Validation of Results from Knowledge Discovery: Mass Density as a Predictor of Breast Cancer

The purpose of our study is to identify and quantify the association between high breast mass density and breast malignancy using inductive logic programming (ILP) and conditional probabilities, and validate this association in an independent dataset. We ran our ILP algorithm on 62,219 mammographic...

Full description

Saved in:
Bibliographic Details
Published in:Journal of digital imaging Vol. 23; no. 5; pp. 554 - 561
Main Authors: Woods, Ryan W., Oliphant, Louis, Shinki, Kazuhiko, Page, David, Shavlik, Jude, Burnside, Elizabeth
Format: Journal Article
Language:English
Published: New York Springer-Verlag 01.10.2010
Springer Nature B.V
Subjects:
ISSN:0897-1889, 1618-727X, 1618-727X
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract The purpose of our study is to identify and quantify the association between high breast mass density and breast malignancy using inductive logic programming (ILP) and conditional probabilities, and validate this association in an independent dataset. We ran our ILP algorithm on 62,219 mammographic abnormalities. We set the Aleph ILP system to generate 10,000 rules per malignant finding with a recall >5% and precision >25%. Aleph reported the best rule for each malignant finding. A total of 80 unique rules were learned. A radiologist reviewed all rules and identified potentially interesting rules. High breast mass density appeared in 24% of the learned rules. We confirmed each interesting rule by calculating the probability of malignancy given each mammographic descriptor. High mass density was the fifth highest ranked predictor. To validate the association between mass density and malignancy in an independent dataset, we collected data from 180 consecutive breast biopsies performed between 2005 and 2007. We created a logistic model with benign or malignant outcome as the dependent variable while controlling for potentially confounding factors. We calculated odds ratios based on dichomotized variables. In our logistic regression model, the independent predictors high breast mass density (OR 6.6, CI 2.5–17.6), irregular mass shape (OR 10.0, CI 3.4–29.5), spiculated mass margin (OR 20.4, CI 1.9–222.8), and subject age ( β  = 0.09, p  < 0.0001) significantly predicted malignancy. Both ILP and conditional probabilities show that high breast mass density is an important adjunct predictor of malignancy, and this association is confirmed in an independent data set of prospectively collected mammographic findings.
AbstractList The purpose of our study is to identify and quantify the association between high breast mass density and breast malignancy using inductive logic programming (ILP) and conditional probabilities, and validate this association in an independent dataset. We ran our ILP algorithm on 62,219 mammographic abnormalities. We set the Aleph ILP system to generate 10,000 rules per malignant finding with a recall >5% and precision >25%. Aleph reported the best rule for each malignant finding. A total of 80 unique rules were learned. A radiologist reviewed all rules and identified potentially interesting rules. High breast mass density appeared in 24% of the learned rules. We confirmed each interesting rule by calculating the probability of malignancy given each mammographic descriptor. High mass density was the fifth highest ranked predictor. To validate the association between mass density and malignancy in an independent dataset, we collected data from 180 consecutive breast biopsies performed between 2005 and 2007. We created a logistic model with benign or malignant outcome as the dependent variable while controlling for potentially confounding factors. We calculated odds ratios based on dichomotized variables. In our logistic regression model, the independent predictors high breast mass density (OR 6.6, CI 2.5-17.6), irregular mass shape (OR 10.0, CI 3.4-29.5), spiculated mass margin (OR 20.4, CI 1.9-222.8), and subject age ( beta =0.09, p<0.0001) significantly predicted malignancy. Both ILP and conditional probabilities show that high breast mass density is an important adjunct predictor of malignancy, and this association is confirmed in an independent data set of prospectively collected mammographic findings.
The purpose of our study is to identify and quantify the association between high breast mass density and breast malignancy using inductive logic programming (ILP) and conditional probabilities, and validate this association in an independent dataset. We ran our ILP algorithm on 62,219 mammographic abnormalities. We set the Aleph ILP system to generate 10,000 rules per malignant finding with a recall >5% and precision >25%. Aleph reported the best rule for each malignant finding. A total of 80 unique rules were learned. A radiologist reviewed all rules and identified potentially interesting rules. High breast mass density appeared in 24% of the learned rules. We confirmed each interesting rule by calculating the probability of malignancy given each mammographic descriptor. High mass density was the fifth highest ranked predictor. To validate the association between mass density and malignancy in an independent dataset, we collected data from 180 consecutive breast biopsies performed between 2005 and 2007. We created a logistic model with benign or malignant outcome as the dependent variable while controlling for potentially confounding factors. We calculated odds ratios based on dichomotized variables. In our logistic regression model, the independent predictors high breast mass density (OR 6.6, CI 2.5-17.6), irregular mass shape (OR 10.0, CI 3.4-29.5), spiculated mass margin (OR 20.4, CI 1.9-222.8), and subject age (β = 0.09, p < 0.0001) significantly predicted malignancy. Both ILP and conditional probabilities show that high breast mass density is an important adjunct predictor of malignancy, and this association is confirmed in an independent data set of prospectively collected mammographic findings.The purpose of our study is to identify and quantify the association between high breast mass density and breast malignancy using inductive logic programming (ILP) and conditional probabilities, and validate this association in an independent dataset. We ran our ILP algorithm on 62,219 mammographic abnormalities. We set the Aleph ILP system to generate 10,000 rules per malignant finding with a recall >5% and precision >25%. Aleph reported the best rule for each malignant finding. A total of 80 unique rules were learned. A radiologist reviewed all rules and identified potentially interesting rules. High breast mass density appeared in 24% of the learned rules. We confirmed each interesting rule by calculating the probability of malignancy given each mammographic descriptor. High mass density was the fifth highest ranked predictor. To validate the association between mass density and malignancy in an independent dataset, we collected data from 180 consecutive breast biopsies performed between 2005 and 2007. We created a logistic model with benign or malignant outcome as the dependent variable while controlling for potentially confounding factors. We calculated odds ratios based on dichomotized variables. In our logistic regression model, the independent predictors high breast mass density (OR 6.6, CI 2.5-17.6), irregular mass shape (OR 10.0, CI 3.4-29.5), spiculated mass margin (OR 20.4, CI 1.9-222.8), and subject age (β = 0.09, p < 0.0001) significantly predicted malignancy. Both ILP and conditional probabilities show that high breast mass density is an important adjunct predictor of malignancy, and this association is confirmed in an independent data set of prospectively collected mammographic findings.
