Online citations, reference lists, and bibliographies.
← Back to Search

A Multichannel Markov Random Field Framework For Tumor Segmentation With An Application To Classification Of Gene Expression-Based Breast Cancer Recurrence Risk

A. Ashraf, Sara Gavenonis, D. Daye, C. Mies, Mark Rosen, D. Kontos
Published 2013 · Computer Science, Medicine

Cite This
Download PDF
Analyze on Scholarcy
Share
We present a methodological framework for multichannel Markov random fields (MRFs). We show that conditional independence allows loopy belief propagation to solve a multichannel MRF as a single channel MRF. We use conditional mutual information to search for features that satisfy conditional independence assumptions. Using this framework we incorporate kinetic feature maps derived from breast dynamic contrast enhanced magnetic resonance imaging as observation channels in MRF for tumor segmentation. Our algorithm based on multichannel MRF achieves an receiver operating characteristic area under curve (AUC) of 0.97 for tumor segmentation when using a radiologist's manual delineation as ground truth. Single channel MRF based on the best feature chosen from the same pool of features as used by the multichannel MRF achieved a lower AUC of 0.89. We also present a comparison against the well established normalized cuts segmentation algorithm along with commonly used approaches for breast tumor segmentation including fuzzy C-means (FCM) and the more recent method of running FCM on enhancement variance features (FCM-VES). These previous methods give a lower AUC of 0.92, 0.88, and 0.60, respectively. Finally, we also investigate the role of superior segmentation in feature extraction and tumor characterization. Specifically, we examine the effect of improved segmentation on predicting the probability of breast cancer recurrence as determined by a validated tumor gene expression assay. We demonstrate that an support vector machine classifier trained on kinetic statistics extracted from tumors as segmented by our algorithm gives a significant improvement in distinguishing between women with high and low recurrence risk, giving an AUC of 0.88 as compared to 0.79, 0.76, 0.75, and 0.66 when using normalized cuts, single channel MRF, FCM, and FCM-VES, respectively, for segmentation.
This paper references
10.1214/10-AOS799
Kernel density estimation via diffusion
Z. Botev (2010)
10.1007/978-3-642-29361-0_14
Normalized Cut Segmentation of Thyroid Tumor Image Based on Fractional Derivatives
Jie Zhao (2012)
10.1200/JCO.2006.06.8080
Dynamic contrast-enhanced magnetic resonance imaging as an imaging biomarker.
N. Hylton (2006)
10.1109/ICCV.1999.790354
Segmentation using eigenvectors: a unifying view
Yair Weiss (1999)
Maximum Likelihood from Incomplete Data via the EM Algorithm
A. D. E. Altri (1977)
10.1200/JCO.2005.04.7985
Gene expression and benefit of chemotherapy in women with node-negative, estrogen receptor-positive breast cancer.
S. Paik (2006)
10.1016/b978-1-55860-247-2.50035-8
Induction of One-Level Decision Trees
Wayne Iba (1992)
10.1118/1.1695652
Computerized interpretation of breast MRI: investigation of enhancement-variance dynamics.
W. Chen (2004)
Fuzzy models for pattern recognition
J. Bezdek (1994)
10.1109/CVPR.1997.609407
Normalized cuts and image segmentation
Jianbo Shi (1997)
10.1118/1.3446799
Multilevel analysis of spatiotemporal association features for differentiation of tumor enhancement patterns in breast DCE-MRI.
S. Lee (2010)
10.1056/NEJMOA041588
A multigene assay to predict recurrence of tamoxifen-treated, node-negative breast cancer.
S. Paik (2004)
10.1007/s00330-003-2000-y
Invasive breast cancer: correlation of dynamic MR features with prognostic factors
B. Szabó (2003)
10.1109/TPAMI.2004.1262185
Spectral grouping using the Nystrom method
Charless C. Fowlkes (2004)
10.1214/AOMS/1177728190
Remarks on Some Nonparametric Estimates of a Density Function
M. Rosenblatt (1956)
10.1109/TMI.2003.819929
Normalized cuts in 3-D for spinal MRI segmentation
J. Carballido-Gamio (2004)
10.1016/j.artmed.2004.01.012
A novel kernelized fuzzy C-means algorithm with application in medical image segmentation
Dao-Qiang Zhang (2004)
10.1111/J.2517-6161.1989.TB01764.X
Exact Maximum A Posteriori Estimation for Binary Images
D. Greig (1989)
10.1007/978-3-642-23626-6_67
A Multichannel Markov Random Field Approach for Automated Segmentation of Breast Cancer Tumor in DCE-MRI Data Using Kinetic Observation Model
A. Ashraf (2011)
10.1109/ICCV.2003.1238308
Learning a classification model for segmentation
X. Ren (2003)
Convergent message passing algorithms - a unifying view
Talya Meltzer (2009)
10.1109/78.887045
Maximum-likelihood array processing in non-Gaussian noise with Gaussian mixtures
R. Kozick (2000)
10.1016/S1470-2045(09)70254-2
Calibration and discriminatory accuracy of prognosis calculation for breast cancer with the online Adjuvant! program: a hospital-based retrospective cohort study.
