Computerized three-class classification of MRI-based prognostic markers for breast cancer

The purpose of this study is to investigate whether computerized analysis using three-class Bayesian artificial neural network (BANN) feature selection and classification can characterize tumor grades (grade 1, grade 2 and grade 3) of breast lesions for prognostic classification on DCE-MRI. A database of 26 IDC grade 1 lesions, 86 IDC grade 2 lesions and 58 IDC grade 3 lesions was collected. The computer automatically segmented the lesions, and kinetic and morphological lesion features were automatically extracted. The discrimination tasks-grade 1 versus grade 3, grade 2 versus grade 3, and grade 1 versus grade 2 lesions-were investigated. Step-wise feature selection was conducted by three-class BANNs. Classification was performed with three-class BANNs using leave-one-lesion-out cross-validation to yield computer-estimated probabilities of being grade 3 lesion, grade 2 lesion and grade 1 lesion. Two-class ROC analysis was used to evaluate the performances. We achieved AUC values of 0.80 ± 0.05, 0.78 ± 0.05 and 0.62 ± 0.05 for grade 1 versus grade 3, grade 1 versus grade 2, and grade 2 versus grade 3, respectively. This study shows the potential for (1) applying three-class BANN feature selection and classification to CADx and (2) expanding the role of DCE-MRI CADx from diagnostic to prognostic classification in distinguishing tumor grades.

[1]  Wendy B DeMartini,et al.  Breast MRI for cancer detection and characterization: a review of evidence-based clinical applications. , 2008, Academic radiology.

[2]  M L Giger,et al.  Computerized analysis of breast lesions in three dimensions using dynamic magnetic-resonance imaging. , 1998, Medical physics.

[3]  M. Giger,et al.  Volumetric texture analysis of breast lesions on contrast‐enhanced magnetic resonance images , 2007, Magnetic resonance in medicine.

[4]  Joseph M. Reinhardt,et al.  Classification of breast MRI lesions using a backpropagation neural network (BNN) , 2004, 2004 2nd IEEE International Symposium on Biomedical Imaging: Nano to Macro (IEEE Cat No. 04EX821).

[5]  M. Giger,et al.  Cancerous breast lesions on dynamic contrast-enhanced MR images: computerized characterization for image-based prognostic markers. , 2010, Radiology.

[6]  Donald E. Henson,et al.  Relation of tumor size, lymph node status, and survival in 24,740 breast cancer cases , 1989 .

[7]  A Horsman,et al.  Observer variability in the interpretation of contrast enhanced MRI of the breast. , 1996, The British journal of radiology.

[8]  Maryellen L. Giger,et al.  Evaluation of clinical breast MR imaging performed with prototype computer-aided diagnosis breast MR imaging workstation: reader study. , 2011, Radiology.

[9]  I. Ellis,et al.  Pathological prognostic factors in breast cancer. I. The value of histological grade in breast cancer: experience from a large study with long-term follow-up. , 2002, Histopathology.

[10]  Maryellen L. Giger,et al.  A Fuzzy C-Means (FCM)-Based Approach for Computerized Segmentation of Breast Lesions in Dynamic Contrast-Enhanced MR Images1 , 2006 .

[11]  Darrin C. Edwards,et al.  Estimating three-class ideal observer decision variables for computerized detection and classification of mammographic mass lesions. , 2003, Medical physics.

[12]  L. Tabár,et al.  Tumour development, histology and grade of breast cancers: Prognosis and progression , 1996, International journal of cancer.

[13]  Steinar Lundgren,et al.  Predicting survival and early clinical response to primary chemotherapy for patients with locally advanced breast cancer using DCE‐MRI , 2009, Journal of magnetic resonance imaging : JMRI.

[14]  J. Folkman,et al.  Tumor angiogenesis and metastasis--correlation in invasive breast carcinoma. , 1991, The New England journal of medicine.

[15]  C A Roe,et al.  Statistical Comparison of Two ROC-curve Estimates Obtained from Partially-paired Datasets , 1998, Medical decision making : an international journal of the Society for Medical Decision Making.

[16]  Heinz-Otto Peitgen,et al.  Computer assistance for MR based diagnosis of breast cancer: Present and future challenges , 2007, Comput. Medical Imaging Graph..

[17]  C. Kuhl,et al.  Dynamic breast MR imaging: are signal intensity time course data useful for differential diagnosis of enhancing lesions? , 1999, Radiology.

[18]  C E Metz,et al.  Some practical issues of experimental design and data analysis in radiological ROC studies. , 1989, Investigative radiology.

[19]  J. Coebergh,et al.  An overview of prognostic factors for long-term survivors of breast cancer , 2007, Breast Cancer Research and Treatment.

[20]  M. Giger,et al.  A fuzzy c-means (FCM)-based approach for computerized segmentation of breast lesions in dynamic contrast-enhanced MR images. , 2006, Academic radiology.

[21]  P Abdolmaleki,et al.  Neural network analysis of breast cancer from MRI findings. , 1997, Radiation medicine.

[22]  I. Ellis,et al.  Pathological prognostic factors in breast cancer. I. The value of histological grade in breast cancer: experience from a large study with long-term follow-up. , 2002, Histopathology.