The purpose of our study is to identify and quantify the association between high breast mass density and breast malignancy using inductive logic programming (ILP) and conditional probabilities, and validate this association in an independent dataset. We ran our ILP algorithm on 62,219 mammographic abnormalities. We set the Aleph ILP system to generate 10,000 rules per malignant finding with a recall >5% and precision >25%. Aleph reported the best rule for each malignant finding. A total of 80 unique rules were learned. A radiologist reviewed all rules and identified potentially interesting rules. High breast mass density appeared in 24% of the learned rules. We confirmed each interesting rule by calculating the probability of malignancy given each mammographic descriptor. High mass density was the fifth highest ranked predictor. To validate the association between mass density and malignancy in an independent dataset, we collected data from 180 consecutive breast biopsies performed between 2005 and 2007. We created a logistic model with benign or malignant outcome as the dependent variable while controlling for potentially confounding factors. We calculated odds ratios based on dichomotized variables. In our logistic regression model, the independent predictors high breast mass density (OR 6.6, CI 2.5–17.6), irregular mass shape (OR 10.0, CI 3.4–29.5), spiculated mass margin (OR 20.4, CI 1.9–222.8), and subject age ( β  = 0.09, p  < 0.0001) significantly predicted malignancy. Both ILP and conditional probabilities show that high breast mass density is an important adjunct predictor of malignancy, and this association is confirmed in an independent data set of prospectively collected mammographic findings.
The purpose of our study is to identify and quantify the association between high breast mass density and breast malignancy using inductive logic programming (ILP) and conditional probabilities, and validate this association in an independent dataset. We ran our ILP algorithm on 62,219 mammographic abnormalities. We set the Aleph ILP system to generate 10,000 rules per malignant finding with a recall >5% and precision >25%. Aleph reported the best rule for each malignant finding. A total of 80 unique rules were learned. A radiologist reviewed all rules and identified potentially interesting rules. High breast mass density appeared in 24% of the learned rules. We confirmed each interesting rule by calculating the probability of malignancy given each mammographic descriptor. High mass density was the fifth highest ranked predictor. To validate the association between mass density and malignancy in an independent dataset, we collected data from 180 consecutive breast biopsies performed between 2005 and 2007. We created a logistic model with benign or malignant outcome as the dependent variable while controlling for potentially confounding factors. We calculated odds ratios based on dichomotized variables. In our logistic regression model, the independent predictors high breast mass density (OR 6.6, CI 2.5-17.6), irregular mass shape (OR 10.0, CI 3.4-29.5), spiculated mass margin (OR 20.4, CI 1.9-222.8), and subject age (β = 0.09, p < 0.0001) significantly predicted malignancy. Both ILP and conditional probabilities show that high breast mass density is an important adjunct predictor of malignancy, and this association is confirmed in an independent data set of prospectively collected mammographic findings.
The purpose of our study is to identify and quantify the association between high breast mass density and breast malignancy using inductive logic programming (ILP) and conditional probabilities, and validate this association in an independent dataset. We ran our ILP algorithm on 62,219 mammographic abnormalities. We set the Aleph ILP system to generate 10,000 rules per malignant finding with a recall >5% and precision >25%. Aleph reported the best rule for each malignant finding. A total of 80 unique rules were learned. A radiologist reviewed all rules and identified potentially interesting rules. High breast mass density appeared in 24% of the learned rules. We confirmed each interesting rule by calculating the probability of malignancy given each mammographic descriptor. High mass density was the fifth highest ranked predictor. To validate the association between mass density and malignancy in an independent dataset, we collected data from 180 consecutive breast biopsies performed between 2005 and 2007. We created a logistic model with benign or malignant outcome as the dependent variable while controlling for potentially confounding factors. We calculated odds ratios based on dichomotized variables. In our logistic regression model, the independent predictors high breast mass density (OR 6.6, CI 2.5-17.6), irregular mass shape (OR 10.0, CI 3.4-29.5), spiculated mass margin (OR 20.4, CI 1.9-222.8), and subject age (β=0.09, p<0.0001) significantly predicted malignancy. Both ILP and conditional probabilities show that high breast mass density is an important adjunct predictor of malignancy, and this association is confirmed in an independent data set of prospectively collected mammographic findings.[PUBLICATION ABSTRACT]
Author Shinki, Kazuhiko
Woods, Ryan W.
Oliphant, Louis
Shavlik, Jude
Page, David
Burnside, Elizabeth
Author_xml – sequence: 1
  givenname: Ryan W.
  surname: Woods
  fullname: Woods, Ryan W.