S. Mook (2009)
10.1109/CVPR.2004.204
Recovering human body configurations: combining segmentation and recognition
G. Mori (2004)
10.1109/FUZZY.1999.793060
MR brain image segmentation using fuzzy clustering
Ock-Kyung Yoon (1999)
10.1137/1114019
Non-Parametric Estimation of a Multivariate Probability Density
V. Y. Epanechnikov (1969)
10.1148/RADIOLOGY.217.3.R00DC07841
Breast masses with peripheral rim enhancement on dynamic contrast-enhanced MR images: correlation of MR findings with histologic features and expression of growth factors.
R. Matsubayashi (2000)
10.1109/TIT.2005.850085
Constructing free-energy approximations and generalized belief propagation algorithms
Jonathan S. Yedidia (2005)
10.1007/BF00133570
Snakes: Active contour models
M. Kass (2004)
A fuzzy c-means (FCM)-based approach for computerized segmentation of breast lesions in dynamic contrast-enhanced MR images.
W. Chen (2006)
10.1148/radiol.09090838
Cancerous breast lesions on dynamic contrast-enhanced MR images: computerized characterization for image-based prognostic markers.
N. Bhooshan (2010)
10.1109/icpr.2004.1334353
Unsupervised image segmentation using a simple MRF model with a new implementation scheme
Huawu Deng (2004)
Pattern Recognition and Machine Learning (Information Science and Statistics)
C. M. Bishop (2006)
10.1006/cviu.1995.1004
Active Shape Models-Their Training and Application
T. Cootes (1995)
10.1016/j.patrec.2009.08.010
Quasi-automatic initialization for parametric active contours
C. Tauber (2010)
10.1214/AOMS/1177704472
On Estimation of a Probability Density Function and Mode
E. Parzen (1962)
10.1016/j.neuroimage.2006.01.015
User-guided 3D active contour segmentation of anatomical structures: Significantly improved efficiency and reliability
P. Yushkevich (2006)
10.1145/1540276.1540286
Approximate inference, structure learning and feature estimation in Markov random fields: thesis abstract
P. Ravikumar (2008)
10.1118/1.2210568
Automatic identification and classification of characteristic kinetic curves of breast lesions on DCE-MRI.
W. Chen (2006)
10.1634/THEONCOLOGIST.12-6-631
Development and clinical utility of a 21-gene recurrence score prognostic assay in patients with early breast cancer treated with tamoxifen.
S. Paik (2007)
10.1016/J.ACRA.2005.08.035
A Fuzzy C-Means (FCM)-Based Approach for Computerized Segmentation of Breast Lesions in Dynamic Contrast-Enhanced MR Images1
W. Chen (2006)
10.1023/B:VISI.0000022288.19776.77
Efficient Graph-Based Image Segmentation
Pedro F. Felzenszwalb (2004)
10.1007/s10549-008-9977-5
Smoking and the risk of breast cancer in BRCA1 and BRCA2 carriers: an update
O. Ginsburg (2008)
10.1109/42.906424
Segmentation of brain MR images through a hidden Markov random field model and the expectation-maximization algorithm
Y. Zhang (2001)
10.1109/CEC.2007.4425049
MRI brain image segmentation by fuzzy symmetry based genetic clustering technique
S. Saha (2007)
10.1109/ICCV.2005.112
Guiding model search using segmentation
G. Mori (2005)



This paper is referenced by
10.1109/SPACES.2018.8316341
Unsupervised learning algorithms for MRI brain tumor segmentation
B. Srinivas (2018)
10.1109/TMI.2018.2865671
Hierarchical Convolutional Neural Networks for Segmentation of Breast Tumors in MRI With Application to Radiogenomics
J. Zhang (2019)
10.1007/S12652-020-02534-6
Optimized radial basis neural network for classification of breast cancer images
G. Rajathi (2020)
10.1016/j.acra.2019.09.012
Breast Cancer Radiogenomics: Current Status and Future Directions.
