Beyond breast density: a review on the advancing role of parenchymal texture analysis in breast cancer risk assessment

Gastounioti, Aimilia; Conant, Emily F.; Kontos, Despina

doi:10.1186/s13058-016-0755-8

Table 3 Breast cancer prediction capacity of automated characterization of the parenchymal patterns

From: Beyond breast density: a review on the advancing role of parenchymal texture analysis in breast cancer risk assessment

Study		Dataset			Model	Discriminatory capacity (AUC)
Year	Participating Institutions	A	B	m		^$Texture	^$PD	^$Texture + PD	^Texture	^PD	^Texture + PD
Distinguishing between cancer cases and healthy women
Wu et al. (2008) [76]	University of Michigan	128^C	549	No	LDA^CV	0.73
Manduca et al. (2009) [66]	Mayo Clinic, Moffitt	246^P	522	Yes	LR^CV	[0.58, 0.60]	0.58		Age, BMI
Manduca et al. (2009) [66]	Mayo Clinic, Moffitt	246^P	522	Yes	LR^CV	[0.58, 0.60]	0.58		[0.61, 0.62]	0.60	[0.62, 0.63]
Wei et al. (2011) [73]	University of Michigan	136^C	246	No	LDA	0.74*	0.61	0.76	Age, BMI, family history of breast cancer, #of previous breast biopsies
Wei et al. (2011) [73]		136^C	246	No	LDA	0.74*	0.61	0.76			0.78
Nielsen et al. (2011) [61]	University of Copenhagen, Nordic Bioscience, Delft University of Technology, RadboudUMC, Mayo Clinic	245^P	250	No	LR^CV	0.63	0.60	0.66*
Brandt et al. (2011) [74]	University of Copenhagen, RadboudUMC, Synarc Imaging Technologies	245^P	245	Yes	kNN^CV	0.63	0.56
Häberle et al. (2012) [56]	Erlangen University Hospital, Fraunhofer Institute for Integrated Circuits IIS, IMPRS, UCLA	864^C	418	Yes	LR^CV	0.75	0.51	0.75	Age, BMI, family history of breast cancer, parity, age at first term pregnancy
Häberle et al. (2012) [56]		864^C	418	Yes	LR^CV	0.75	0.51	0.75	0.79	0.66	0.79
Li et al. (2012) [84]	University of Chicago	75^C	328	No	BANN^CV	0.73
Li et al. (2012) [84]	University of Chicago	67^C	268	Yes	BANN^CV	0.70
Chen et al. (2014) [75]	University of Manchester	50^C	50	No	LR	0.71	0.62	0.68
Nielsen et al. (2014) [64]	UCPH, Nordic Bioscience, Biomediq, RadboudUMC, Mayo Clinic	245^P	250	No	LR^CV				Age, BMI, menopause, hormonal use
Nielsen et al. (2014) [64]	UCPH, Nordic Bioscience, Biomediq, RadboudUMC, Mayo Clinic	245^P	250	No	LR^CV				0.60	0.63	0.66
Nielsen et al. (2014) [64]	UCPH, Nordic Bioscience, Biomediq, RadboudUMC, Mayo Clinic	226^C	442	Yes	LR^CV				Age, BMI, menopause, hormonal use
Nielsen et al. (2014) [64]	UCPH, Nordic Bioscience, Biomediq, RadboudUMC, Mayo Clinic	226^C	442	Yes	LR^CV				0.61	0.63
Li et al. (2014) [71]	University of Chicago	67^C	268	Yes	BANN^CV	0.70*	0.57	0.68
Karemore et al. (2014) [90]	UCPH, RadboudUMC	245^P	250	Yes	kNN^CV	0.59
Zheng et al. (2015) [51]	University of Pennsylvania	106^C	318	Yes	LR^CV	0.85*	0.59	0.86
Sun et al. (2015) [53]	University of Texas, China Northeastern University, University of Oklahoma, TTUHS, Guiyang Medical University	141^P	199	No	SVM^CV	0.73			Age, BMI, family history of breast cancer, hormonal use, age at first term pregnancy
Sun et al. (2015) [53]		141^P	199	No	SVM^CV	0.73			0.77
Tan et al. (2015) [77]	University of Texas, University of Oklahoma, University of Pittsburgh				ANN^CV				age
Tan et al. (2015) [77]		812^P	1084	No	ANN^CV	0.71			0.78
Tan et al. (2015) [78]	University of Oklahoma, University of Pittsburgh	430^P	440	No	ANN^CV	[0.64, 0.73]
Predicting the risk of carrying a high-risk genetic mutation
Huo et al. (2000) [80]	University of Chicago	15	143	No	LDA	[0.59, 0.82]
Huo et al. (2000) [80]	University of Chicago	15	30	Yes	LDA	[0.53, 0.87]
Huo et al. (2002) [55]	University of Chicago, University of Pennsylvania	30	142	No	LDA	0.91
Huo et al. (2002) [55]	University of Chicago, University of Pennsylvania	30	60	Yes	LDA	0.92
Li et al. (2004) [54]	University of Chicago, University of Pennsylvania	30	60	Yes	LDA^CV	[0.69, 0.92]
Li et al. (2005) [81]	University of Chicago	30	142	No	ROCA	[0.66, 0.86]
Li et al. (2005) [81]	University of Chicago	30	60	Yes	ROCA	[0.67, 0.86]
Li et al. (2007) [82]	University of Chicago	30	142	No	ROCA^CV	[0.74, 0.93]
Li et al. (2007) [82]	University of Chicago	30	60	Yes	ROCA^CV	[0.77, 0.91]
Li et al. (2008) [83]	University of Chicago	30	142	No	ROCA	0.90
Li et al. (2008) [83]	University of Chicago	30	60	Yes	ROCA	0.89
Li et al. (2012) [84]	University of Chicago	53	328	No	BANN^CV	0.82
Li et al. (2012) [84]	University of Chicago	34	136	Yes	BANN^CV	0.81
Li et al. (2014) [71]	University of Chicago	34	136	Yes	BANN^CV	0.81*	0.53	0.81
Gierach et al. (2014) [85]	University of Chicago	137	100	No	BANN^CV	0.68	0.59	0.72
Gierach et al. (2014) [85]	University of Chicago, NCI-NIH, Washington Radiology Associates, Genentech, USUHS, UCL, WRNMC, Westat Inc.	126	89	Yes	BANN^CV	0.71	0.55	0.72