  organization: Department of Radiology, University of Wisconsin School of Medicine and Public Health
– sequence: 2
  givenname: Louis
  surname: Oliphant
  fullname: Oliphant, Louis
  organization: Department of Biostatistics and Medical Informatics, University of Wisconsin
– sequence: 3
  givenname: Kazuhiko
  surname: Shinki
  fullname: Shinki, Kazuhiko
  organization: Department of Statistics, University of Wisconsin
– sequence: 4
  givenname: David
  surname: Page
  fullname: Page, David
  organization: Department of Biostatistics and Medical Informatics, University of Wisconsin
– sequence: 5
  givenname: Jude
  surname: Shavlik
  fullname: Shavlik, Jude
  organization: Department of Biostatistics and Medical Informatics, University of Wisconsin
– sequence: 6
  givenname: Elizabeth
  surname: Burnside
  fullname: Burnside, Elizabeth
  email: eburnside@uwhealth.org
  organization: Department of Radiology, University of Wisconsin School of Medicine and Public Health
BackLink https://www.ncbi.nlm.nih.gov/pubmed/19760292$$D View this record in MEDLINE/PubMed
BookMark eNp9kktvFDEQhC0URDaBH8AFWVzIZcBtr18cIsGGlwgCIUAckCzH07NMNGsHeybR_nu8bAgQiZx88Fel6u7aIzsxRSTkPrDHwJh-UoBxbRrGbGO5kI24RWagwDSa6687ZMaM1Q0YY3fJXimnjIGWen6H7ILVinHLZ-TbFz_0rR_7FGnq6Ecs0zAW2uW0om9juhiwXSI96ktI55jXT-k7Xwo9wlj6cU19oZ5-yNj2YUx5Y_A8oy8jXfgYMN8ltzs_FLx3-e6Tzy9ffFq8bo7fv3qzeHbcBMlgbLqWKxNaw4GhrcmwQ62NFkyr0IouzLUQlnmhvGJMSa9hLqSQATgEBSco9snh1vdsOllhGzCO2Q_uLPcrn9cu-d79-xP7726Zzh23sm5QVoNHlwY5_ZiwjG5VJ8Zh8BHTVJyWynBhFa_kwY0kKA1cAgOo6MNr6GmacqyLcMYwMbec2wo9-Dv6VebfF6qA3gIhp1Iydi7046971Un6wQFzmy64bRdc7YLbdMGJqoRryivzGzR8qymVjUvMfzL_X_QT4YDEtg
CitedBy_id crossref_primary_10_1016_j_ejrad_2024_111614
crossref_primary_10_1007_s10278_013_9588_5
crossref_primary_10_3389_fgene_2022_822858
crossref_primary_10_3389_fonc_2023_1110657
Cites_doi 10.1148/radiology.196.3.7644649
10.2214/ajr.171.1.9648759
10.1109/51.853478
10.1148/radiology.184.2.1620838
10.1148/radiology.167.2.3282256
10.1016/j.jacr.2007.09.003
10.1148/radiology.192.2.8029411
10.2214/ajr.157.1.1646563
10.2214/AJR.07.2153
10.1148/radiology.219.2.r01ma11475
10.1007/978-3-662-04599-2_3
10.1148/radiology.165.1.3628796
10.1148/radiology.178.1.1984295
ContentType Journal Article
Copyright Society for Imaging Informatics in Medicine 2009
Society for Imaging Informatics in Medicine 2010
Copyright_xml – notice: Society for Imaging Informatics in Medicine 2009
– notice: Society for Imaging Informatics in Medicine 2010
DBID C6C
AAYXX
CITATION
CGR
CUY
CVF
ECM
EIF
NPM
3V.
7QO
7RV
7SC
7TK
7X7
7XB
88E
8AO
8FD
8FE
8FG
8FH
8FI
8FJ
8FK
ABUWG
AFKRA
ARAPS
AZQEC
BBNVY
BENPR
BGLVJ
BHPHI
CCPQU
DWQXO
FR3
FYUFA
GHDGH
GNUQQ
HCIFZ
JQ2
K9.
KB0
L7M
LK8
L~C
L~D
M0S
M1P
M7P
NAPCQ
P5Z
P62
P64
PHGZM
PHGZT
PJZUB
PKEHL
PPXIY
PQEST
PQGLB
PQQKQ
PQUKI
PRINS
7X8
5PM
DOI 10.1007/s10278-009-9235-3
DatabaseName Springer Nature OA Free Journals
CrossRef
Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
ProQuest Central (Corporate)
Biotechnology Research Abstracts
Nursing & Allied Health Database
Computer and Information Systems Abstracts
Neurosciences Abstracts
Health & Medical Collection
ProQuest Central (purchase pre-March 2016)
Medical Database (Alumni Edition)
ProQuest Pharma Collection
Technology Research Database
ProQuest SciTech Collection
ProQuest Technology Collection
ProQuest Natural Science Journals
Hospital Premium Collection
Hospital Premium Collection (Alumni Edition)
ProQuest Central (Alumni) (purchase pre-March 2016)
ProQuest Central (Alumni)
ProQuest Central UK/Ireland
Advanced Technologies & Computer Science Collection
ProQuest Central Essentials
Biological Science Collection
ProQuest Central
ProQuest Technology Collection
Natural Science Collection
ProQuest One
ProQuest Central
Engineering Research Database
Proquest Health Research Premium Collection
Health Research Premium Collection (Alumni)
ProQuest Central Student
ProQuest SciTech Premium Collection
ProQuest Computer Science Collection
ProQuest Health & Medical Complete (Alumni)
Nursing & Allied Health Database (Alumni Edition)
Advanced Technologies Database with Aerospace
Biological Sciences
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
ProQuest Health & Medical Collection
Medical Database
Biological Science Database
Nursing & Allied Health Premium
Advanced Technologies & Aerospace Database
ProQuest Advanced Technologies & Aerospace Collection
Biotechnology and BioEngineering Abstracts
ProQuest Central Premium
ProQuest One Academic (New)
ProQuest Health & Medical Research Collection
ProQuest One Academic Middle East (New)
ProQuest One Health & Nursing
ProQuest One Academic Eastern Edition (DO NOT USE)
One Applied & Life Sciences
ProQuest One Academic (retired)
ProQuest One Academic UKI Edition
ProQuest Central China
MEDLINE - Academic
