Automated selection of trabecular bone regions in knee radiographs

Osteoarthritic (OA) changes in knee joints can be assessed by analyzing the structure of trabecular bone (TB) in the tibia. This analysis is performed on TB regions selected manually by a human operator on x-ray images. Manual selection is time-consuming, tedious, and expensive. Even if a radiologis...

Full description

Saved in:
Bibliographic Details
Published inMedical physics (Lancaster) Vol. 35; no. 5; pp. 1870 - 1883
Main Authors Podsiadlo, P., Wolski, M., Stachowiak, G. W.
Format Journal Article
LanguageEnglish
Published United States American Association of Physicists in Medicine 01.05.2008
Subjects
Online AccessGet full text
ISSN0094-2405
2473-4209
DOI10.1118/1.2905025

Cover

Abstract Osteoarthritic (OA) changes in knee joints can be assessed by analyzing the structure of trabecular bone (TB) in the tibia. This analysis is performed on TB regions selected manually by a human operator on x-ray images. Manual selection is time-consuming, tedious, and expensive. Even if a radiologist expert or highly trained person is available to select regions, high inter- and intraobserver variabilities are still possible. A fully automated image segmentation method was, therefore, developed to select the bone regions for numerical analyses of changes in bone structures. The newly developed method consists of image preprocessing, delineation of cortical bone plates (active shape model), and location of regions of interest (ROI). The method was trained on an independent set of 40 x-ray images. Automatically selected regions were compared to the “gold standard” that contains ROIs selected manually by a radiologist expert on 132 x-ray images. All images were acquired from subjects locked in a standardized standing position using a radiography rig. The size of each ROI is 12.8 × 12.8   mm . The automated method results showed a good agreement with the gold standard [similarity index ( SI ) = 0.83 (medial) and 0.81 (lateral) and the offset = [ − 1.78 ,   1.27 ] × [ − 0.65 , 0.26 ]   mm (medial) and [ − 2.15 ,   1.59 ] × [ − 0.58 ,   0.52 ]   mm (lateral)]. Bland and Altman plots were constructed for fractal signatures, and changes of fractal dimensions (FD) to region offsets calculated between the gold standard and automatically selected regions were calculated. The plots showed a random scatter and the 95% confidence intervals were ( − 0.006 , 0.008) and ( − 0.001 , 0.011). The changes of FDs to region offsets were less than 0.035. Previous studies showed that differences in FDs between non-OA and OA bone regions were greater than 0.05. ROIs were also selected by a second radiologist and then evaluated. Results indicated that the newly developed method could replace a human operator and produces bone regions with an accuracy that is sufficient for fractal analyses of bone texture.
AbstractList Osteoarthritic (OA) changes in knee joints can be assessed by analyzing the structure of trabecular bone (TB) in the tibia. This analysis is performed on TB regions selected manually by a human operator on x‐ray images. Manual selection is time‐consuming, tedious, and expensive. Even if a radiologist expert or highly trained person is available to select regions, high inter‐ and intraobserver variabilities are still possible. A fully automated image segmentation method was, therefore, developed to select the bone regions for numerical analyses of changes in bone structures. The newly developed method consists of image preprocessing, delineation of cortical bone plates (active shape model), and location of regions of interest (ROI). The method was trained on an independent set of 40 x‐ray images. Automatically selected regions were compared to the “gold standard” that contains ROIs selected manually by a radiologist expert on 132 x‐ray images. All images were acquired from subjects locked in a standardized standing position using a radiography rig. The size of each ROI is . The automated method results showed a good agreement with the gold standard [similarity index (medial) and 0.81 (lateral) and the (medial) and (lateral)]. Bland and Altman plots were constructed for fractal signatures, and changes of fractal dimensions (FD) to region offsets calculated between the gold standard and automatically selected regions were calculated. The plots showed a random scatter and the 95% confidence intervals were ( , 0.008) and ( , 0.011). The changes of FDs to region offsets were less than 0.035. Previous studies showed that differences in FDs between non‐OA and OA bone regions were greater than 0.05. ROIs were also selected by a second radiologist and then evaluated. Results indicated that the newly developed method could replace a human operator and produces bone regions with an accuracy that is sufficient for fractal analyses of bone texture.
Osteoarthritic (OA) changes in knee joints can be assessed by analyzing the structure of trabecular bone (TB) in the tibia. This analysis is performed on TB regions selected manually by a human operator on x‐ray images. Manual selection is time‐consuming, tedious, and expensive. Even if a radiologist expert or highly trained person is available to select regions, high inter‐ and intraobserver variabilities are still possible. A fully automated image segmentation method was, therefore, developed to select the bone regions for numerical analyses of changes in bone structures. The newly developed method consists of image preprocessing, delineation of cortical bone plates (active shape model), and location of regions of interest (ROI). The method was trained on an independent set of 40 x‐ray images. Automatically selected regions were compared to the “gold standard” that contains ROIs selected manually by a radiologist expert on 132 x‐ray images. All images were acquired from subjects locked in a standardized standing position using a radiography rig. The size of each ROI is 12.8×12.8mm. The automated method results showed a good agreement with the gold standard [similarity index (SI)=0.83 (medial) and 0.81 (lateral) and the offset=[−1.78,1.27]×[−0.65,0.26]mm (medial) and [−2.15,1.59]×[−0.58,0.52]mm (lateral)]. Bland and Altman plots were constructed for fractal signatures, and changes of fractal dimensions (FD) to region offsets calculated between the gold standard and automatically selected regions were calculated. The plots showed a random scatter and the 95% confidence intervals were (−0.006, 0.008) and (−0.001, 0.011). The changes of FDs to region offsets were less than 0.035. Previous studies showed that differences in FDs between non‐OA and OA bone regions were greater than 0.05. ROIs were also selected by a second radiologist and then evaluated. Results indicated that the newly developed method could replace a human operator and produces bone regions with an accuracy that is sufficient for fractal analyses of bone texture.
