks from the 3D tomographic reconstruction of an object. For 2D landmark detection, we propose a customized ResNet18-based neural network, BoneNet, to automatically detect geometrical landmarks on X-ray fluoroscopy images. With a deeper network architecture in comparison to the original ResNet18 model, BoneNet can extract and propagate feature vectors for accurate 2D landmark inference. The 3D poses of the animal are then reconstructed by aligning the extracted 2D landmarks from X-ray radiographs and the corresponding 3D landmarks in a 3D object reference model. Our proposed method is validated on X-ray images, simulated from a real piglet hindlimb 3D computed tomography scan and does not require manual annotation of landmark positions. The simulation results show that BoneNet is able to accurately detect the 2D landmarks in simulated, noisy 2D X-ray images, resulting in promising rigid and articulated parameter estimations. 2D/3D registration landmark-based registration pose estimation automatic landmark detection deep learning Veterinary medicine Luis F. Alves Pereira verfasserin aut Luis F. Alves Pereira verfasserin aut Zhihua Liang verfasserin aut Falk Mielke verfasserin aut Falk Mielke verfasserin aut Jeroen Van Houtte verfasserin aut Jan Sijbers verfasserin aut Jan De Beenhouwer verfasserin aut In Frontiers in Veterinary Science Frontiers Media S.A., 2015 9(2022) (DE-627)835029417 (DE-600)2834243-4 22971769 nnns volume:9 year:2022 https://doi.org/10.3389/fvets.2022.923449 kostenfrei https://doaj.org/article/716f03ceb1f14e1bb41676bc3f3f6b61 kostenfrei https://www.frontiersin.org/articles/10.3389/fvets.2022.923449/full kostenfrei https://doaj.org/toc/2297-1769 Journal toc kostenfrei GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_24 GBV_ILN_31 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_602 GBV_ILN_2003 GBV_ILN_2014 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700 AR 9 2022
language	English
source	In Frontiers in Veterinary Science 9(2022) volume:9 year:2022
sourceStr	In Frontiers in Veterinary Science 9(2022) volume:9 year:2022
format_phy_str_mv	Article
institution	findex.gbv.de
topic_facet	2D/3D registration landmark-based registration pose estimation automatic landmark detection deep learning Veterinary medicine
isfreeaccess_bool	true
container_title	Frontiers in Veterinary Science
authorswithroles_txt_mv	Van Nguyen @@aut@@ Luis F. Alves Pereira @@aut@@ Zhihua Liang @@aut@@ Falk Mielke @@aut@@ Jeroen Van Houtte @@aut@@ Jan Sijbers @@aut@@ Jan De Beenhouwer @@aut@@
publishDateDaySort_date	2022-01-01T00:00:00Z
hierarchy_top_id	835029417
id	DOAJ079061524
language_de	englisch
fullrecord	<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000naa a22002652 4500</leader><controlfield tag="001">DOAJ079061524</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230307012809.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">230307s2022 xx \|\|\|\|\|o 00\| \|\|eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.3389/fvets.2022.923449</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)DOAJ079061524</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)DOAJ716f03ceb1f14e1bb41676bc3f3f6b61</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="050" ind1=" " ind2="0"><subfield code="a">SF600-1100</subfield></datafield><datafield tag="100" ind1="0" ind2=" "><subfield code="a">Van Nguyen</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Automatic landmark detection and mapping for 2D/3D registration with BoneNet</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2022</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">Computermedien</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Online-Ressource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">The 3D musculoskeletal motion of animals is of interest for various biological studies and can be derived from X-ray fluoroscopy acquisitions by means of image matching or manual landmark annotation and mapping. While the image matching method requires a robust similarity measure (intensity-based) or an expensive computation (tomographic reconstruction-based), the manual annotation method depends on the experience of operators. In this paper, we tackle these challenges by a strategic approach that consists of two building blocks: an automated 3D landmark extraction technique and a deep neural network for 2D landmarks detection. For 3D landmark extraction, we propose a technique based on the shortest voxel coordinate variance to extract the 3D landmarks from the 3D tomographic reconstruction of an object. For 2D landmark detection, we propose a customized ResNet18-based neural network, BoneNet, to automatically detect geometrical landmarks on X-ray fluoroscopy images. With a deeper network architecture in comparison to the original ResNet18 model, BoneNet can extract and propagate feature vectors for accurate 2D landmark inference. The 3D poses of the animal are then reconstructed by aligning the extracted 2D landmarks from X-ray radiographs and the corresponding 3D landmarks in a 3D object reference model. Our proposed method is validated on X-ray images, simulated from a real piglet hindlimb 3D computed tomography scan and does not require manual annotation of landmark positions. The simulation results show that BoneNet is able to accurately detect the 2D landmarks in simulated, noisy 2D X-ray images, resulting in promising rigid and articulated parameter estimations.