Area under the ROC curve (AUC) achieved by risk assessment models when fed with mammographic texture and/or density measures
IMPRS International Max Planck Research School for Optics and Imaging, Moffitt Moffitt Cancer Center and Research Institute, NCI-NIH National Cancer Institute, National Institutes of Health, RadboudUMC Radboud University Nijmegen Medical Centre, TTUHS Texas Tech University Health Sciences, UCL University College London, UCLA University of California at Los Angeles, USUHS Uniformed Services University of the Health Sciences, WRNMC Walter Reed National Military Medical Center
Dataset: A cancer cases (^Pprior unaffected images, ^Cimages from the contralateral, unaffected, breast at the time of cancer diagnosis) or other high-risk population (i.e., BRCA1/2 carriers), B controls, m matched subgroups; Model: LDA Linear Discriminant Analysis, LR Logistic Regression, kNN k-nearest neighbors, BANN Bayesian Artificial Neural Network, ANN Artificial Neural Network, ROCA Receiver Operating Characteristic Analysis. PD percent density. ^CVcross-validated models; ^$unadjusted models; ^models adjusted for established risk factors; *statistically significant from ^$PD at < 0.05

Back to article page

ISSN: 1465-542X

Contact us

Submission enquiries: journalsubmissions@springernature.com

Breast Cancer Research

Contact us