PubMed Central (Full Participant titles)
DatabaseTitle CrossRef
MEDLINE
Medline Complete
MEDLINE with Full Text
PubMed
MEDLINE (Ovid)
ProQuest Central Student
ProQuest Advanced Technologies & Aerospace Collection
ProQuest Central Essentials
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
SciTech Premium Collection
ProQuest Central China
ProQuest One Applied & Life Sciences
Health Research Premium Collection
Natural Science Collection
Health & Medical Research Collection
Biological Science Collection
ProQuest Central (New)
ProQuest Medical Library (Alumni)
Advanced Technologies & Aerospace Collection
ProQuest Biological Science Collection
ProQuest One Academic Eastern Edition
ProQuest Hospital Collection
ProQuest Technology Collection
Health Research Premium Collection (Alumni)
Biological Science Database
Neurosciences Abstracts
ProQuest Hospital Collection (Alumni)
Biotechnology and BioEngineering Abstracts
Nursing & Allied Health Premium
ProQuest Health & Medical Complete
ProQuest One Academic UKI Edition
ProQuest Nursing & Allied Health Source (Alumni)
Engineering Research Database
ProQuest One Academic
ProQuest One Academic (New)
Technology Collection
Technology Research Database
Computer and Information Systems Abstracts – Academic
ProQuest One Academic Middle East (New)
ProQuest Health & Medical Complete (Alumni)
ProQuest Central (Alumni Edition)
ProQuest One Community College
ProQuest One Health & Nursing
ProQuest Natural Science Collection
ProQuest Pharma Collection
ProQuest Central
ProQuest Health & Medical Research Collection
Biotechnology Research Abstracts
Health and Medicine Complete (Alumni Edition)
ProQuest Central Korea
Advanced Technologies Database with Aerospace
ProQuest Nursing & Allied Health Source
ProQuest SciTech Collection
Computer and Information Systems Abstracts Professional
Advanced Technologies & Aerospace Database
ProQuest Medical Library
ProQuest Central (Alumni)
MEDLINE - Academic
DatabaseTitleList Computer and Information Systems Abstracts
MEDLINE - Academic

MEDLINE

ProQuest Central Student
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: BENPR
  name: ProQuest Central
  url: https://www.proquest.com/central
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Medicine
EISSN 1618-727X
EndPage 561
ExternalDocumentID PMC2950275
2413476651
19760292
10_1007_s10278_009_9235_3
Genre Validation Study
Journal Article
Research Support, N.I.H., Extramural
GrantInformation_xml – fundername: NCI NIH HHS
  grantid: K07-CA114181
– fundername: NCI NIH HHS
  grantid: K07 CA114181
– fundername: NCI NIH HHS
  grantid: R01-CA127379
– fundername: NCI NIH HHS
  grantid: R01 CA127379
GroupedDBID ---
-5E
-5G
-BR
-EM
-Y2
-~C
.4S
.86
.DC
.VR
04C
06C
06D
0R~
0VY
1N0
2.D
203
29K
29~
2J2
2JN
2JY
2KG
2KM
2LR
2P1
2VQ
2~H
30V
36B
3V.
4.4
406
408
409
40D
40E
53G
5GY
5RE
5VS
67Z
6NX
6PF
78A
7RV
7X7
88E
8AO
8FE
8FG
8FH
8FI
8FJ
8FW
8TC
8UJ
95-
95.
95~
96X
AAAVM
AABHQ
AAHNG
AAIAL
AAJKR
AAKDD
AAKPC
AANXM
AANZL
AARHV
AARTL
AATVU
AAUYE
AAWCG
AAWTL
AAYIU
AAYQN
AAYTO
ABBBX
ABBXA
ABDZT
ABECU
ABFTV
ABHLI
ABHQN
ABIPD
ABJNI
ABJOX
ABKCH
ABKTR
ABMNI
ABMQK
ABNWP
ABPLI
ABQBU
ABQSL
ABSXP
ABTEG
ABTKH
ABTMW
ABULA
ABUWG
ABWNU
ABXPI
ACAOD
ACGFS
ACHSB
ACHXU
ACIWK
ACKNC
ACMDZ
ACMLO
ACOKC
ACOMO
ACPRK
ACSNA
ACZOJ
ADBBV
ADHHG
ADHIR
ADINQ
ADJJI
ADKNI
ADKPE
ADMLS
ADOJX
ADRFC
ADTPH
ADURQ
ADYFF
ADZKW
AEBTG
AEFQL
AEGAL
AEGNC
AEJHL
AEJRE
AEKMD
AEMSY
AENEX
AEOHA
AEPYU
AESKC
AETLH
AEVLU
AEXYK
AFKRA
AFLOW
AFQWF
AFRAH
AFWTZ
AFZKB
AGAYW
AGDGC
AGJBK
AGMZJ
AGQEE
AGQMX
AGRTI
AGWIL
AGWZB
AGYKE
AHAVH
AHBYD
AHIZS
AHKAY
AHMBA
AHSBF
AHYZX
AIAKS
AIIXL
AILAN
AITGF
AJBLW
AJRNO
AJZVZ
AKMHD
ALIPV
ALMA_UNASSIGNED_HOLDINGS
ALWAN
AMKLP
AMXSW
AMYLF
AMYQR
AOCGG
AOIJS
ARAPS
ARCSS
ARMRJ
ASPBG
AVWKF
AXYYD
AZFZN
B-.
BA0
BAWUL
BBNVY
BDATZ
BENPR
BGLVJ
BGNMA
BHPHI
BKEYQ
BMSDO
BPHCQ
BSONS
BVXVI
C6C
CAG
CCPQU
COF
CS3
CSCUP
D-I
DDRTE
DIK
DL5
DNIVK
DPUIP
DU5
EBD
EBS
ECT
EDO
EIHBH
EIOEI
EJD
EMB
EMOBN
EN4
ESBYG
EX3
F5P
FEDTE
FERAY
FFXSO
FIGPU
FINBP
FNLPD
FRRFC
FSGXE
FWDCC
FYUFA
G-Y
G-Z
GGCAI
GGRSB
GJIRD
GNWQR
GQ6
GQ7
GQ8
GX1
GXS
H13
HCIFZ
HF~
HG5
HG6
HMCUK
HMJXF
HQYDN
HRMNR
HVGLF
HYE
HZ~
I-F
I09
IHE
IJ-
IKXTQ
IMOTQ
ITM
IWAJR
IXC
IZIGR
IZQ
I~X
I~Z
J-C
J0Z
JBSCW
JCJTX
KDC
KOV
KPH
LAS
LK8
LLZTM
M1P
M4Y
M7P
MA-
N2Q
NAPCQ
NB0
NPVJJ
NQJWS
NU0
O9-
O93
O9I
O9J
OAM
OK1
P2P
P62
P9S
PF0
PQQKQ
PROAC
PSQYO
Q2X
QOK
QOR
QOS
R89
R9I
RNS
ROL
RPM
RPX
RRX
RSV
S16
S1Z
S27
S37
S3B
SAP
SDH
SHX
SISQX
SMD
SNE
SNPRN
SNX
SOHCF
SOJ
SPISZ
SRMVM
SSLCW
SSXJD
STPWE
SV3
SZ9
SZN
T13
TSG
TSK
TSV
TT1
TUC
TUS
U2A
U9L
UDS
UG4
UKHRP
UOJIU
UTJUX
UZXMN
VC2
VFIZW
W23
W48
WJK
WK8
WOW
YLTOR
Z45
Z7R
Z7W
Z7X
Z82
Z83
Z88
Z8R
Z8V
Z8W
Z92
ZMTXR
ZOVNA
~A9
AAPKM
AAYXX
ACSTC
ADHKG
AFFHD
AGQPQ
AHPBZ
AYFIA
CITATION
PHGZM
PHGZT
PJZUB
PPXIY
PQGLB
CGR
CUY
CVF
ECM
EIF
NPM
7QO
7SC
7TK
7XB
8FD
8FK
AZQEC
DWQXO
FR3
GNUQQ
JQ2
K9.