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">2D/3D registration</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">landmark-based registration</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">pose estimation</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">automatic landmark detection</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">deep learning</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Veterinary medicine</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Luis F. Alves Pereira</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Luis F. Alves Pereira</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Zhihua Liang</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Falk Mielke</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Falk Mielke</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Jeroen Van Houtte</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Jan Sijbers</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Jan De Beenhouwer</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">In</subfield><subfield code="t">Frontiers in Veterinary Science</subfield><subfield code="d">Frontiers Media S.A., 2015</subfield><subfield code="g">9(2022)</subfield><subfield code="w">(DE-627)835029417</subfield><subfield code="w">(DE-600)2834243-4</subfield><subfield code="x">22971769</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:9</subfield><subfield code="g">year:2022</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.3389/fvets.2022.923449</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doaj.org/article/716f03ceb1f14e1bb41676bc3f3f6b61</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://www.frontiersin.org/articles/10.3389/fvets.2022.923449/full</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="u">https://doaj.org/toc/2297-1769</subfield><subfield code="y">Journal toc</subfield><subfield code="z">kostenfrei</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_DOAJ</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_11</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_20</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_22</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_24</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_31</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_39</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_40</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_60</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_62</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_63</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_65</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_69</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_70</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_73</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_95</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_105</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_110</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_151</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_161</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_213</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_230</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_285</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_293</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_602</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2003</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2014</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4012</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4037</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4112</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4125</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4126</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4249</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4305</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4306</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4307</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4313</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4322</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4323</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4324</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4325</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4338</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4367</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4700</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">9</subfield><subfield code="j">2022</subfield></datafield></record></collection>
callnumber-first	S - Agriculture
author	Van Nguyen
spellingShingle	Van Nguyen misc SF600-1100 misc 2D/3D registration misc landmark-based registration misc pose estimation misc automatic landmark detection misc deep learning misc Veterinary medicine Automatic landmark detection and mapping for 2D/3D registration with BoneNet
authorStr	Van Nguyen
ppnlink_with_tag_str_mv	@@773@@(DE-627)835029417
format	electronic Article
delete_txt_mv	keep
author_role	aut aut aut aut aut aut aut aut aut
collection	DOAJ
remote_str	true
callnumber-label	SF600-1100
illustrated	Not Illustrated
issn	22971769
topic_title	SF600-1100 Automatic landmark detection and mapping for 2D/3D registration with BoneNet 2D/3D registration landmark-based registration pose estimation automatic landmark detection deep learning
topic	misc SF600-1100 misc 2D/3D registration misc landmark-based registration misc pose estimation misc automatic landmark detection misc deep learning misc Veterinary medicine
topic_unstemmed	misc SF600-1100 misc 2D/3D registration misc landmark-based registration misc pose estimation misc automatic landmark detection misc deep learning misc Veterinary medicine
topic_browse	misc SF600-1100 misc 2D/3D registration misc landmark-based registration misc pose estimation misc automatic landmark detection misc deep learning misc Veterinary medicine
format_facet	Elektronische Aufsätze Aufsätze Elektronische Ressource
format_main_str_mv	Text Zeitschrift/Artikel
carriertype_str_mv	cr
hierarchy_parent_title	Frontiers in Veterinary Science
hierarchy_parent_id	835029417
hierarchy_top_title	Frontiers in Veterinary Science
isfreeaccess_txt	true
familylinks_str_mv	(DE-627)835029417 (DE-600)2834243-4
title	Automatic landmark detection and mapping for 2D/3D registration with BoneNet
