Carmel Hayes

Nonrigid registration using free-form deformations: application to breast MR images

In this paper the authors present a new approach for the nonrigid registration of contrast-enhanced breast MRI. A hierarchical transformation model of the motion of the breast has been developed. The global motion of the breast is modeled by an affine transformation while the local breast motion is described by a free-form deformation (FFD) based on B-splines. Normalized mutual information is used as a voxel-based similarity measure which is insensitive to intensity changes as a result of the contrast enhancement. Registration is achieved by minimizing a cost function, which represents a combination of the cost associated with the smoothness of the transformation and the cost associated with the image similarity. The algorithm has been applied to the fully automated registration of three-dimensional (3-D) breast MRI in volunteers and patients. In particular, the authors have compared the results of the proposed nonrigid registration algorithm to those obtained using rigid and affine registration techniques. The results clearly indicate that the nonrigid registration algorithm is much better able to recover the motion and deformation of the breast than rigid or affine registration algorithms.

Comparison and evaluation of rigid, affine, and nonrigid registration of breast MR images.

PURPOSE A new nonrigid registration method, designed to reduce the effect of movement artifact in subtraction images from breast MR, is compared with existing rigid and affine registration methods. METHOD Nonrigid registration was compared with rigid and affine registration methods and unregistered images using 54 gadolinium-enhanced 3D breast MR data sets. Twenty-seven data sets had been previously reported normal, and 27 contained a histologically proven carcinoma. The comparison was based on visual assessment and ranking by two radiologists. RESULTS When analyzed by two radiologists independently, all three registration methods gave better-quality subtraction images than unregistered images (p < 0.01), but nonrigid registration gave significantly better results than the rigid and affine registration methods (p < 0.01). There was no significant difference between rigid and affine registration methods. CONCLUSION Nonrigid registration significantly reduces the effects of movement artifact in subtracted contrast-enhanced breast MRI. This may enable better visualization of small tumors and those within a glandular breast.

Magnetic resonance imaging screening in women at genetic risk of breast cancer: imaging and analysis protocol for the UK multicentre study

The imaging and analysis protocol of the UK multicentre study of magnetic resonance imaging (MRI) as a method of screening for breast cancer in women at genetic risk is described. The study will compare the sensitivity and specificity of contrast-enhanced MRI with two-view x-ray mammography. Approximately 500 women below the age of 50 at high genetic risk of breast cancer will be recruited per year for three years, with annual MRI and x-ray mammography continuing for up to 5 years. A symptomatic cohort will be measured in the first year to ensure consistent reporting between centres. The MRI examination comprises a high-sensitivity three-dimensional contrast-enhanced assessment, followed by a high-specificity contrast-enhanced study in equivocal cases. Multiparametric analysis will encompass morphological assessment, the kinetics of contrast agent uptake and determination of quantitative pharmacokinetic parameters. Retrospective analysis will identify the most specific indicators of malignancy. Sensitivity and specificity, together with diagnostic performance, diagnostic impact and therapeutic impact will be assessed with reference to pathology, follow-up and changes in diagnostic certainty and therapeutic decisions. Mammography, lesion localisation, pathology and cytology will be performed in accordance with the UK NHS Breast Screening Programme quality assurance standards. Similar standards of quality assurance will be applied for MR measurements and evaluation.

Non-rigid Registration of Breast MR Images Using Mutual Information

We present a new approach for the non-rigid registration of contrast-enhanced breast MRI using normalised mutual information. A hierarchical transformation model of the motion of the breast has been developed: The global motion of the breast is modelled using affine transformation models while the local motion of the breast is modelled using spline-based free-form deformation (FFD) models. The algorithm has been applied to the fully automated registration of 3D breast MRI. In particular, we have compared the results of the proposed non-rigid registration algorithm to those obtained using rigid and affine registration techniques. The results clearly indicate that the non-rigid registration algorithm is much better able to recover the motion and deformation of the breast than rigid or affine registration algorithms.

Dynamic contrast-enhanced MRI in the differentiation of breast tumors: user-defined versus semi-automated region-of-interest analysis.

Dynamic contrast‐enhanced MR mammography is an increasingly used method of evaluating breast pathology. The purpose of this study was to compare two semi‐automated methods of region of interest (ROI) analysis with a user‐defined method, in the discrimination of breast tumors using dynamic contrast‐enhanced MRI. Results are presented from the retrospective analysis of 81 malignant and 36 benign breast lesions. The study demonstrates the importance of a consistent ROI strategy and also shows that semi‐automated approaches offer a standardized method, which may improve the discrimination of primary breast tumors. J. Magn. Reson. Imaging 1999; 10:945–949.