L7M
L~C
L~D
P64
PKEHL
PQEST
PQUKI
PRINS
7X8
PUEGO
5PM
ID FETCH-LOGICAL-c501t-fd268cd8210e9976efe77873076cd3fc473390a36a60065a7143535c121c61be3
IEDL.DBID M7P
ISICitedReferencesCount 9
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000282597100007&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0897-1889
1618-727X
IngestDate Tue Nov 04 01:52:20 EST 2025
Thu Sep 04 23:52:30 EDT 2025
Sun Nov 09 13:14:01 EST 2025
Tue Nov 04 18:51:50 EST 2025
Mon Jul 21 05:59:01 EDT 2025
Sat Nov 29 01:57:20 EST 2025
Tue Nov 18 22:04:25 EST 2025
Fri Feb 21 02:31:27 EST 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed false
IsScholarly false
Issue 5
Keywords mammography
Data mining
machine learning
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c501t-fd268cd8210e9976efe77873076cd3fc473390a36a60065a7143535c121c61be3
Notes ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 14
ObjectType-Article-1
ObjectType-Feature-2
content type line 23
ObjectType-Undefined-3
OpenAccessLink https://pubmed.ncbi.nlm.nih.gov/PMC2950275
PMID 19760292
PQID 880349229
PQPubID 34218
PageCount 8
ParticipantIDs pubmedcentral_primary_oai_pubmedcentral_nih_gov_2950275
proquest_miscellaneous_756823962
proquest_miscellaneous_1671251011
proquest_journals_880349229
pubmed_primary_19760292
crossref_citationtrail_10_1007_s10278_009_9235_3
crossref_primary_10_1007_s10278_009_9235_3
springer_journals_10_1007_s10278_009_9235_3
PublicationCentury 2000
PublicationDate 2010-10-01
PublicationDateYYYYMMDD 2010-10-01
PublicationDate_xml – month: 10
  year: 2010
  text: 2010-10-01
  day: 01
PublicationDecade 2010
PublicationPlace New York
PublicationPlace_xml – name: New York
– name: United States
PublicationSubtitle The Journal of the Society for Computer Applications in Radiology
PublicationTitle Journal of digital imaging
PublicationTitleAbbrev J Digit Imaging
PublicationTitleAlternate J Digit Imaging
PublicationYear 2010
Publisher Springer-Verlag
Springer Nature B.V
Publisher_xml – name: Springer-Verlag
– name: Springer Nature B.V
References DzeroskiSLavracNDzeroskiSLavracNIntroduction to inductive logic programmingRelational Data Mining2001BerlinSpringer4871
VizcainoIGadeaLAndreoLShort-term follow-up results in 795 nonpalpable probably benign lesions detected at screening mammographyRadiology200121924754831:STN:280:DC%2BD3M3mt1eitg%3D%3D11323475
American College of Radiology: Breast Imaging Reporting and Data System (BI-RADS), 4th edition. Reston, VA, 2003
DangPAKalraMKBlakeMANatural language processing using online analytic processing for assessing recommendations in radiology reportsJ Am Coll Radiol20085319720410.1016/j.jacr.2007.09.00318312968
CiattoSCataliottiLDistanteVNonpalpable lesions detected with mammography: review of 512 consecutive casesRadiology19871651991021:STN:280:DyaL2szhvVKgtQ%3D%3D3628796
HallFMStorellaJMSilverstoneDZWyshakGNonpalpable breast lesions: recommendations for biopsy based on suspicion of carcinoma at mammographyRadiology198816723533581:STN:280:DyaL1c7ptVeltw%3D%3D3282256
JacksonVPDinesKABassettLWGoldRHReynoldsHEDiagnostic importance of the radiographic density of noncalcified breast masses: analysis of 91 lesionsAJR Am J Roentgenol1991157125281:STN:280:DyaK3M3mtl2nug%3D%3D1646563
Burnside ES, Davis J, Costa VS, et al: Knowledge discovery from structured mammography reports using inductive logic programming. AMIA Annu Symp Proc 96–100, 2005
LangMKirpekarNBurkleTLaumannSProkoschHUResults from data mining in a radiology department: the relevance of data qualityStud Health Technol Inform2007129Pt 157658017911782
LibermanLAbramsonAFSquiresFBGlassmanJRMorrisEADershawDDThe breast imaging reporting and data system: positive predictive value of mammographic features and final assessment categoriesAJR Am J Roentgenol1998171135401:STN:280:DyaK1czhtFSqsQ%3D%3D9648759
CiosKJTeresinskaAKoniecznaSPotockaJSharmaSA knowledge discovery approach to diagnosing myocardial perfusionIEEE Eng Med Biol Mag200019417251:STN:280:DC%2BD3M%2FlvFWjsg%3D%3D10.1109/51.85347810916729
GrinsteadCMSnellJLIntroduction to Probability19972ProvidenceAmerican Mathematical Society
BakerJAKornguthPJLoJYWillifordMEFloydCEJrBreast cancer: prediction with artificial neural network based on BI-RADS® standardized lexiconRadiology199519638178221:STN:280:DyaK2Mznt1GgtQ%3D%3D7644649
Srinivasan A: The Aleph Manual, 4th edition:http://www.comlab.ox.ac.uk/activities/machinelearning/Aleph/aleph_toc.html. Accessed May 24th, 2009.