Osteoarthritic (OA) changes in knee joints can be assessed by analyzing the structure of trabecular bone (TB) in the tibia. This analysis is performed on TB regions selected manually by a human operator on x-ray images. Manual selection is time-consuming, tedious, and expensive. Even if a radiologist expert or highly trained person is available to select regions, high inter- and intraobserver variabilities are still possible. A fully automated image segmentation method was, therefore, developed to select the bone regions for numerical analyses of changes in bone structures. The newly developed method consists of image preprocessing, delineation of cortical bone plates (active shape model), and location of regions of interest (ROI). The method was trained on an independent set of 40 x-ray images. Automatically selected regions were compared to the "gold standard" that contains ROIs selected manually by a radiologist expert on 132 x-ray images. All images were acquired from subjects locked in a standardized standing position using a radiography rig. The size of each ROI is 12.8 × 12.8   mm . The automated method results showed a good agreement with the gold standard [similarity index ( SI ) = 0.83 (medial) and 0.81 (lateral) and the offset = [ − 1.78 ,   1.27 ] × [ − 0.65 , 0.26 ]   mm (medial) and [ − 2.15 ,   1.59 ] × [ − 0.58 ,   0.52 ]   mm (lateral)]. Bland and Altman plots were constructed for fractal signatures, and changes of fractal dimensions (FD) to region offsets calculated between the gold standard and automatically selected regions were calculated. The plots showed a random scatter and the 95% confidence intervals were ( − 0.006 , 0.008) and ( − 0.001 , 0.011). The changes of FDs to region offsets were less than 0.035. Previous studies showed that differences in FDs between non-OA and OA bone regions were greater than 0.05. ROIs were also selected by a second radiologist and then evaluated. Results indicated that the newly developed method could replace a human operator and produces bone regions with an accuracy that is sufficient for fractal analyses of bone texture.
Osteoarthritic (OA) changes in knee joints can be assessed by analyzing the structure of trabecular bone (TB) in the tibia. This analysis is performed on TB regions selected manually by a human operator on x-ray images. Manual selection is time-consuming, tedious, and expensive. Even if a radiologist expert or highly trained person is available to select regions, high inter- and intraobserver variabilities are still possible. A fully automated image segmentation method was, therefore, developed to select the bone regions for numerical analyses of changes in bone structures. The newly developed method consists of image preprocessing, delineation of cortical bone plates (active shape model), and location of regions of interest (ROI). The method was trained on an independent set of 40 x-ray images. Automatically selected regions were compared to the "gold standard" that contains ROIs selected manually by a radiologist expert on 132 x-ray images. All images were acquired from subjects locked in a standardized standing position using a radiography rig. The size of each ROI is 12.8 x 12.8 mm. The automated method results showed a good agreement with the gold standard [similarity index (SI) = 0.83 (medial) and 0.81 (lateral) and the offset =[-1.78, 1.27]x[-0.65,0.26] mm (medial) and [-2.15, 1.59]x[-0.58, 0.52] mm (lateral)]. Bland and Altman plots were constructed for fractal signatures, and changes of fractal dimensions (FD) to region offsets calculated between the gold standard and automatically selected regions were calculated. The plots showed a random scatter and the 95% confidence intervals were (-0.006, 0.008) and (-0.001, 0.011). The changes of FDs to region offsets were less than 0.035. Previous studies showed that differences in FDs between non-OA and OA bone regions were greater than 0.05. ROIs were also selected by a second radiologist and then evaluated. Results indicated that the newly developed method could replace a human operator and produces bone regions with an accuracy that is sufficient for fractal analyses of bone texture.Osteoarthritic (OA) changes in knee joints can be assessed by analyzing the structure of trabecular bone (TB) in the tibia. This analysis is performed on TB regions selected manually by a human operator on x-ray images. Manual selection is time-consuming, tedious, and expensive. Even if a radiologist expert or highly trained person is available to select regions, high inter- and intraobserver variabilities are still possible. A fully automated image segmentation method was, therefore, developed to select the bone regions for numerical analyses of changes in bone structures. The newly developed method consists of image preprocessing, delineation of cortical bone plates (active shape model), and location of regions of interest (ROI). The method was trained on an independent set of 40 x-ray images. Automatically selected regions were compared to the "gold standard" that contains ROIs selected manually by a radiologist expert on 132 x-ray images. All images were acquired from subjects locked in a standardized standing position using a radiography rig. The size of each ROI is 12.8 x 12.8 mm. The automated method results showed a good agreement with the gold standard [similarity index (SI) = 0.83 (medial) and 0.81 (lateral) and the offset =[-1.78, 1.27]x[-0.65,0.26] mm (medial) and [-2.15, 1.59]x[-0.58, 0.52] mm (lateral)]. Bland and Altman plots were constructed for fractal signatures, and changes of fractal dimensions (FD) to region offsets calculated between the gold standard and automatically selected regions were calculated. The plots showed a random scatter and the 95% confidence intervals were (-0.006, 0.008) and (-0.001, 0.011). The changes of FDs to region offsets were less than 0.035. Previous studies showed that differences in FDs between non-OA and OA bone regions were greater than 0.05. ROIs were also selected by a second radiologist and then evaluated. Results indicated that the newly developed method could replace a human operator and produces bone regions with an accuracy that is sufficient for fractal analyses of bone texture.
Osteoarthritic (OA) changes in knee joints can be assessed by analyzing the structure of trabecular bone (TB) in the tibia. This analysis is performed on TB regions selected manually by a human operator on x-ray images. Manual selection is time-consuming, tedious, and expensive. Even if a radiologist expert or highly trained person is available to select regions, high inter- and intraobserver variabilities are still possible. A fully automated image segmentation method was, therefore, developed to select the bone regions for numerical analyses of changes in bone structures. The newly developed method consists of image preprocessing, delineation of cortical bone plates (active shape model), and location of regions of interest (ROI). The method was trained on an independent set of 40 x-ray images. Automatically selected regions were compared to the "gold standard" that contains ROIs selected manually by a radiologist expert on 132 x-ray images. All images were acquired from subjects locked in a standardized standing position using a radiography rig. The size of each ROI is 12.8 x 12.8 mm. The automated method results showed a good agreement with the gold standard [similarity index (SI) = 0.83 (medial) and 0.81 (lateral) and the offset =[-1.78, 1.27]x[-0.65,0.26] mm (medial) and [-2.15, 1.59]x[-0.58, 0.52] mm (lateral)]. Bland and Altman plots were constructed for fractal signatures, and changes of fractal dimensions (FD) to region offsets calculated between the gold standard and automatically selected regions were calculated. The plots showed a random scatter and the 95% confidence intervals were (-0.006, 0.008) and (-0.001, 0.011). The changes of FDs to region offsets were less than 0.035. Previous studies showed that differences in FDs between non-OA and OA bone regions were greater than 0.05. ROIs were also selected by a second radiologist and then evaluated. Results indicated that the newly developed method could replace a human operator and produces bone regions with an accuracy that is sufficient for fractal analyses of bone texture.