[23]  Jurgen J Fütterer,et al.  Variability in the Description of Morphologic and Contrast Enhancement Characteristics of Breast Lesions onMagnetic Resonance Imaging , 2005, Investigative radiology.

[24]  H. V. Trees.  Detection, Estimation, And Modulation Theory , 2001 .

[25]  J. Peterse,et al.  The impact of preoperative MRI on breast-conserving surgery of invasive cancer: a comparative cohort study , 2009, Breast Cancer Research and Treatment.

[26]  P Aspelin,et al.  Contrast-enhanced MR imaging as a prognostic indicator of breast cancer , 1998, Acta radiologica.

[27]  K. Doi,et al.  Potential of computer-aided diagnosis to reduce variability in radiologists' interpretations of mammograms depicting microcalcifications. , 2001, Radiology.

[28]  Robert M. Nishikawa,et al.  Estimation of three-class ideal observer decision functions with a Bayesian artificial neural network , 2002, SPIE Medical Imaging.

[29]  Peter Gibbs,et al.  Breast lesion analysis of shape technique: Semiautomated vs. manual morphological description , 2006, Journal of magnetic resonance imaging : JMRI.

[30]  Antanas Verikas,et al.  Feature selection with neural networks , 2002, Pattern Recognit. Lett..

[31]  M. Giger,et al.  Computerized interpretation of breast MRI: investigation of enhancement-variance dynamics. , 2004, Medical physics.

[32]  C. J. Huberty,et al.  Applied Discriminant Analysis , 1994 .

[33]  N. Hylton,et al.  Diagnostic architectural and dynamic features at breast MR imaging: multicenter study. , 2006, Radiology.

[34]  L. Turnbull,et al.  Textural analysis of contrast‐enhanced MR images of the breast , 2003, Magnetic resonance in medicine.

[35]  N. Hylton,et al.  Magnetic resonance imaging of the breast prior to biopsy. , 2004, JAMA.

[36]  Tibor Tot,et al.  Invasive breast cancer: correlation of dynamic MR features with prognostic factors , 2003, European Radiology.

[37]  D. Mackay,et al.  Bayesian methods for adaptive models , 1992 .

[38]  Lina Arbash Meinel,et al.  Breast MRI lesion classification: Improved performance of human readers with a backpropagation neural network computer‐aided diagnosis (CAD) system , 2007, Journal of magnetic resonance imaging : JMRI.

[39]  Maryellen L. Giger,et al.  Ideal observer approximation using Bayesian classification neural networks , 2001, IEEE Transactions on Medical Imaging.

[40]  Jane Warwick,et al.  Time‐dependent effects on survival in breast carcinoma , 2004, Cancer.

[41]  Megumi Jinguji,et al.  Rim enhancement of breast cancers on contrast-enhanced MR imaging: Relationship with prognostic factors , 2006, Breast cancer.

[42]  M. Giger,et al.  Anniversary paper: History and status of CAD and quantitative image analysis: the role of Medical Physics and AAPM. , 2008, Medical physics.

[43]  M. Giger,et al.  Automatic identification and classification of characteristic kinetic curves of breast lesions on DCE-MRI. , 2006, Medical physics.

[44]  D. Vanel.  The American College of Radiology (ACR) Breast Imaging and Reporting Data System (BI-RADS): a step towards a universal radiological language? , 2007, European journal of radiology.

[45]  C. Carter,et al.  Relation of tumor size, lymph node status, and survival in 24,740 breast cancer cases , 1989, Cancer.

[46]  A. Jemal,et al.  Cancer Statistics, 2010 , 2010, CA: a cancer journal for clinicians.

[47]  L. Liberman,et al.  Observer variability and applicability of BI-RADS terminology for breast MR imaging: invasive carcinomas as focal masses. , 2001, AJR. American journal of roentgenology.

[48]  A Horsman,et al.  Dynamic MR imaging of invasive breast cancer: correlation with tumour grade and other histological factors. , 1997, The British journal of radiology.

[49]  H. Lehr,et al.  Dynamic MR imaging of breast lesions: correlation with microvessel distribution pattern and histologic characteristics of prognosis. , 2006, Radiology.

[50]  D. Ikeda,et al.  Mammographic characteristics of 115 missed cancers later detected with screening mammography and the potential utility of computer-aided detection. , 2001, Radiology.

[51]  W Vach,et al.  Vascular grading of angiogenesis: prognostic significance in breast cancer , 2000, British Journal of Cancer.

[52]  D. Hanahan,et al.  Induction of angiogenesis during the transition from hyperplasia to neoplasia , 1989, Nature.

[53]  Martin O. Leach,et al.  The UK MARIBS Breast Screening Study: Evaluation of radiological features for breast tumour classification in clinical screening with machine learning methods , 2005, Artif. Intell. Medicine.

[54]  Harry L. Van Trees,et al.  Detection, Estimation, and Modulation Theory, Part I , 1968 .

[55]  Richard A. Johnson,et al.  Applied Multivariate Statistical Analysis , 1983 .