LehmanCDRutterCMEbyPRWhiteEBuistDSTaplinSHLesion and patient characteristics associated with malignancy after a probably benign finding on community practice mammographyAJR Am J Roentgenol2008190251151510.2214/AJR.07.215318212240
SicklesEANonpalpable, circumscribed, noncalcified solid breast masses: likelihood of malignancy based on lesion size and age of patientRadiology199419224394421:STN:280:DyaK2czgt1agsA%3D%3D8029411
VarasXLeborgneFLeborgneJHNonpalpable, probably benign lesions: role of follow-up mammographyRadiology199218424094141:STN:280:DyaK38zhvF2nsQ%3D%3D1620838
HelvieMAPennesDRRebnerMAdlerDDMammographic follow-up of low-suspicion lesions: compliance rate and diagnostic yieldRadiology199117811551581:STN:280:DyaK3M%2FnsV2luw%3D%3D1984295
EganRLBreast Imaging : Diagnosis and Morphology of Breast Diseases1988PhiladelphiaSaunders
CD Lehman (9235_CR12) 2008; 190
9235_CR1
M Lang (9235_CR3) 2007; 129
KJ Cios (9235_CR4) 2000; 19
X Varas (9235_CR15) 1992; 184
MA Helvie (9235_CR11) 1991; 178
PA Dang (9235_CR2) 2008; 5
L Liberman (9235_CR13) 1998; 171
JA Baker (9235_CR8) 1995; 196
FM Hall (9235_CR10) 1988; 167
I Vizcaino (9235_CR16) 2001; 219
S Ciatto (9235_CR9) 1987; 165
RL Egan (9235_CR19) 1988
CM Grinstead (9235_CR6) 1997
EA Sickles (9235_CR14) 1994; 192
S Dzeroski (9235_CR5) 2001
9235_CR18
9235_CR7
VP Jackson (9235_CR17) 1991; 157
References_xml – reference: LehmanCDRutterCMEbyPRWhiteEBuistDSTaplinSHLesion and patient characteristics associated with malignancy after a probably benign finding on community practice mammographyAJR Am J Roentgenol2008190251151510.2214/AJR.07.215318212240
– reference: VizcainoIGadeaLAndreoLShort-term follow-up results in 795 nonpalpable probably benign lesions detected at screening mammographyRadiology200121924754831:STN:280:DC%2BD3M3mt1eitg%3D%3D11323475
– reference: JacksonVPDinesKABassettLWGoldRHReynoldsHEDiagnostic importance of the radiographic density of noncalcified breast masses: analysis of 91 lesionsAJR Am J Roentgenol1991157125281:STN:280:DyaK3M3mtl2nug%3D%3D1646563
– reference: HallFMStorellaJMSilverstoneDZWyshakGNonpalpable breast lesions: recommendations for biopsy based on suspicion of carcinoma at mammographyRadiology198816723533581:STN:280:DyaL1c7ptVeltw%3D%3D3282256
– reference: SicklesEANonpalpable, circumscribed, noncalcified solid breast masses: likelihood of malignancy based on lesion size and age of patientRadiology199419224394421:STN:280:DyaK2czgt1agsA%3D%3D8029411
– reference: GrinsteadCMSnellJLIntroduction to Probability19972ProvidenceAmerican Mathematical Society
– reference: Burnside ES, Davis J, Costa VS, et al: Knowledge discovery from structured mammography reports using inductive logic programming. AMIA Annu Symp Proc 96–100, 2005
– reference: VarasXLeborgneFLeborgneJHNonpalpable, probably benign lesions: role of follow-up mammographyRadiology199218424094141:STN:280:DyaK38zhvF2nsQ%3D%3D1620838
– reference: CiosKJTeresinskaAKoniecznaSPotockaJSharmaSA knowledge discovery approach to diagnosing myocardial perfusionIEEE Eng Med Biol Mag200019417251:STN:280:DC%2BD3M%2FlvFWjsg%3D%3D10.1109/51.85347810916729
– reference: DzeroskiSLavracNDzeroskiSLavracNIntroduction to inductive logic programmingRelational Data Mining2001BerlinSpringer4871
– reference: American College of Radiology: Breast Imaging Reporting and Data System (BI-RADS), 4th edition. Reston, VA, 2003
– reference: Srinivasan A: The Aleph Manual, 4th edition:http://www.comlab.ox.ac.uk/activities/machinelearning/Aleph/aleph_toc.html. Accessed May 24th, 2009.
