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

Comparison Of Breast MRI Tumor Classification Using Human-Engineered Radiomics, Transfer Learning From Deep Convolutional Neural Networks, And Fusion Method

H. M. Whitney, H. Li, Y. Ji, Peifang Liu, M. Giger
Published 2020 · Computer Science

Cite This
Download PDF
Analyze on Scholarcy
Share
Digital image-based signatures of breast tumors may ultimately contribute to the design of patient-specific breast cancer diagnostics and treatments. Beyond traditional human-engineered computer vision methods, tumor classification methods using transfer learning from deep convolutional neural networks (CNNs) are actively under development. This article will first discuss our progress in using CNN-based transfer learning to characterize breast tumors for various diagnostic, prognostic, or predictive image-based tasks across multiple imaging modalities, including mammography, digital breast tomosynthesis, ultrasound (US), and magnetic resonance imaging (MRI), compared to both human-engineered feature-based radiomics and fusion classifiers created through combination of such features. Second, a new study is presented that reports on a comprehensive comparison of the classification performances of features derived from human-engineered radiomic features, CNN transfer learning, and fusion classifiers for breast lesions imaged with MRI. These studies demonstrate the utility of transfer learning for computer-aided diagnosis and highlight the synergistic improvement in classification performance using fusion classifiers.
This paper references
10.1016/S0001-2998(78)80014-2
Basic principles of ROC analysis.
C. Metz (1978)
10.1117/1.JMI.3.3.034501
Digital mammographic tumor classification using transfer learning from deep convolutional neural networks
B. Huynh (2016)
10.1118/1.598345
Computerized analysis of breast lesions in three dimensions using dynamic magnetic-resonance imaging.
K. G. Gilhuijs (1998)
10.21147/j.issn.1000-9604.2018.04.06
A radiomic nomogram based on an apparent diffusion coefficient map for differential diagnosis of suspicious breast findings
B. Hu (2018)
ACR BI-RADS Atlas, Breast Imaging and Data System
C. J. D’Orsi (2013)
10.1371/journal.pone.0187501
Using quantitative features extracted from T2-weighted MRI to improve breast MRI computer-aided diagnosis (CAD)
C. Gallego-Ortiz (2017)
10.1002/mp.12453
A deep feature fusion methodology for breast cancer diagnosis demonstrated on three imaging modality datasets
Natalia Antropova (2017)
10.3322/caac.21551
Cancer statistics, 2019
R. Siegel (2019)
10.1002/jmri.26556
Role of texture analysis in breast MRI as a cancer biomarker: A review
Rhea D Chitalia (2019)
10.1002/mrm.21347
Volumetric texture analysis of breast lesions on contrast‐enhanced magnetic resonance images
W. Chen (2007)
10.1118/1.597177
Computerized detection of clustered microcalcifications in digital mammograms using a shift-invariant artificial neural network.
W. Zhang (1994)
10.1097/00004424-198903000-00012
Some practical issues of experimental design and data analysis in radiological ROC studies.
C. Metz (1989)
10.1016/j.acra.2018.06.019
Transfer Learning From Convolutional Neural Networks for Computer-Aided Diagnosis: A Comparison of Digital Breast Tomosynthesis and Full-Field Digital Mammography.
Kayla R. Mendel (2019)
Very Deep Convolutional Networks for Large-Scale Image Recognition
K. Simonyan (2015)
10.1148/radiol.10091394
BI-RADS data should not be used to estimate ROC curves.
Y. Jiang (2010)
10.1145/3065386
ImageNet classification with deep convolutional neural networks
A. Krizhevsky (2017)
10.1016/j.acra.2017.12.025
Using Convolutional Neural Networks for Enhanced Capture of Breast Parenchymal Complexity Patterns Associated with Breast Cancer Risk.
A. Gastounioti (2018)
10.1118/1.1695652
Computerized interpretation of breast MRI: investigation of enhancement-variance dynamics.
W. Chen (2004)
A fuzzy c-means (FCM)-based approach for computerized segmentation of breast lesions in dynamic contrast-enhanced MR images.
W. Chen (2006)
10.1002/mp.13361
Breast mass classification in sonography with transfer learning using a deep convolutional neural network and color conversion
Michal Byra (2019)
10.1002/mp.13264
Deep learning in medical imaging and radiation therapy.
B. Sahiner (2019)
10.1148/radiol.14132641
Radiogenomic analysis of breast cancer: luminal B molecular subtype is associated with enhancement dynamics at MR imaging.
M. Mazurowski (2014)
10.1002/jmri.26732
Characterization of Sub‐1 cm Breast Lesions Using Radiomics Analysis
P. Gibbs (2019)
10.1146/annurev-bioeng-071812-152416
Breast image analysis for risk assessment, detection, diagnosis, and treatment of cancer.
M. Giger (2013)
10.1002/jmri.25661
Identifying relations between imaging phenotypes and molecular subtypes of breast cancer: Model discovery and external validation
J. Wu (2017)
10.1148/radiol.2018181352
Radiomic versus Convolutional Neural Networks Analysis for Classification of Contrast-enhancing Lesions at Multiparametric Breast MRI.
D. Truhn (2019)
10.1117/1.JMI.4.4.041304
Deep learning in breast cancer risk assessment: evaluation of convolutional neural networks on a clinical dataset of full-field digital mammograms
H. Li (2017)
10.1002/jmri.25606
Prediction of malignancy by a radiomic signature from contrast agent‐free diffusion MRI in suspicious breast lesions found on screening mammography.
S. Bickelhaupt (2017)
10.3322/caac.21552
Artificial intelligence in cancer imaging: Clinical challenges and applications
W. Bi (2019)
10.1007/s10278-012-9452-z
Computerized Analysis of Mammographic Parenchymal Patterns on a Large Clinical Dataset of Full-Field Digital Mammograms: Robustness Study with Two High-Risk Datasets
Hui Li (2012)
10.1117/1.JMI.6.1.011002
Breast lesion classification based on dynamic contrast-enhanced magnetic resonance images sequences with long short-term memory networks.
Natalia Antropova (2019)
10.1371/journal.pone.0143308
Identifying Triple-Negative Breast Cancer Using Background Parenchymal Enhancement Heterogeneity on Dynamic Contrast-Enhanced MRI: A Pilot Radiomics Study
J. Wang (2015)
10.1158/1078-0432.CCR-18-1115
Deep Learning to Distinguish Recalled but Benign Mammography Images in Breast Cancer Screening
Sarah S. Aboutalib (2018)
10.1117/1.JMI.5.1.014503
Use of clinical MRI maximum intensity projections for improved breast lesion classification with deep convolutional neural networks
Natalia Antropova (2018)
Prediction of malignancy by a radiomic signature from contrast agent-free diffusion MRI in suspicious breast lesions found on screening mammography
S. Bickelhaupt (2017)
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)
10.1016/j.acra.2018.04.019
Additive Benefit of Radiomics Over Size Alone in the Distinction Between Benign Lesions and Luminal A Cancers on a Large Clinical Breast MRI Dataset.
H. M. Whitney (2019)
10.1118/1.2210568
Automatic identification and classification of characteristic kinetic curves of breast lesions on DCE-MRI.
W. Chen (2006)
10.1109/CVPRW.2009.5206848
ImageNet: A large-scale hierarchical image database
J. Deng (2009)
10.1088/0031-9155/61/13/R150
Applications and limitations of radiomics.
S. Yip (2016)



This paper is referenced by
Semantic Scholar Logo Some data provided by SemanticScholar