L. Grimm (2020)
Efficient Breast Cancer Classification using Improved Artificial Immune Recognize System with Csonn
D. Thuthi Sarabai (2016)
The Use of Textural Kinetic Habitats to Mine Diagnostic Information from DCE MR Images of Breast Tumors
B. Chaudhury (2015)
10.5530/SRP.2018.1.3
The Effect of Thermography on Breast Cancer Detection-A Survey
P. Pavithra (2018)
10.1080/24699322.2017.1389398
A segmentation of brain MRI images utilizing intensity and contextual information by Markov random field
Mingsheng Chen (2017)
10.14569/IJACSA.2017.080917
Effectiveness of Existing CAD-Based Research Work towards Screening Breast Cancer
Vidya Kattepura (2017)
DETECTION OF BREAST CANCER USING CONTINUOUS WAVELET TRANSFORM AND SUPPORT VECTOR MACHINE
(2016)
10.5120/cae2018652760
Novel Framework for Breast Cancer Classification for Retaining Computational Efficiency and Precise Diagnosis
K. Vidya (2018)
10.1002/jmri.25870
Background, current role, and potential applications of radiogenomics
K. Pinker (2018)
10.1016/j.media.2014.12.001
Automated localization of breast cancer in DCE-MRI
A. Gubern-Mérida (2015)
10.1155/2014/978373
A New Kernel-Based Fuzzy Level Set Method for Automated Segmentation of Medical Images in the Presence of Intensity Inhomogeneity
M. Rastgarpour (2014)
10.1007/s11548-017-1530-8
Validation of a method for retroperitoneal tumor segmentation
Cristina Suárez-Mejías (2017)
10.1109/TMI.2019.2937458
Lung 4D CT Image Registration Based on High-Order Markov Random Field
P. Xue (2020)
10.1371/journal.pone.0193871
Radiogenomics analysis identifies correlations of digital mammography with clinical molecular signatures in breast cancer
Jose-Gerardo Tamez-Peña (2018)
Automated analysis of magnetic resonance imaging of the breast
Angel Mérida (2015)
10.1002/jmri.25116
Breast MRI radiogenomics: Current status and research implications
L. Grimm (2016)
10.1109/INDIN.2015.7281793
Introduction of SVM algorithms and recent applications about fault diagnosis and other aspects
Z. Yin (2015)
Deep Learning Based Anomaly Detection
L. Sun (2018)
10.1148/radiol.14132641
Radiogenomic analysis of breast cancer: luminal B molecular subtype is associated with enhancement dynamics at MR imaging.
M. Mazurowski (2014)
10.1109/TBME.2015.2395812
Pharmacokinetic Tumor Heterogeneity as a Prognostic Biomarker for Classifying Breast Cancer Recurrence Risk
Majid Mahrooghy (2015)
10.1016/j.jacr.2015.04.019
Radiogenomics: what it is and why it is important.
M. Mazurowski (2015)
10.1109/BIBM.2013.6732583
A 3D segmentation framework for an accurate extraction of the spongy and cortical bones from the MRI data
S. M. Moghadas (2013)
Efficient Breast Cancer Classification Using Improved Fuzzy Cognitive Maps with Csonn
D. Sarabai (2016)
10.1016/j.bspc.2016.12.001
Automatic pharynx and larynx cancer segmentation framework (PLCSF) on contrast enhanced MR images
T. Doshi (2017)
10.1002/ima.22081
Brain tumor severity analysis using modified multi‐texton histogram and hybrid kernel SVM
A. Jayachandran (2014)
10.1142/S1793545818500141
An image segmentation framework for extracting tumors from breast magnetic resonance images
L. Sun (2018)
10.1118/1.4955435
Interobserver variability in identification of breast tumors in MRI and its implications for prognostic biomarkers and radiogenomics.
Ashirbani Saha (2016)
10.1109/PUNECON.2018.8745420
Deep Learning for Cancer Cell Detection and Segmentation: A Survey
Priyank Hajela (2018)
10.1002/ima.22467
Breast cancer diagnosis from mammographic images using optimized feature selection and neural network architecture
Ekta Shivhare (2020)
See more
Semantic Scholar Logo Some data provided by SemanticScholar