Osteoarthritic (OA) changes in knee joints can be assessed by analyzing the structure of trabecular bone (TB) in the tibia. This analysis is performed on TB regions selected manually by a human operator on x-ray images. Manual selection is time-consuming, tedious, and expensive. Even if a radiologist expert or highly trained person is available to select regions, high inter- and intraobserver variabilities are still possible. A fully automated image segmentation method was, therefore, developed to select the bone regions for numerical analyses of changes in bone structures. The newly developed method consists of image preprocessing, delineation of cortical bone plates (active shape model), and location of regions of interest (ROI). The method was trained on an independent set of 40 x-ray images. Automatically selected regions were compared to the ''gold standard'' that contains ROIs selected manually by a radiologist expert on 132 x-ray images. All images were acquired from subjects locked in a standardized standing position using a radiography rig. The size of each ROI is 12.8x12.8 mm. The automated method results showed a good agreement with the gold standard [similarity index (SI)=0.83 (medial) and 0.81 (lateral) and the offset=[-1.78, 1.27]x[-0.65,0.26] mm (medial) and [-2.15, 1.59]x[-0.58, 0.52] mm (lateral)]. Bland and Altman plots were constructed for fractal signatures, and changes of fractal dimensions (FD) to region offsets calculated between the gold standard and automatically selected regions were calculated. The plots showed a random scatter and the 95% confidence intervals were (-0.006, 0.008) and (-0.001, 0.011). The changes of FDs to region offsets were less than 0.035. Previous studies showed that differences in FDs between non-OA and OA bone regions were greater than 0.05. ROIs were also selected by a second radiologist and then evaluated. Results indicated that the newly developed method could replace a human operator and produces bone regions with an accuracy that is sufficient for fractal analyses of bone texture.
Author Podsiadlo, P.
Stachowiak, G. W.
Wolski, M.
Author_xml – sequence: 1
  givenname: P.
  surname: Podsiadlo
  fullname: Podsiadlo, P.
  email: pawel@mech.uwa.edu.au
  organization: Tribology Laboratory, School of Mechanical Engineering, The University of Western Australia, Crawley 6009, Western Australia
– sequence: 2
  givenname: M.
  surname: Wolski
  fullname: Wolski, M.
  organization: Tribology Laboratory, School of Mechanical Engineering, The University of Western Australia, Crawley 6009, Western Australia
– sequence: 3
  givenname: G. W.
  surname: Stachowiak
  fullname: Stachowiak, G. W.
  organization: Tribology Laboratory, School of Mechanical Engineering, The University of Western Australia, Crawley 6009, Western Australia
BackLink https://www.ncbi.nlm.nih.gov/pubmed/18561662$$D View this record in MEDLINE/PubMed
https://www.osti.gov/biblio/21120690$$D View this record in Osti.gov
BookMark eNp9kUFP3DAQhS1EBQvl0D9QRapUCaTA2LG98aEHQNAiUbWH9mw5zhjcZuPFTkD8e4yy0Aq6PVkjf2_mzZsdstmHHgl5R-GQUlof0UOmQAATG2TG-LwqOQO1SWYAipeMg9gmOyn9AgBZCdgi27QWkkrJZuTkeBzCwgzYFgk7tIMPfRFcMUTToB07E4smDysiXuWfVPi--N1jrk3rw1U0y-v0lrxxpku4t3p3yc_zsx-nX8rLb58vTo8vS5stiVKhQF43HOZt1QBK5YTiXMm2sc5RmosajGps1dYGXc2FoFbVjbAMeeucrHbJh6lvSIPXyfoB7bUNfZ9da0YpA6kgUx8nahnDzYhp0AufLHad6TGMSUvFWK3oPIPvV-DYLLDVy-gXJt7rp2wysD8BNoaUIro_COjH3DXVq9wze_SCzfbMY5g5SN_9U1FOijvf4f361vrr9xX_aeLTU-f1mueb6uebZv3BOv1tiH_NW7buf_DrTR4AEx7BQw
CODEN MPHYA6
CitedBy_id crossref_primary_10_1007_s00330_017_4826_8
crossref_primary_10_1002_jor_24593
crossref_primary_10_1002_jor_21396
crossref_primary_10_1016_j_bsbt_2016_11_004
crossref_primary_10_1016_j_joca_2013_10_017
crossref_primary_10_1016_j_joca_2009_04_010
crossref_primary_10_1016_j_joca_2020_03_006
crossref_primary_10_1155_2010_107036
crossref_primary_10_1243_09544119JEIM436
crossref_primary_10_1186_s13075_021_02594_9
crossref_primary_10_1016_j_joca_2016_10_005
crossref_primary_10_1118_1_3373522
crossref_primary_10_1016_j_triboint_2010_07_006
crossref_primary_10_2174_1874120701307010018
crossref_primary_10_1177_09544119251318434
crossref_primary_10_1002_art_33410
crossref_primary_10_1016_j_bbe_2021_03_002
crossref_primary_10_1016_j_joca_2016_05_003
crossref_primary_10_1007_s11548_011_0550_z
crossref_primary_10_1177_0954411912456650
Cites_doi 10.1146/annurev.bioeng.2.1.315
10.1016/S1361-8415(01)00051-2
10.1088/0031-9155/36/6/001
10.1109/34.254061
10.1006/cviu.1995.1004
10.1118/1.598331
10.1118/1.598897
10.1016/S0021-9290(02)00386-X
10.1118/1.1449875
10.1016/j.compmedimag.2005.12.001
10.1109/TMI.2006.872747
10.1016/0262-8856(94)90060-4
10.1109/34.142909
10.1109/42.363096
10.1034/j.1600-0455.2002.430119.x
10.1117/12.595640
10.1093/schbul/17.3.483
10.1016/j.joca.2006.07.012
10.1016/0262‐8856(94)90060‐4