ctrlnum	(DE-627)DOAJ079061524 (DE-599)DOAJ716f03ceb1f14e1bb41676bc3f3f6b61
title_full	Automatic landmark detection and mapping for 2D/3D registration with BoneNet
author_sort	Van Nguyen
journal	Frontiers in Veterinary Science
journalStr	Frontiers in Veterinary Science
callnumber-first-code	S
lang_code	eng
isOA_bool	true
recordtype	marc
publishDateSort	2022
contenttype_str_mv	txt
author_browse	Van Nguyen Luis F. Alves Pereira Zhihua Liang Falk Mielke Jeroen Van Houtte Jan Sijbers Jan De Beenhouwer
container_volume	9
class	SF600-1100
format_se	Elektronische Aufsätze
author-letter	Van Nguyen
doi_str_mv	10.3389/fvets.2022.923449
author2-role	verfasserin
title_sort	automatic landmark detection and mapping for 2d/3d registration with bonenet
callnumber	SF600-1100
title_auth	Automatic landmark detection and mapping for 2D/3D registration with BoneNet
abstract	The 3D musculoskeletal motion of animals is of interest for various biological studies and can be derived from X-ray fluoroscopy acquisitions by means of image matching or manual landmark annotation and mapping. While the image matching method requires a robust similarity measure (intensity-based) or an expensive computation (tomographic reconstruction-based), the manual annotation method depends on the experience of operators. In this paper, we tackle these challenges by a strategic approach that consists of two building blocks: an automated 3D landmark extraction technique and a deep neural network for 2D landmarks detection. For 3D landmark extraction, we propose a technique based on the shortest voxel coordinate variance to extract the 3D landmarks from the 3D tomographic reconstruction of an object. For 2D landmark detection, we propose a customized ResNet18-based neural network, BoneNet, to automatically detect geometrical landmarks on X-ray fluoroscopy images. With a deeper network architecture in comparison to the original ResNet18 model, BoneNet can extract and propagate feature vectors for accurate 2D landmark inference. The 3D poses of the animal are then reconstructed by aligning the extracted 2D landmarks from X-ray radiographs and the corresponding 3D landmarks in a 3D object reference model. Our proposed method is validated on X-ray images, simulated from a real piglet hindlimb 3D computed tomography scan and does not require manual annotation of landmark positions. The simulation results show that BoneNet is able to accurately detect the 2D landmarks in simulated, noisy 2D X-ray images, resulting in promising rigid and articulated parameter estimations.
abstractGer	The 3D musculoskeletal motion of animals is of interest for various biological studies and can be derived from X-ray fluoroscopy acquisitions by means of image matching or manual landmark annotation and mapping. While the image matching method requires a robust similarity measure (intensity-based) or an expensive computation (tomographic reconstruction-based), the manual annotation method depends on the experience of operators. In this paper, we tackle these challenges by a strategic approach that consists of two building blocks: an automated 3D landmark extraction technique and a deep neural network for 2D landmarks detection. For 3D landmark extraction, we propose a technique based on the shortest voxel coordinate variance to extract the 3D landmarks from the 3D tomographic reconstruction of an object. For 2D landmark detection, we propose a customized ResNet18-based neural network, BoneNet, to automatically detect geometrical landmarks on X-ray fluoroscopy images. With a deeper network architecture in comparison to the original ResNet18 model, BoneNet can extract and propagate feature vectors for accurate 2D landmark inference. The 3D poses of the animal are then reconstructed by aligning the extracted 2D landmarks from X-ray radiographs and the corresponding 3D landmarks in a 3D object reference model. Our proposed method is validated on X-ray images, simulated from a real piglet hindlimb 3D computed tomography scan and does not require manual annotation of landmark positions. The simulation results show that BoneNet is able to accurately detect the 2D landmarks in simulated, noisy 2D X-ray images, resulting in promising rigid and articulated parameter estimations.
abstract_unstemmed	The 3D musculoskeletal motion of animals is of interest for various biological studies and can be derived from X-ray fluoroscopy acquisitions by means of image matching or manual landmark annotation and mapping. While the image matching method requires a robust similarity measure (intensity-based) or an expensive computation (tomographic reconstruction-based), the manual annotation method depends on the experience of operators. In this paper, we tackle these challenges by a strategic approach that consists of two building blocks: an automated 3D landmark extraction technique and a deep neural network for 2D landmarks detection. For 3D landmark extraction, we propose a technique based on the shortest voxel coordinate variance to extract the 3D landmarks from the 3D tomographic reconstruction of an object. For 2D landmark detection, we propose a customized ResNet18-based neural network, BoneNet, to automatically detect geometrical landmarks on X-ray fluoroscopy images. With a deeper network architecture in comparison to the original ResNet18 model, BoneNet can extract and propagate feature vectors for accurate 2D landmark inference. The 3D poses of the animal are then reconstructed by aligning the extracted 2D landmarks from X-ray radiographs and the corresponding 3D landmarks in a 3D object reference model. Our proposed method is validated on X-ray images, simulated from a real piglet hindlimb 3D computed tomography scan and does not require manual annotation of landmark positions. The simulation results show that BoneNet is able to accurately detect the 2D landmarks in simulated, noisy 2D X-ray images, resulting in promising rigid and articulated parameter estimations.
