Automatic detection of 3D breast lesions in dynamic contrast-enhanced MR images

Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is being increasingly used in the clinic as an adjunct to x-ray mammography and ultrasound for the detection and characterisation of breast cancer. The technique involves acquiring T1-weighted volume images of one or both breasts before and at several time points after the injection of a contrast agent. Interpretation of this 4D data is a complex task for the radiologist and is becoming more so with developments of higher fieldstrength MRI scanners and associated increases in spatial, temporal and contrast information. Several commercial computer-assisted detection/diagnosis (CAD) systems for breast MRI have been developed in recent years to help radiologists with this task. However, these systems at present fall short of automatically locating and classifying malignant lesions. It is not surprising, therefore, that the efficacy of breast MRI CAD remains an open question. A recent review concluded that breast MRI CAD needs to be based on “quantitative features extracted preferably from the automatically segmented 3D lesion”. This thesis deals specifically with the problem of automatically segmenting (i.e. delineating) 3D lesions in breast DCE-MRI data. In particular it reviews existing approaches and proffers a novel approach based on voxel-wise classification. The new approach involves assigning a “suspiciousness” score to each voxel using features extracted from its time series, and then computing the spatial co-occurrence of this score in a neighbourhood including the voxel. The thesis also presents an empirical evaluation of the efficacy of this technique versus a competing method based on multispectral co-occurrence. The evaluation was performed on real clinical breast MRI data for 32 subjects. The results demonstrate that the proposed method achieves a comparable level of performance (AUC of 0.8989± 0.0021 versus AUC of 0.9330± 0.0018). However the advantage of the proposed method over the competing method is that it does not require subjective specification of feature ranges for computing co-occurrence.

[1]  R. R. Hocking.  The analysis and selection of variables in linear regression , 1976 .

[2]  Gunnar Rätsch,et al.  An introduction to kernel-based learning algorithms , 2001, IEEE Trans. Neural Networks.

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

[4]  Marcia Koomen.  Practical MR mammography , 2005 .

[5]  Stuart Crozier,et al.  Two Non-linear Parametric Models of Contrast Enhancement for DCE-MRI of the Breast Amenable to Fitting Using Linear Least Squares , 2010, 2010 International Conference on Digital Image Computing: Techniques and Applications.

[6]  Anna N. Vioral,et al.  Breast Cancer Overview , 2007, Plastic surgical nursing : official journal of the American Society of Plastic and Reconstructive Surgical Nurses.

[7]  Lia Morra,et al.  A fully automatic lesion detection method for DCE-MRI fat-suppressed breast images , 2009, Medical Imaging.

[8]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[9]  R. Slutsky,et al.  Tissue distribution and magnetic resonance spin lattice relaxation effects of gadolinium-DTPA. , 1985, Radiology.

[10]  Johan Löfhede,et al.  The EEG of the neonatal brain : classification of background activity , 2009 .

[11]  Chih-Jen Lin,et al.  Combining SVMs with Various Feature Selection Strategies , 2006, Feature Extraction.

[12]  Ron Kohavi,et al.  A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection , 1995, IJCAI.

[13]  Melinda J. Staiger,et al.  Breast cancer measurements with magnetic resonance imaging, ultrasonography, and mammography , 2005, Breast Cancer Research and Treatment.

[14]  D. Hudson.  Fitting Segmented Curves Whose Join Points Have to Be Estimated , 1966 .

[15]  Thierry Denoeux,et al.  A k-nearest neighbor classification rule based on Dempster-Shafer theory , 1995, IEEE Trans. Syst. Man Cybern..

[16]  Bradley D. Clymer,et al.  Multispectral Co-Occurrence With Three Random Variables in Dynamic Contrast Enhanced Magnetic Resonance Imaging of Breast Cancer , 2008, IEEE Transactions on Medical Imaging.

[17]  Peter E. Hart,et al.  Nearest neighbor pattern classification , 1967, IEEE Trans. Inf. Theory.

[18]  S. V. Sree,et al.  Breast imaging: A survey. , 2011, World journal of clinical oncology.

[19]  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.

[20]  Robert M. Nishikawa,et al.  Current status and future directions of computer-aided diagnosis in mammography , 2007, Comput. Medical Imaging Graph..

[21]  Anil K. Jain,et al.  Statistical Pattern Recognition: A Review , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[22]  Sang Ho Lee,et al.  Texture analysis of lesion perfusion volumes in dynamic contrast-enhanced breast MRI , 2008, 2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[23]  A. Padhani.  Dynamic contrast‐enhanced MRI in clinical oncology: Current status and future directions , 2002, Journal of magnetic resonance imaging : JMRI.