10.1016/j.joca.2007.07.010
10.1136/ard.16.4.494
10.1016/S0140-6736(86)90837-8
10.1016/S1361‐8415(01)00051‐2
10.1136/ard.59.8.641
10.1117/12.975399
10.1016/S0021‐9290(02)00386‐X
10.1016/j.joca.2004.10.009
10.1016/S8756-3282(02)00982-1
10.1034/j.1600‐0455.2002.430119.x
10.1088/0031‐9155/36/6/001
10.1136/ard.51.8.938
ContentType Journal Article
Copyright American Association of Physicists in Medicine
2008 American Association of Physicists in Medicine
Copyright_xml – notice: American Association of Physicists in Medicine
– notice: 2008 American Association of Physicists in Medicine
DBID AAYXX
CITATION
CGR
CUY
CVF
ECM
EIF
NPM
7X8
OTOTI
DOI 10.1118/1.2905025
DatabaseName CrossRef
Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
MEDLINE - Academic
OSTI.GOV
DatabaseTitle CrossRef
MEDLINE
Medline Complete
MEDLINE with Full Text
PubMed
MEDLINE (Ovid)
MEDLINE - Academic
DatabaseTitleList CrossRef


MEDLINE - Academic

MEDLINE

Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: EIF
  name: MEDLINE
  url: https://proxy.k.utb.cz/login?url=https://www.webofscience.com/wos/medline/basic-search
  sourceTypes: Index Database
DeliveryMethod fulltext_linktorsrc
Discipline Medicine
Physics
EISSN 2473-4209
EndPage 1883
ExternalDocumentID 21120690
18561662
10_1118_1_2905025
MP5025
Genre article
Research Support, Non-U.S. Gov't
Journal Article
GroupedDBID ---
--Z
-DZ
.GJ
0R~
1OB
1OC
29M
2WC
33P
36B
3O-
4.4
476
53G
5GY
5RE
5VS
AAHHS
AANLZ
AAQQT
AASGY
AAXRX
AAZKR
ABCUV
ABEFU
ABFTF
ABJNI
ABLJU
ABQWH
ABTAH
ABXGK
ACAHQ
ACBEA
ACCFJ
ACCZN
ACGFO
ACGFS
ACGOF
ACPOU
ACSMX
ACXBN
ACXQS
ADBBV
ADBTR
ADKYN
ADOZA
ADXAS
ADZMN
AEEZP
AEGXH
AEIGN
AENEX
AEQDE
AEUYR
AFBPY
AFFPM
AHBTC
AIACR
AIAGR
AIURR
AIWBW
AJBDE
ALMA_UNASSIGNED_HOLDINGS
ALUQN
AMYDB
ASPBG
BFHJK
C45
CS3
DCZOG
DRFUL
DRMAN
DRSTM
DU5
EBD
EBS
EJD
EMB
EMOBN
F5P
G8K
HDBZQ
HGLYW
I-F
KBYEO
LATKE
LEEKS
LOXES
LUTES
LYRES
MEWTI
O9-
OVD
P2P
P2W
PALCI
PHY
RJQFR
RNS
ROL
SAMSI
SUPJJ
SV3
TEORI
TN5
TWZ
USG
WOHZO
WXSBR
XJT
ZGI
ZVN
ZXP
ZY4
ZZTAW
AAHQN
AAIPD
AAMNL
AAYCA
ABDPE
AFWVQ
AITYG
ALVPJ
AAMMB
AAYXX
ADMLS
AEFGJ
AEYWJ
AGHNM
AGXDD
AGYGG
AIDQK
AIDYY
AIQQE
CITATION
LH4
CGR
CUY
CVF
ECM
EIF
NPM
7X8
ABUFD
AAJUZ
AAPBV
ABCVL
ABPTK
ADDAD
AEUQT
OTOTI
ID FETCH-LOGICAL-c4735-9e5e48b407d3b0e69f594496dbcff1159480a9bc3d8aef84551c98b5c2e4dff63
ISSN 0094-2405
IngestDate Thu May 18 18:33:46 EDT 2023
Tue Oct 21 14:11:14 EDT 2025
Thu Apr 03 06:57:41 EDT 2025
Wed Oct 01 03:41:55 EDT 2025
Thu Apr 24 23:05:53 EDT 2025
Wed Jan 22 16:15:21 EST 2025
Fri Jun 21 00:19:57 EDT 2024
Sun Jul 14 10:05:19 EDT 2019
Fri Jun 21 00:29:03 EDT 2024
IsPeerReviewed true
IsScholarly true
Issue 5
Keywords knee radiography
trabecular bone
computer-aided diagnosis
osteoarthritis
Language English
License 0094-2405/2008/35(5)/1870/14/$23.00
http://onlinelibrary.wiley.com/termsAndConditions#vor
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c4735-9e5e48b407d3b0e69f594496dbcff1159480a9bc3d8aef84551c98b5c2e4dff63
Notes pawel@mech.uwa.edu.au
Electronic mail
ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
PMID 18561662
PQID 69228917
PQPubID 23479
PageCount 14
ParticipantIDs proquest_miscellaneous_69228917
osti_scitechconnect_21120690
scitation_primary_10_1118_1_2905025
crossref_citationtrail_10_1118_1_2905025
wiley_primary_10_1118_1_2905025_MP5025
crossref_primary_10_1118_1_2905025
pubmed_primary_18561662
scitation_primary_10_1118_1_2905025Automated_selection
ProviderPackageCode CITATION
AAYXX
PublicationCentury 2000
PublicationDate May 2008
PublicationDateYYYYMMDD 2008-05-01
PublicationDate_xml – month: 05
  year: 2008
  text: May 2008
PublicationDecade 2000
PublicationPlace United States
PublicationPlace_xml – name: United States
PublicationTitle Medical physics (Lancaster)
PublicationTitleAlternate Med Phys
PublicationYear 2008
Publisher American Association of Physicists in Medicine
Publisher_xml – name: American Association of Physicists in Medicine
References Podsiadlo, Dahl, Englund, Lohmander, Stachowiak (c3) 2008; 16
Bobinac, Spanjol, Zoricic, Maric (c15) 2003; 32
Podsiadlo, Stachowiak (c26) 2002; 29
Kauffman, Slump, Moens (c8) 2005; 5747
Armato, Giger, Ashizawa, MacMahon (c27) 1998; 25
Zijdenbos, Dawant, Margolin, Palmer (c23) 1994; 13
Duryea, Li, Peterfy, Gordon, Genant (c28) 2000; 27
Buckland-Wright, Lynch, Dave (c12) 2000; 59
Behiels, Maes, Vandermeulen, Suetens (c5) 2002; 6
Loog, van Ginneken (c7) 2006; 25
McKinley, Bay (c13) 2003; 36
McCrae, Shouls, Dieppe, Watt (c14) 1991; 51
Pizer, Austin, Perry, Safrit, Zimmerman (c16) 1986; 626
Pham, Hu, Prince (c4) 2000; 2
Podsiadlo, Stachowiak (c9) 2002; 43
Bartko (c22) 1991; 17
Messent, Ward, Tonkin, Buckland-Wright (c2) 2005; 13
Brunelli, Poggio (c17) 1993; 15
Cootes, Taylor, Cooper, Graham (c20) 1995; 61
Messent, Ward, Tonkin, Buckland-Wright (c10) 2006; 14
Kellgren, Lawrence (c11) 1957; 16