– reference: DangPAKalraMKBlakeMANatural language processing using online analytic processing for assessing recommendations in radiology reportsJ Am Coll Radiol20085319720410.1016/j.jacr.2007.09.00318312968
– reference: HelvieMAPennesDRRebnerMAdlerDDMammographic follow-up of low-suspicion lesions: compliance rate and diagnostic yieldRadiology199117811551581:STN:280:DyaK3M%2FnsV2luw%3D%3D1984295
– reference: LibermanLAbramsonAFSquiresFBGlassmanJRMorrisEADershawDDThe breast imaging reporting and data system: positive predictive value of mammographic features and final assessment categoriesAJR Am J Roentgenol1998171135401:STN:280:DyaK1czhtFSqsQ%3D%3D9648759
– reference: LangMKirpekarNBurkleTLaumannSProkoschHUResults from data mining in a radiology department: the relevance of data qualityStud Health Technol Inform2007129Pt 157658017911782
– reference: EganRLBreast Imaging : Diagnosis and Morphology of Breast Diseases1988PhiladelphiaSaunders
– reference: CiattoSCataliottiLDistanteVNonpalpable lesions detected with mammography: review of 512 consecutive casesRadiology19871651991021:STN:280:DyaL2szhvVKgtQ%3D%3D3628796
– reference: BakerJAKornguthPJLoJYWillifordMEFloydCEJrBreast cancer: prediction with artificial neural network based on BI-RADS® standardized lexiconRadiology199519638178221:STN:280:DyaK2Mznt1GgtQ%3D%3D7644649
– volume: 196
  start-page: 817
  issue: 3
  year: 1995
  ident: 9235_CR8
  publication-title: Radiology
  doi: 10.1148/radiology.196.3.7644649
– volume: 171
  start-page: 35
  issue: 1
  year: 1998
  ident: 9235_CR13
  publication-title: AJR Am J Roentgenol
  doi: 10.2214/ajr.171.1.9648759
– volume: 19
  start-page: 17
  issue: 4
  year: 2000
  ident: 9235_CR4
  publication-title: IEEE Eng Med Biol Mag
  doi: 10.1109/51.853478
– volume: 184
  start-page: 409
  issue: 2
  year: 1992
  ident: 9235_CR15
  publication-title: Radiology
  doi: 10.1148/radiology.184.2.1620838
– ident: 9235_CR1
– volume: 167
  start-page: 353
  issue: 2
  year: 1988
  ident: 9235_CR10
  publication-title: Radiology
  doi: 10.1148/radiology.167.2.3282256
– volume: 5
  start-page: 197
  issue: 3
  year: 2008
  ident: 9235_CR2
  publication-title: J Am Coll Radiol
  doi: 10.1016/j.jacr.2007.09.003
– volume: 192
  start-page: 439
  issue: 2
  year: 1994
  ident: 9235_CR14
  publication-title: Radiology
  doi: 10.1148/radiology.192.2.8029411
– volume-title: Introduction to Probability
  year: 1997
  ident: 9235_CR6
– volume: 157
  start-page: 25
  issue: 1
  year: 1991
  ident: 9235_CR17
  publication-title: AJR Am J Roentgenol
  doi: 10.2214/ajr.157.1.1646563
– ident: 9235_CR18
– volume: 190
  start-page: 511
  issue: 2
  year: 2008
  ident: 9235_CR12
  publication-title: AJR Am J Roentgenol
  doi: 10.2214/AJR.07.2153
– volume: 219
  start-page: 475
  issue: 2
  year: 2001
  ident: 9235_CR16
  publication-title: Radiology
  doi: 10.1148/radiology.219.2.r01ma11475
– ident: 9235_CR7
– start-page: 48
  volume-title: Relational Data Mining
  year: 2001
  ident: 9235_CR5
  doi: 10.1007/978-3-662-04599-2_3
– volume: 129
  start-page: 576
  issue: Pt 1
  year: 2007
  ident: 9235_CR3
  publication-title: Stud Health Technol Inform
– volume: 165
  start-page: 99
  issue: 1
  year: 1987
  ident: 9235_CR9
  publication-title: Radiology
  doi: 10.1148/radiology.165.1.3628796
– volume: 178
  start-page: 155
  issue: 1
  year: 1991
  ident: 9235_CR11
  publication-title: Radiology
  doi: 10.1148/radiology.178.1.1984295
– volume-title: Breast Imaging : Diagnosis and Morphology of Breast Diseases
  year: 1988
  ident: 9235_CR19
SSID ssj0017574
Score 1.5560708
Snippet The purpose of our study is to identify and quantify the association between high breast mass density and breast malignancy using inductive logic programming...
SourceID pubmedcentral
proquest
pubmed
crossref
springer
SourceType Open Access Repository
Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage 554
SubjectTerms Abnormalities
Algorithms
Biopsy
Breast
Breast - pathology
Breast Neoplasms - diagnostic imaging
Breast Neoplasms - pathology
Densitometry - methods
Density
Dependent variables
Female
Humans
Imaging
Logic programming
Logistic Models
Logistics
Mammography
Mathematical models
Medicine
Medicine & Public Health
Predictive Value of Tests
Prospective Studies
Radiographic Image Interpretation, Computer-Assisted - methods
Radiology
Registries
Regression
Title Validation of Results from Knowledge Discovery: Mass Density as a Predictor of Breast Cancer
URI https://link.springer.com/article/10.1007/s10278-009-9235-3
https://www.ncbi.nlm.nih.gov/pubmed/19760292
https://www.proquest.com/docview/880349229
https://www.proquest.com/docview/1671251011
https://www.proquest.com/docview/756823962