collection_details	GBV_USEFLAG_A SYSFLAG_A GBV_DOAJ GBV_ILN_11 GBV_ILN_20 GBV_ILN_22 GBV_ILN_24 GBV_ILN_31 GBV_ILN_39 GBV_ILN_40 GBV_ILN_60 GBV_ILN_62 GBV_ILN_63 GBV_ILN_65 GBV_ILN_69 GBV_ILN_70 GBV_ILN_73 GBV_ILN_95 GBV_ILN_105 GBV_ILN_110 GBV_ILN_151 GBV_ILN_161 GBV_ILN_213 GBV_ILN_230 GBV_ILN_285 GBV_ILN_293 GBV_ILN_602 GBV_ILN_2003 GBV_ILN_2014 GBV_ILN_4012 GBV_ILN_4037 GBV_ILN_4112 GBV_ILN_4125 GBV_ILN_4126 GBV_ILN_4249 GBV_ILN_4305 GBV_ILN_4306 GBV_ILN_4307 GBV_ILN_4313 GBV_ILN_4322 GBV_ILN_4323 GBV_ILN_4324 GBV_ILN_4325 GBV_ILN_4338 GBV_ILN_4367 GBV_ILN_4700
title_short	Automatic landmark detection and mapping for 2D/3D registration with BoneNet
url	https://doi.org/10.3389/fvets.2022.923449 https://doaj.org/article/716f03ceb1f14e1bb41676bc3f3f6b61 https://www.frontiersin.org/articles/10.3389/fvets.2022.923449/full https://doaj.org/toc/2297-1769
remote_bool	true
author2	Luis F. Alves Pereira Zhihua Liang Falk Mielke Jeroen Van Houtte Jan Sijbers Jan De Beenhouwer
author2Str	Luis F. Alves Pereira Zhihua Liang Falk Mielke Jeroen Van Houtte Jan Sijbers Jan De Beenhouwer
ppnlink	835029417
callnumber-subject	SF - Animal Culture
mediatype_str_mv	c
isOA_txt	true
hochschulschrift_bool	false
doi_str	10.3389/fvets.2022.923449
callnumber-a	SF600-1100
up_date	2024-07-03T21:30:06.220Z
_version_	1803594976434585600
fullrecord_marcxml	<?xml version="1.0" encoding="UTF-8"?><collection xmlns="http://www.loc.gov/MARC21/slim"><record><leader>01000naa a22002652 4500</leader><controlfield tag="001">DOAJ079061524</controlfield><controlfield tag="003">DE-627</controlfield><controlfield tag="005">20230307012809.0</controlfield><controlfield tag="007">cr uuu---uuuuu</controlfield><controlfield tag="008">230307s2022 xx \|\|\|\|\|o 00\| \|\|eng c</controlfield><datafield tag="024" ind1="7" ind2=" "><subfield code="a">10.3389/fvets.2022.923449</subfield><subfield code="2">doi</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-627)DOAJ079061524</subfield></datafield><datafield tag="035" ind1=" " ind2=" "><subfield code="a">(DE-599)DOAJ716f03ceb1f14e1bb41676bc3f3f6b61</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="050" ind1=" " ind2="0"><subfield code="a">SF600-1100</subfield></datafield><datafield tag="100" ind1="0" ind2=" "><subfield code="a">Van Nguyen</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="245" ind1="1" ind2="0"><subfield code="a">Automatic landmark detection and mapping for 2D/3D registration with BoneNet</subfield></datafield><datafield tag="264" ind1=" " ind2="1"><subfield code="c">2022</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">Computermedien</subfield><subfield code="b">c</subfield><subfield code="2">rdamedia</subfield></datafield><datafield tag="338" ind1=" " ind2=" "><subfield code="a">Online-Ressource</subfield><subfield code="b">cr</subfield><subfield code="2">rdacarrier</subfield></datafield><datafield tag="520" ind1=" " ind2=" "><subfield code="a">The 3D musculoskeletal motion of animals is of interest for various biological studies and can be derived from X-ray fluoroscopy acquisitions by means of image matching or manual landmark annotation and mapping. While the image matching method requires a robust similarity measure (intensity-based) or an expensive computation (tomographic reconstruction-based), the manual annotation method depends on the experience of operators. In this paper, we tackle these challenges by a strategic approach that consists of two building blocks: an automated 3D landmark extraction technique and a deep neural network for 2D landmarks detection. For 3D landmark extraction, we propose a technique based on the shortest voxel coordinate variance to extract the 3D landmarks from the 3D tomographic reconstruction of an object. For 2D landmark detection, we propose a customized ResNet18-based neural network, BoneNet, to automatically detect geometrical landmarks on X-ray fluoroscopy images. With a deeper network architecture in comparison to the original ResNet18 model, BoneNet can extract and propagate feature vectors for accurate 2D landmark inference. The 3D poses of the animal are then reconstructed by aligning the extracted 2D landmarks from X-ray radiographs and the corresponding 3D landmarks in a 3D object reference model. Our proposed method is validated on X-ray images, simulated from a real piglet hindlimb 3D computed tomography scan and does not require manual annotation of landmark positions. The simulation results show that BoneNet is able to accurately detect the 2D landmarks in simulated, noisy 2D X-ray images, resulting in promising rigid and articulated parameter estimations.