Bland, Altman (c24) 1986; 8476
Mallat, Zhong (c21) 1992; 14
Udupa, LeBlanc, Zhuge, Imielinska, Schmidt, Currie, Hirsch, Woodburn (c25) 2006; 30
Lynch, Hawkes, Buckland-Wright (c1) 1991; 36
Cootes, Hill, Taylor, Haslam (c18) 1994; 12
Buckland-Wright, J.; Lynch, J.; Dave, B. 2000; 59
Bland, J.; Altman, D. 1986; 8476
McCrae, F.; Shouls, J.; Dieppe, P.; Watt, I. 1991; 51
Cootes, T.; Hill, A.; Taylor, C.; Haslam, J. 1994; 12
Zijdenbos, A.; Dawant, B.; Margolin, R.; Palmer, A. 1994; 13
Lynch, J.; Hawkes, D.; Buckland-Wright, J. 1991; 36
Loog, M.; van Ginneken, B. 2006; 25
Brunelli, R.; Poggio, T. 1993; 15
Behiels, G.; Maes, F.; Vandermeulen, D.; Suetens, P. 2002; 6
Udupa, J.; LeBlanc, V.; Zhuge, Y.; Imielinska, C.; Schmidt, H.; Currie, L.; Hirsch, B.; Woodburn, J. 2006; 30
Pham, D.; Hu, C.; Prince, J. 2000; 2
Bartko, J. 1991; 17
Mallat, S.; Zhong, S. 1992; 14
Kauffman, J.; Slump, C.; Moens, H. 2005; 5747
Cootes, T.; Taylor, C.; Cooper, D.; Graham, J. 1995; 61
Messent, E.; Ward, R.; Tonkin, C.; Buckland-Wright, J. 2005; 13
McKinley, T.; Bay, B. 2003; 36
Duryea, J.; Li, J.; Peterfy, C.; Gordon, C.; Genant, H. 2000; 27
Podsiadlo, P.; Stachowiak, G. 2002; 43
Kellgren, J.; Lawrence, J. 1957; 16
Bobinac, D.; Spanjol, J.; Zoricic, S.; Maric, I. 2003; 32
Pizer, S.; Austin, J.; Perry, J.; Safrit, H.; Zimmerman, J. 1986; 626
Podsiadlo, P.; Dahl, L.; Englund, M.; Lohmander, L.; Stachowiak, G. 2008; 16
Messent, E.; Ward, R.; Tonkin, C.; Buckland-Wright, J. 2006; 14
Armato, S.; Giger, M.; Ashizawa, K.; MacMahon, H. 1998; 25
Podsiadlo, P.; Stachowiak, G. 2002; 29
2006; 30
1991; 17
1991; 36
2000; 27
2002; 6
2008; 16
2006; 14
1991; 51
2003; 36
2000; 2
2005
1992; 14
1957; 16
2003; 32
1998; 25
1993; 15
1986; 626
1995; 61
2002; 29
2000; 59
2006; 25
2002; 43
1986; 8476
1994; 12
1994; 13
2001; 3
2005; 5747
1994; 1
2005; 13
e_1_2_7_6_1
e_1_2_7_5_1
e_1_2_7_4_1
e_1_2_7_3_1
e_1_2_7_9_1
e_1_2_7_8_1
e_1_2_7_19_1
e_1_2_7_18_1
e_1_2_7_17_1
e_1_2_7_16_1
e_1_2_7_2_1
e_1_2_7_15_1
e_1_2_7_14_1
e_1_2_7_13_1
Seise M. (e_1_2_7_30_1) 2005
e_1_2_7_12_1
e_1_2_7_11_1
e_1_2_7_10_1
e_1_2_7_26_1
e_1_2_7_27_1
e_1_2_7_28_1
e_1_2_7_29_1
He P. (e_1_2_7_7_1) 2001
Cootes T. F. (e_1_2_7_20_1) 1994
e_1_2_7_25_1
e_1_2_7_24_1
e_1_2_7_23_1
e_1_2_7_22_1
e_1_2_7_21_1
References_xml – volume: 61
  start-page: 38
  issn: 1077-3142
  year: 1995
  ident: c20
  article-title: Active shape model—Their training and application
  publication-title: Comput. Vis. Image Underst.
– volume: 13
  start-page: 716
  issn: 0278-0062
  year: 1994
  ident: c23
  article-title: Morphometric analysis of white matter lesions in MR images: Method and validation
  publication-title: IEEE Trans. Med. Imaging
– volume: 32
  start-page: 284
  issn: 8756-3282
  year: 2003
  ident: c15
  article-title: Changes in articular cartilage and subchondral bone histomorphometry in osteoarthritic knee joints in humans
  publication-title: Bone
– volume: 51
  start-page: 938
  issn: 0003-4967
  year: 1991
  ident: c14
  article-title: Scintigraphic assessment of osteoarthritis of the knee joint
  publication-title: Ann. Rheum. Dis.
– volume: 16
  start-page: 323
  issn: 1063-4584
  year: 2008
  ident: c3
  article-title: Differences in trabecular bone texture between knees with and without radiographic osteoarthritis detected by fractal methods
  publication-title: Osteoarthritis Cartilage
– volume: 27
  start-page: 580
  issn: 0094-2405
  year: 2000
  ident: c28
  article-title: Trainable rule-based algorithm for the measurement of joint space width in digital radiographic images of the knee
  publication-title: Med. Phys.
– volume: 25
  start-page: 602
  issn: 0278-0062
  year: 2006
  ident: c7
  article-title: Segmentation of the posterior ribs in chest radiographs using iterated contextual pixel classification
  publication-title: IEEE Trans. Med. Imaging
– volume: 14
  start-page: 710
  issn: 0162-8828
  year: 1992
  ident: c21
  article-title: Characterization of signals from multiscale edges
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
– volume: 12
  start-page: 355
  issn: 0262-8856
  year: 1994
  ident: c18
  article-title: The use of active shape models for locating structures in medical images
  publication-title: Image Vis. Comput.
– volume: 17
  start-page: 483
  issn: 0586-7614
  year: 1991
  ident: c22
  article-title: Measurement and reliability: Statistical thinking considerations
  publication-title: Schizophr. Bull.
– volume: 15
  start-page: 1042
  issn: 0162-8828
  year: 1993
  ident: c17
  article-title: Face recognition: Features versus templates
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
– volume: 2
  start-page: 315
  issn: 1523-9829
  year: 2000
  ident: c4
  article-title: Current methods in medical image segmentation
  publication-title: Annu. Rev. Biomed. Eng.