https://pubmed.ncbi.nlm.nih.gov/PMC2950275
Volume 23
WOSCitedRecordID wos000282597100007&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVPQU
  databaseName: Advanced Technologies & Aerospace Database
  customDbUrl:
  eissn: 1618-727X
  dateEnd: 20171231
  omitProxy: false
  ssIdentifier: ssj0017574
  issn: 0897-1889
  databaseCode: P5Z
  dateStart: 19970201
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/hightechjournals
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Biological Science Database
  customDbUrl:
  eissn: 1618-727X
  dateEnd: 20171231
  omitProxy: false
  ssIdentifier: ssj0017574
  issn: 0897-1889
  databaseCode: M7P
  dateStart: 19970201
  isFulltext: true
  titleUrlDefault: http://search.proquest.com/biologicalscijournals
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Health & Medical Collection
  customDbUrl:
  eissn: 1618-727X
  dateEnd: 20171231
  omitProxy: false
  ssIdentifier: ssj0017574
  issn: 0897-1889
  databaseCode: 7X7
  dateStart: 19970201
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/healthcomplete
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Nursing & Allied Health Database
  customDbUrl:
  eissn: 1618-727X
  dateEnd: 20171231
  omitProxy: false
  ssIdentifier: ssj0017574
  issn: 0897-1889
  databaseCode: 7RV
  dateStart: 19970201
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/nahs
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest Central
  customDbUrl:
  eissn: 1618-727X
  dateEnd: 20171231
  omitProxy: false
  ssIdentifier: ssj0017574
  issn: 0897-1889
  databaseCode: BENPR
  dateStart: 19970201
  isFulltext: true
  titleUrlDefault: https://www.proquest.com/central
  providerName: ProQuest
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3daxQxEB9sK-JL_axdq0cEn5Tg7mazSXwR-4UgPY5DyyHCkmazeFD26u2e0P_emf06ztK--JKXZEOyM5NMMr_8BuBtGFkvTaS5vbAJTxJpuZXWcZ2HxK4W4a6um2QTajzWs5mZdNicqoNV9mtis1DnC0d35B9Qz4hILzafrn5zShpFwdUug8YW7BBJgmiQe5MhiKBkS8KsjeKR1qYParYv52Kilg0NRw9HcrG5Ld3wNW9CJv-Jmzbb0emj_5zIY9jt_FD2uVWcJ3DPl0_hwVkXaX8GP8_RQW_zLbFFwaa-Wl3WFaPXKOxrfw_HjueVIwzo9Ud2hl44OyY4fH3NbMUsmyypNzzTUweHBH6v2REp2fI5fD89-Xb0hXeZGLiTYVTzIo9T7XKN50Nv0IHxhVdo6bg-pC4XhUuUECa0IrUp-TSWkqpLIR1KxaXRhRd7sF0uSr8PTGk8__o8xM3TJ96F2ttIFxRu9cQW5gMIe0FkrqMpp2wZl9maYJlkl6HsMpJdJgJ4N3xy1XJ03NX4oBdL1plrlQ0yCeDNUIt2RsETW_rFqsqiVJEviMthAOyWNkqmOhYmjQN40arLejz418LYYI3aUKShAdF8b9aU818N3XdsJMWWA3jfq9x64LdO8-Wd0zyAhw0KogElvoLternyr-G--1PPq-UIttT0nMqZako9gp3Dk_FkOmrsC8uJ_PEXH-EmUg
linkProvider ProQuest
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Lb9QwEB6VgoAL70coDyPBBWQRO3FiIyEEXapW211VVal6QAqu44iVqqQkWdD-KP4jnrxWS9XeeuBsx7Ljz_PwjL8BeOUzbYVikupjHdIwFJpqoQ2VqY_sasxpddkUm4inU3l0pPbW4E__FgbTKnuZ2AjqtDB4R_7O4QyJ9Lj6ePqTYtEoDK72FTRaVIzt4rfz2KoPOyO3va853_pysLlNu6IC1Aif1TRLeSRNKp2rY5XTxTazsQOtg3pk0iAzYRwEytdBpCNUzxrrg4tAGMaZidixDdy4V-CqE-MMM8ji_cMhaBGLlvRZqpgyKVUfRG1f6nGksvUVdRaVoMGqGjxj255N0fwnTtuov63b_9mPuwO3OjubfGoPxl1Ys_k9uD7pMgnuw7dD54C09aRIkZF9W81P6orgaxsy7u8ZyWhWGcxxXbwnE-dlkBGm-9cLoiuiyV6Jo9VFiQN8xuT-mmziISofwNdLWdtDWM-L3D4GEkvn39vUd8aBDa3xpdVMZhhOtsiGZj3w-41PTEfDjtVATpIlgTRiJXFYSRArSeDBm-GT05aD5KLOGz0Mkk4cVcmAAQ9eDq1OjmBwSOe2mFcJi2K0dZ2494Cc0ycWkeSBirgHj1p4Lufj_prPlWuJV4A7dEAa89WWfPajoTPnSmDs3IO3PcSXEz93mU8uXOYLuLF9MNlNdnem4w242WR8NAmYT2G9Luf2GVwzv-pZVT5vTjCB75eN_L-EmnrU
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Lb9QwEB6Vgiou5U1DeRgJLiCrsfOwjYQQdFlRLV2tEKAekILrOGKlKilJFrQ_jX-HJ6_VUrW3Hjjbsezks2cm8_kbgGc-0zZSTFJ9rEMahpGmOtKGytRHdTXmrLpsik2I6VQeHanZBvzp78IgrbI_E5uDOi0M_iPfczhDIT2u9rKOFTEbjd-c_qRYQAoTrX01jRYhE7v87aK36vXByH3q55yP33_e_0C7AgPURD6raZbyWJpUurDHKmeXbWaFA7CDfWzSIDOhCALl6yDWMZpqjbXCoyAyjDMTs2MbuHGvwFWBmuUNa3A2JDBE1ApASyUok1L1CdX21h5HWVtfUeddRTRYN4ln_NyzdM1_craNKRzf-I9f4k3Y7vxv8rbdMLdgw-a3YeuwYxjcgW9fXWDS1pkiRUY-2WpxUlcEb-GQSf__kYzmlUHu6_IVOXTRBxnhNYB6SXRFNJmVOFpdlDjAOyT912QfN1d5F75cytruwWZe5HYHiJAu7rep75wGG1rjS6uZzDDNbFElzXrg9yBITCfPjlVCTpKVsDTiJnG4SRA3SeDBi-GR01ab5KLOuz0kku6YqpIBDx48HVrd-YJJI53bYlElLBboAzsz4AE5p4-IYskDFXMP7rdQXc3HvTWfK9ci1kA8dEB58_WWfP6jkTnnKsKcugcve7ivJn7uMh9cuMwnsOUAn3w8mE524XpDBGl4mQ9hsy4X9hFcM7_qeVU-bjYzge-XDfy_9oSDdg
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=Validation+of+results+from+knowledge+discovery%3A+mass+density+as+a+predictor+of+breast+cancer&rft.jtitle=Journal+of+digital+imaging&rft.au=Woods%2C+Ryan+W&rft.au=Oliphant%2C+Louis&rft.au=Shinki%2C+Kazuhiko&rft.au=Page%2C+David&rft.date=2010-10-01&rft.issn=1618-727X&rft.eissn=1618-727X&rft.volume=23&rft.issue=5&rft.spage=554&rft_id=info:doi/10.1007%2Fs10278-009-9235-3&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0897-1889&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0897-1889&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0897-1889&client=summon