[24]  L. Schwartz,et al.  Malignant lesion segmentation in contrast-enhanced breast MR images based on the marker-controlled watershed. , 2009, Medical physics.

[25]  J O Barentsz,et al.  Breast tumors: comparative accuracy of MR imaging relative to mammography and US for demonstrating extent. , 1995, Radiology.

[26]  Johannes Buurman,et al.  Robust segmentation of mass‐lesions in contrast‐enhanced dynamic breast MR images , 2010, Journal of magnetic resonance imaging : JMRI.

[27]  S. Sinha,et al.  Recent advances in breast MRI and MRS , 2009, NMR in biomedicine.

[28]  Chih-Jen Lin,et al.  A Practical Guide to Support Vector Classication , 2008 .

[29]  Wei Huang,et al.  Detection of breast malignancy: diagnostic MR protocol for improved specificity. , 2004, Radiology.

[30]  Matthijs Oudkerk,et al.  Computer-aided detection in breast MRI: a systematic review and meta-analysis , 2011, European Radiology.

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

[32]  Tahsin Kurc,et al.  Malignant‐lesion segmentation using 4D co‐occurrence texture analysis applied to dynamic contrast‐enhanced magnetic resonance breast image data , 2007, Journal of magnetic resonance imaging : JMRI.

[33]  C. Mathers,et al.  Estimates of worldwide burden of cancer in 2008: GLOBOCAN 2008 , 2010, International journal of cancer.

[34]  Andrew James Heinrich Mehnert.  Image analysis for the study of chromatin distribution in cell nuclei with application to cervical cancer screening , 2003 .

[35]  G L Wolf,et al.  Relaxation of water protons in the intra‐ and extracellular regions of blood containing Gd(DTPA) , 1986, Magnetic resonance in medicine.

[36]  D B Plewes,et al.  Comparison of breast magnetic resonance imaging, mammography, and ultrasound for surveillance of women at high risk for hereditary breast cancer. , 2001, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[37]  Andrew P. Bradley,et al.  The use of the area under the ROC curve in the evaluation of machine learning algorithms , 1997, Pattern Recognit..

[38]  Shigeo Abe DrEng.  Pattern Classification , 2001, Springer London.

[39]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[40]  David W. Hosmer,et al.  Applied Logistic Regression , 1991 .

[41]  Yoshua Bengio,et al.  Pattern Recognition and Neural Networks , 1995 .

[42]  Anke Meyer-Bäse,et al.  Computer-aided diagnosis and visualization based on clustering and independent component analysis for breast MRI , 2008, 2008 15th IEEE International Conference on Image Processing.

[43]  M V Knopp,et al.  Dynamic contrast-enhanced magnetic resonance imaging in oncology. , 2001, Topics in magnetic resonance imaging : TMRI.

[44]  Lucila Ohno-Machado,et al.  Logistic regression and artificial neural network classification models: a methodology review , 2002, J. Biomed. Informatics.

[45]  David M Catarious,et al.  Incorporation of an iterative, linear segmentation routine into a mammographic mass CAD system. , 2004, Medical physics.

[46]  Peter Devilee,et al.  Pathology and Genetics of Tumours of the Breast and Female Genital Organs , 2003 .

[47]  Ali Mahlooji Far,et al.  PROVIDING CONTEXT FOR TUMOR RECOGNITION USING THE WRAPPER FRAMEWORK , 2007, 2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[48]  Maryellen L. Giger,et al.  Automated seeded lesion segmentation on digital mammograms , 1998, IEEE Transactions on Medical Imaging.

[49]  Stuart Crozier,et al.  Automatic Segmentation of Enhancing Breast Tissue in Dynamic Contrast-Enhanced MR Images , 2007, 9th Biennial Conference of the Australian Pattern Recognition Society on Digital Image Computing Techniques and Applications (DICTA 2007).

[50]  L. Liberman,et al.  Breast imaging reporting and data system (BI-RADS). , 2002, Radiologic clinics of North America.

[51]  G. Meijer.  GLOBOCAN 1: Cancer Incidence and Mortality Worldwide. , 2000 .

[52]  Stuart Crozier,et al.  Denoising of Dynamic Contrast-Enhanced MR Images Using Dynamic Nonlocal Means , 2010, IEEE Transactions on Medical Imaging.

[53]  Thomas Bülow,et al.  Segmentation of suspicious lesions in dynamic contrast-enhanced breast MR images , 2007, SPIE Medical Imaging.