– volume: 29
  start-page: 460
  issn: 0094-2405
  year: 2002
  ident: c26
  article-title: Analysis of trabecular bone texture by modified Hurst orientation transform method
  publication-title: Med. Phys.
– volume: 16
  start-page: 494
  issn: 0003-4967
  year: 1957
  ident: c11
  article-title: Radiological assessment of osteoarthritis
  publication-title: Ann. Rheum. Dis.
– volume: 14
  start-page: 1302
  issn: 1063-4584
  year: 2006
  ident: c10
  article-title: Differences in trabecular structure between knees with and without osteoarthritis quantified by macro and standard radiography, respectively
  publication-title: Osteoarthritis Cartilage
– volume: 36
  start-page: 709
  issn: 0031-9155
  year: 1991
  ident: c1
  article-title: Analysis of texture in macroradiographs of osteoarthritic knee using the fractal signature
  publication-title: Phys. Med. Biol.
– volume: 36
  start-page: 155
  issn: 0021-9290
  year: 2003
  ident: c13
  article-title: Trabecular bone strain changes associated with subchondral stiffening of the proximal tibia
  publication-title: J. Biomech.
– volume: 59
  start-page: 641
  issn: 0003-4967
  year: 2000
  ident: c12
  article-title: Early radiographic features in patients with anterior cruciate ligament rupture
  publication-title: Ann. Rheum. Dis.
– volume: 6
  start-page: 47
  issn: 1361-8415
  year: 2002
  ident: c5
  article-title: Evaluation of image features and search strategies for segmentation of bone structures in radiographs using active shape models
  publication-title: Med. Image Anal.
– volume: 30
  start-page: 75
  issn: 0895-6111
  year: 2006
  ident: c25
  article-title: A framework for evaluating image segmentation algorithms
  publication-title: Comput. Med. Imaging Graph.
– volume: 5747
  start-page: 1571
  issn: 0277-786X
  year: 2005
  ident: c8
  article-title: Segmentation of hand radiographs by using multi-level connected active appearance models
  publication-title: Proc. SPIE
– volume: 8476
  start-page: 307
  issn: 0140-6736
  year: 1986
  ident: c24
  article-title: Statistical methods for assessing agreement between two methods of clinical measurement
  publication-title: Lancet
– volume: 25
  start-page: 1507
  issn: 0094-2405
  year: 1998
  ident: c27
  article-title: Automated lung segmentation in digital lateral chest radiographs
  publication-title: Med. Phys.
– volume: 43
  start-page: 101
  issn: 0284-1851
  year: 2002
  ident: c9
  article-title: A rig for acquisition of standardized trabecular bone radiographs
  publication-title: Acta Radiol.
– volume: 13
  start-page: 39
  issn: 1063-4584
  year: 2005
  ident: c2
  article-title: Cancellous bone difference between knees with early, definite and advanced joint space loss: A comparative quantitative macroradiographic study
  publication-title: Osteoarthritis Cartilage
– volume: 626
  start-page: 242
  issn: 0277-786X
  year: 1986
  ident: c16
  article-title: Adaptive histogram equalization for automatic contrast enhancement of medical images
  publication-title: Proc. SPIE
– volume: 2
  start-page: 315-317
  year: 2000
  publication-title: Annu. Rev. Biomed. Eng.
  doi: 10.1146/annurev.bioeng.2.1.315
– volume: 6
  start-page: 47-62
  year: 2002
  publication-title: Med. Image Anal.
  doi: 10.1016/S1361-8415(01)00051-2
– volume: 8476
  start-page: 307-310
  year: 1986
  publication-title: Lancet
– volume: 14
  start-page: 1302-1305
  year: 2006
  publication-title: Osteoarthritis Cartilage
– volume: 626
  start-page: 242-250
  year: 1986
  publication-title: Proc. SPIE
– volume: 13
  start-page: 39-47
  year: 2005
  publication-title: Osteoarthritis Cartilage
– volume: 16
  start-page: 494-501
  year: 1957
  publication-title: Ann. Rheum. Dis.
– volume: 16
  start-page: 323-329
  year: 2008
  publication-title: Osteoarthritis Cartilage
– volume: 36
  start-page: 709-722
  year: 1991
  publication-title: Phys. Med. Biol.
  doi: 10.1088/0031-9155/36/6/001
– volume: 15
  start-page: 1042-1052
  year: 1993
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/34.254061
– volume: 61
  start-page: 38-59
  year: 1995
  publication-title: Comput. Vis. Image Underst.
  doi: 10.1006/cviu.1995.1004
– volume: 25
  start-page: 1507-1520
  year: 1998
  publication-title: Med. Phys.
  doi: 10.1118/1.598331
– volume: 27
  start-page: 580-591
  year: 2000
  publication-title: Med. Phys.
  doi: 10.1118/1.598897
– volume: 36
  start-page: 155-163
  year: 2003
  publication-title: J. Biomech.
  doi: 10.1016/S0021-9290(02)00386-X
– volume: 17
  start-page: 483-489
  year: 1991
  publication-title: Schizophr. Bull.
– volume: 29
  start-page: 460-74
  year: 2002
  publication-title: Med. Phys.
  doi: 10.1118/1.1449875
– volume: 30
  start-page: 75-87
  year: 2006
  publication-title: Comput. Med. Imaging Graph.
  doi: 10.1016/j.compmedimag.2005.12.001
– volume: 25
  start-page: 602-611
  year: 2006
  publication-title: IEEE Trans. Med. Imaging
  doi: 10.1109/TMI.2006.872747
– volume: 12
  start-page: 355-366
  year: 1994
  publication-title: Image Vis. Comput.
  doi: 10.1016/0262-8856(94)90060-4
– volume: 59
  start-page: 641-646
  year: 2000
  publication-title: Ann. Rheum. Dis.
– volume: 32
  start-page: 284-290
  year: 2003
  publication-title: Bone
– volume: 14
  start-page: 710-732
  year: 1992
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/34.142909
– volume: 51
  start-page: 938-42
  year: 1991
  publication-title: Ann. Rheum. Dis.