</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">2D/3D registration</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">landmark-based registration</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">pose estimation</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">automatic landmark detection</subfield></datafield><datafield tag="650" ind1=" " ind2="4"><subfield code="a">deep learning</subfield></datafield><datafield tag="653" ind1=" " ind2="0"><subfield code="a">Veterinary medicine</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Luis F. Alves Pereira</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Luis F. Alves Pereira</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Zhihua Liang</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Falk Mielke</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Falk Mielke</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Jeroen Van Houtte</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Jan Sijbers</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="700" ind1="0" ind2=" "><subfield code="a">Jan De Beenhouwer</subfield><subfield code="e">verfasserin</subfield><subfield code="4">aut</subfield></datafield><datafield tag="773" ind1="0" ind2="8"><subfield code="i">In</subfield><subfield code="t">Frontiers in Veterinary Science</subfield><subfield code="d">Frontiers Media S.A., 2015</subfield><subfield code="g">9(2022)</subfield><subfield code="w">(DE-627)835029417</subfield><subfield code="w">(DE-600)2834243-4</subfield><subfield code="x">22971769</subfield><subfield code="7">nnns</subfield></datafield><datafield tag="773" ind1="1" ind2="8"><subfield code="g">volume:9</subfield><subfield code="g">year:2022</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doi.org/10.3389/fvets.2022.923449</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://doaj.org/article/716f03ceb1f14e1bb41676bc3f3f6b61</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="0"><subfield code="u">https://www.frontiersin.org/articles/10.3389/fvets.2022.923449/full</subfield><subfield code="z">kostenfrei</subfield></datafield><datafield tag="856" ind1="4" ind2="2"><subfield code="u">https://doaj.org/toc/2297-1769</subfield><subfield code="y">Journal toc</subfield><subfield code="z">kostenfrei</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_DOAJ</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_11</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_20</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_22</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_24</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_31</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_39</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_40</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_60</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_62</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_63</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_65</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_69</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_70</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_73</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_95</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_105</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_110</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_151</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_161</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_213</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_230</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_285</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_293</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_602</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2003</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_2014</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4012</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4037</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4112</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4125</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4126</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4249</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4305</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4306</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4307</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4313</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4322</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4323</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4324</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4325</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4338</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4367</subfield></datafield><datafield tag="912" ind1=" " ind2=" "><subfield code="a">GBV_ILN_4700</subfield></datafield><datafield tag="951" ind1=" " ind2=" "><subfield code="a">AR</subfield></datafield><datafield tag="952" ind1=" " ind2=" "><subfield code="d">9</subfield><subfield code="j">2022</subfield></datafield></record></collection>
score	7.4015245

Nicht das Richtige dabei?

Schreiben Sie uns!

Automatic landmark detection and mapping for 2D/3D registration with BoneNet

Nicht das Richtige dabei?

Zugang & Verfügbarkeit

Vorhandene Bände

Nicht das Richtige dabei?