A Phase I study of the angiogenesis inhibitor SU5416 (semaxanib) in solid tumours, incorporating dynamic contrast MR pharmacodynamic end points

SU5416 (Z-3-[(2,4-dimethylpyrrol-5-yl)methylidenyl]-2-indolinone; semaxanib) is a small molecule inhibitor of the vascular endothelial growth factor receptor (VEGFR)2. A Phase I dose escalation study was performed. Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) was used as a pharmacodynamic assessment tool. In all, 27 patients were recruited. SU5416 was administered twice weekly by fixed rate intravenous infusion. Patients were treated in sequential cohorts of three patients at 48, 65, 85 110 and 145 mg m−2. A further dose level of 190 mg m−2 after a 2-week lead in period at a lower dose was completed; thereafter, the cohort at 145 mg m−2 was expanded. SU5416 showed linear pharmacokinetics to 145 mg m−2 with a large volume of distribution and rapid clearance. A significant degree of interpatient variability was seen. SU5416 was well tolerated, by definition a maximum-tolerated dose was not defined. No reproducible changes were seen in DCE-MRI end points. Serial assessments of VEGF in a cohort of patients treated at 145 mg m−2 did not show a statistically significant treatment-related change. Parallel assessments of the impact of SU5416 on coagulation profiles in six patients showed a transient effect within the fibrinolytic pathway. Clinical experience showed that patients who had breaks of therapy longer than a week could not have treatment reinitiated at a dose of 190 mg m−2 without unacceptable toxicity. The 145 mg m−2 dose level is thus the recommended dose for future study.

Evaluation of radiological features for breast tumour classification in clinical screening with machine learning methods

OBJECTIVE In this work, methods utilizing supervised and unsupervised machine learning are applied to analyze radiologically derived morphological and calculated kinetic tumour features. The features are extracted from dynamic contrast enhanced magnetic resonance imaging (DCE-MRI) time-course data. MATERIAL The DCE-MRI data of the female breast are obtained within the UK Multicenter Breast Screening Study. The group of patients imaged in this study is selected on the basis of an increased genetic risk for developing breast cancer. METHODS The k-means clustering and self-organizing maps (SOM) are applied to analyze the signal structure in terms of visualization. We employ k-nearest neighbor classifiers (k-nn), support vector machines (SVM) and decision trees (DT) to classify features using a computer aided diagnosis (CAD) approach. RESULTS Regarding the unsupervised techniques, clustering according to features indicating benign and malignant characteristics is observed to a limited extend. The supervised approaches classified the data with 74% accuracy (DT) and providing an area under the receiver-operator-characteristics (ROC) curve (AUC) of 0.88 (SVM). CONCLUSION It was found that contour and wash-out type (WOT) features determined by the radiologists lead to the best SVM classification results. Although a fast signal uptake in early time-point measurements is an important feature for malignant/benign classification of tumours, our results indicate that the wash-out characteristics might be considered as important.

Assessment of left ventricular function by breath‐hold cine MR imaging: Comparison of different steady‐state free precession sequences

To compare steady‐state free precession (SSFP) sequence protocols with different acquisition times (TA) and temporal resolutions (tRes) due to the implementation of a view sharing technique called shared phases for the assessment of left ventricular (LV) function by breath‐hold cine magnetic resonance (MR) imaging.

Validation of Non-rigid Registration Using Finite Element Methods

We present a novel validation method for non-rigid registration using a simulation of deformations based on biomechanical modelling of tissue properties. This method is tested on a previously developed non-rigid registration method for dynamic contrast enhanced Magnetic Resonance (MR) mammography image pairs [1]. We have constructed finite element breast models and applied a range of displacements to them, with an emphasis on generating physically plausible deformations which may occur during normal patient scanning procedures. From the finite element method (FEM) solutions, we have generated a set of deformed contrast enhanced images against which we have registered the original dynamic image pairs. The registration results have been successfully validated at all breast tissue locations by comparing the recovered displacements with the biomechanical displacements. The validation method presented in this paper is an important tool to provide biomechanical gold standard deformations for registration error quantification, which may also form the basis to improve and compare different non-rigid registration techniques for a diversity of medical applications.

A method for the comparison of biomechanical breast models

Biomechanical models of the breast are being developed for a wide range of applications including image alignment tasks to improve diagnosis and therapy monitoring, imaging related studies of the biomechanical properties of lesions, and image guided interventions. In this paper we present a method to evaluate the accuracy with which biomechanical breast models based on finite element methods (FEM) can predict the displacements of tissue within the breast. Our experimental data was obtained by compressing the breast of a volunteer in a controlled manner, and the acquisition of MR images of the breast before and after compression. Non-rigid registration of these two MR volumes together with interactive identification of corresponding landmarks provided an independent estimate of the displacements. In addition, the non-rigid registration provided estimates of the displacements of the surface points (skin points) of the breast. The accuracy of the FEM models was evaluated using all or a subset of these surface displacements as boundary conditions. The influence of pectoral muscle movement on the performance of the FEM models was also investigated. Our initial results indicate that the accurate setting of the boundary conditions is more important than the actual choice of elastic properties in these compression scenarios. With the complete boundary conditions, the displacements agreed to within 2.6 mm for all FEM models on average. Assuming no movement at the posterior or the medial side of the breast, the accuracy of the FEM models deteriorated to worse than 4.6 mm for all models.