– volume: 13
  start-page: 716-724
  year: 1994
  publication-title: IEEE Trans. Med. Imaging
  doi: 10.1109/42.363096
– volume: 43
  start-page: 101-103
  year: 2002
  publication-title: Acta Radiol.
  doi: 10.1034/j.1600-0455.2002.430119.x
– volume: 5747
  start-page: 1571-1581
  year: 2005
  publication-title: Proc. SPIE
  doi: 10.1117/12.595640
– volume: 27
  start-page: 580
  year: 2000
  end-page: 591
  article-title: Trainable rule‐based algorithm for the measurement of joint space width in digital radiographic images of the knee
  publication-title: Med. Phys.
– volume: 29
  start-page: 460
  year: 2002
  end-page: 74
  article-title: Analysis of trabecular bone texture by modified Hurst orientation transform method
  publication-title: Med. Phys.
– volume: 61
  start-page: 38
  year: 1995
  end-page: 59
  article-title: Active shape model—Their training and application
  publication-title: Comput. Vis. Image Underst.
– volume: 43
  start-page: 101
  year: 2002
  end-page: 103
  article-title: A rig for acquisition of standardized trabecular bone radiographs
  publication-title: Acta Radiol.
– volume: 32
  start-page: 284
  year: 2003
  end-page: 290
  article-title: Changes in articular cartilage and subchondral bone histomorphometry in osteoarthritic knee joints in humans
  publication-title: Bone
– volume: 14
  start-page: 710
  year: 1992
  end-page: 732
  article-title: Characterization of signals from multiscale edges
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
– volume: 2
  start-page: 315
  year: 2000
  end-page: 317
  article-title: Current methods in medical image segmentation
  publication-title: Annu. Rev. Biomed. Eng.
– volume: 25
  start-page: 602
  year: 2006
  end-page: 611
  article-title: Segmentation of the posterior ribs in chest radiographs using iterated contextual pixel classification
  publication-title: IEEE Trans. Med. Imaging
– volume: 3
  start-page: 2712
  year: 2001
  end-page: 2715
  article-title: Segmentation of tibia bone in ultrasound images using active shape models
– volume: 14
  start-page: 1302
  year: 2006
  end-page: 1305
  article-title: Differences in trabecular structure between knees with and without osteoarthritis quantified by macro and standard radiography, respectively
  publication-title: Osteoarthritis Cartilage
– volume: 1
  start-page: 610
  year: 1994
  end-page: 612
  article-title: Multi‐resolution search with active shape models
– volume: 13
  start-page: 716
  year: 1994
  end-page: 724
  article-title: Morphometric analysis of white matter lesions in MR images: Method and validation
  publication-title: IEEE Trans. Med. Imaging
– volume: 36
  start-page: 155
  year: 2003
  end-page: 163
  article-title: Trabecular bone strain changes associated with subchondral stiffening of the proximal tibia
  publication-title: J. Biomech.
– volume: 6
  start-page: 47
  year: 2002
  end-page: 62
  article-title: Evaluation of image features and search strategies for segmentation of bone structures in radiographs using active shape models
  publication-title: Med. Image Anal.
– volume: 15
  start-page: 1042
  year: 1993
  end-page: 1052
  article-title: Face recognition: Features versus templates
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
– volume: 30
  start-page: 75
  year: 2006
  end-page: 87
  article-title: A framework for evaluating image segmentation algorithms
  publication-title: Comput. Med. Imaging Graph.
– volume: 16
  start-page: 323
  year: 2008
  end-page: 329
  article-title: Differences in trabecular bone texture between knees with and without radiographic osteoarthritis detected by fractal methods
  publication-title: Osteoarthritis Cartilage
– volume: 5747
  start-page: 1571
  year: 2005
  end-page: 1581
  article-title: Segmentation of hand radiographs by using multi‐level connected active appearance models
  publication-title: Proc. SPIE
– volume: 25
  start-page: 1507
  year: 1998
  end-page: 1520
  article-title: Automated lung segmentation in digital lateral chest radiographs
  publication-title: Med. Phys.
– volume: 16
  start-page: 494
  year: 1957
  end-page: 501
  article-title: Radiological assessment of osteoarthritis
  publication-title: Ann. Rheum. Dis.
– volume: 12
  start-page: 355
  year: 1994
  end-page: 366
  article-title: The use of active shape models for locating structures in medical images
  publication-title: Image Vis. Comput.
– start-page: 103
  year: 2005
  end-page: 106
  article-title: Segmenting tibia and femur from knee X‐ray images
– volume: 36
  start-page: 709
  year: 1991
  end-page: 722
  article-title: Analysis of texture in macroradiographs of osteoarthritic knee using the fractal signature
  publication-title: Phys. Med. Biol.
– volume: 626
  start-page: 242
  year: 1986
  end-page: 250
  article-title: Adaptive histogram equalization for automatic contrast enhancement of medical images
  publication-title: Proc. SPIE
– volume: 8476
  start-page: 307
  year: 1986
  end-page: 310
  article-title: Statistical methods for assessing agreement between two methods of clinical measurement
  publication-title: Lancet
– volume: 59
  start-page: 641
  year: 2000
  end-page: 646
  article-title: Early radiographic features in patients with anterior cruciate ligament rupture
  publication-title: Ann. Rheum. Dis.
– volume: 13
  start-page: 39
  year: 2005
  end-page: 47
  article-title: Cancellous bone difference between knees with early, definite and advanced joint space loss: A comparative quantitative macroradiographic study
  publication-title: Osteoarthritis Cartilage
– volume: 17
  start-page: 483
  year: 1991
  end-page: 489
  article-title: Measurement and reliability: Statistical thinking considerations
  publication-title: Schizophr. Bull.
– volume: 51
  start-page: 938
  year: 1991
  end-page: 42
  article-title: Scintigraphic assessment of osteoarthritis of the knee joint
  publication-title: Ann. Rheum. Dis.
– ident: e_1_2_7_29_1
  doi: 10.1118/1.598897
– ident: e_1_2_7_5_1
  doi: 10.1146/annurev.bioeng.2.1.315
– ident: e_1_2_7_18_1
  doi: 10.1109/34.254061
– ident: e_1_2_7_23_1
  doi: 10.1093/schbul/17.3.483
– ident: e_1_2_7_11_1
  doi: 10.1016/j.joca.2006.07.012
– start-page: 103
  year: 2005
  ident: e_1_2_7_30_1
– start-page: 2712
  year: 2001
  ident: e_1_2_7_7_1
– ident: e_1_2_7_26_1
  doi: 10.1016/j.compmedimag.2005.12.001
– ident: e_1_2_7_19_1
  doi: 10.1016/0262‐8856(94)90060‐4
– ident: e_1_2_7_4_1
  doi: 10.1016/j.joca.2007.07.010
– ident: e_1_2_7_12_1
  doi: 10.1136/ard.16.4.494
– ident: e_1_2_7_9_1
  doi: 10.1117/12.595640
– ident: e_1_2_7_25_1
  doi: 10.1016/S0140-6736(86)90837-8
– ident: e_1_2_7_6_1
  doi: 10.1016/S1361‐8415(01)00051‐2
– ident: e_1_2_7_13_1
  doi: 10.1136/ard.59.8.641
– ident: e_1_2_7_8_1
  doi: 10.1109/TMI.2006.872747
– ident: e_1_2_7_17_1
  doi: 10.1117/12.975399
– start-page: 610
  year: 1994
  ident: e_1_2_7_20_1
– ident: e_1_2_7_28_1
  doi: 10.1118/1.598331
– ident: e_1_2_7_14_1
  doi: 10.1016/S0021‐9290(02)00386‐X
– ident: e_1_2_7_3_1
  doi: 10.1016/j.joca.2004.10.009
– ident: e_1_2_7_21_1
  doi: 10.1006/cviu.1995.1004
– ident: e_1_2_7_16_1
  doi: 10.1016/S8756-3282(02)00982-1
– ident: e_1_2_7_27_1
  doi: 10.1118/1.1449875
– ident: e_1_2_7_10_1
  doi: 10.1034/j.1600‐0455.2002.430119.x
– ident: e_1_2_7_22_1
  doi: 10.1109/34.142909
– ident: e_1_2_7_24_1
  doi: 10.1109/42.363096
– ident: e_1_2_7_2_1
  doi: 10.1088/0031‐9155/36/6/001
– ident: e_1_2_7_15_1
  doi: 10.1136/ard.51.8.938
SSID ssj0006350
Score 2.025506
Snippet Osteoarthritic (OA) changes in knee joints can be assessed by analyzing the structure of trabecular bone (TB) in the tibia. This analysis is performed on TB...
SourceID osti
proquest
pubmed
crossref
wiley
scitation
SourceType Open Access Repository
Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage 1870
SubjectTerms ACCURACY
automatic optical inspection
Automation
Biomedical modeling
BIOMEDICAL RADIOGRAPHY
bone
Bone and Bones - pathology
BONE JOINTS
computer-aided diagnosis
Diagnosis, Computer-Assisted
diagnostic radiography
Fractals
Humans
Image enhancement
IMAGE PROCESSING
Image Processing, Computer-Assisted
image segmentation
image texture
Knee - diagnostic imaging
Knee Joint - diagnostic imaging
Knee Joint - pathology
knee radiography
medical image processing
Medical imaging
Medical X‐ray imaging
Models, Statistical
NUMERICAL ANALYSIS
Numerical modeling
osteoarthritis
Osteoarthritis - diagnostic imaging
Osteoarthritis, Knee - diagnostic imaging
Osteoarthritis, Knee - pathology
Radiographic Image Interpretation, Computer-Assisted - methods
Radiography
Radiologists
RADIOLOGY AND NUCLEAR MEDICINE
Scattering, Radiation
Segmentation
Software
Testing procedures
TIBIA
TRABECULAR BONE
X RADIATION
X-Rays
X‐ray imaging
Title Automated selection of trabecular bone regions in knee radiographs
URI http://dx.doi.org/10.1118/1.2905025
https://onlinelibrary.wiley.com/doi/abs/10.1118%2F1.2905025
https://www.ncbi.nlm.nih.gov/pubmed/18561662
https://www.proquest.com/docview/69228917
https://www.osti.gov/biblio/21120690
Volume 35
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVEBS
  databaseName: Inspec with Full Text
  customDbUrl:
  eissn: 2473-4209
  dateEnd: 20241105
  omitProxy: false
  ssIdentifier: ssj0006350
  issn: 0094-2405
  databaseCode: ADMLS
  dateStart: 20070101
  isFulltext: true
  titleUrlDefault: https://www.ebsco.com/products/research-databases/inspec-full-text
  providerName: EBSCOhost
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1bb9MwFLagE7cHBOMWGBABmvYSSBMnjR8LbEyoHZVoRd8sO7ahYkpKm4LEr-c4dpxUKjB4SdvIsVN_Jyffsc8FoRccRzwDXhEIFqsAnkQWMC6TIIpZJGOlhKyjXMdn6ekMv58n87bgXR1dUvGX-c-dcSX_gyqcA1x1lOw_IOs6hRPwHfCFIyAMxwthPNxUJTBO4IzrupyNJX_VCibC-JfystB1UT43DuNfCwm_mViYTNXrLjdt9mzMYke9GqsjpJmp3eEWDCalWC-YMFs2LjrsU3luK2B3CxSDbv2xYLXCfWdc-dwKQ9b68zVak2C9C5N0taZJMmKlI-mowH5mKoHs0M063gBschImoYl23s5_ffaBnsxGIzo9nk8Pl98CXRpMb6HbOimX0V4Eqjvsob3h2_Hoo3vhAmcykUb2Nm0CKRjvlRtti3b0SlCfu0yKG-gaEA_jA7FtrdR0Y3oL3bR2gj80oN9Gl2Sxj66OrSfEProyMSjdQa-dFPhOCvxS-a0U-FoKfCsF_qLwtRT4HSm4i2Ynx9M3p4GtjBHkulR0QGQiccbBGBcxD2VKVEIwJqnguVLA8QnOQkZ4HouMSZVhoMU5yXiSRxILpdL4HuoVMPQD5DNFMFxFQhUKjAeSDJhQAsu-kkCVcd9DR83E0WZqdPWSc2rMx4z2qZ1jDz1zTZcmV8quRgd69qmeZ5l_ybU7V17RCHi_TprtoacNKhQUnd69YoUsN2uakijKSH_gofsGrHaMDIyANI089Nyh96cbSC_QykFHHXQ7u_9ertqL6FIoDx3WYvP7rul4oj8e_vWfPkLX28fxAPWq1UY-Bgpc8Sf2EfgFGM2wNQ
linkProvider EBSCOhost
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Automated+selection+of+trabecular+bone+regions+in+knee+radiographs&rft.jtitle=Medical+physics+%28Lancaster%29&rft.au=Podsiadlo%2C+P&rft.au=Wolski%2C+M&rft.au=Stachowiak%2C+G+W&rft.date=2008-05-01&rft.issn=0094-2405&rft.volume=35&rft.issue=5&rft.spage=1870&rft_id=info:doi/10.1118%2F1.2905025&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0094-2405&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0094-2405&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0094-2405&client=summon