Caroline M. E. Rubin

Automatic point correspondence and registration based on linear structures

A novel method to obtain point correspondence in pairs of images is presented. Our approach is based on automatically establishing correspondence between linear structures which appear in images using robust features such as orientation, width and curvature extracted from those structures. The extracted points can be used to register sets of images. The potential of the developed approach is demonstrated on mammographic images.

A novel similarity measure to evaluate image correspondence

We have developed a novel similarity measure to evaluate image correspondence. Our method is based on the mutual information between images. The main difference to other mutual information approaches is that we incorporate spatial information using grey-level co-occurrence matrices, leading to a more general measurement. We have used this technique to evaluate two registration algorithms (local affine transformation and thin plate splines) applied to a dataset of mammographic images.

Automatic Registration of Mammograms Based on Linear Structures

A novel method to obtain correspondence between landmarks when comparing pairs of mammographic images from the same patient is presented. Our approach is based on automatically established correspondence between linear structures (i.e. ducts and vessels) which appear in mammograms using robust features such as orientation, width and curvature extracted from those structures. In addition, a novel multiscale feature matching approach is presented which results in a reliable correspondence between extracted features.

TWO-DIMENSIONAL–THREE-DIMENSIONAL CORRESPONDENCE IN MAMMOGRAPHY

We present a framework for the registration and correspondence of magnetic resonance (MR) (three-dimensional data, 3D, data) and x-ray (two-dimensional data, 2D, data) mammographic images. The robustness of this work relies on the development of a novel method to establish nonlinear correspondence between modalities of different dimensionality, which also represent different physical tissue aspects. The correspondence is based on a 2D–2D matching process, which takes into account features from internal linear structures from both images and a measure of global similarity between modalities (Martí et al., International Journal of Pattern Recognition and Artificial Intelligence, vol. 16, no. 3, pp. 331–340, 2002). The 2D–3D correspondence relies on an intermediate step, which establishes registration between the 2D x-ray image and a projection of the 3D MR data. Initial quantitative and qualitative evaluation results, based on a small data set, are presented that show the validity of the developed approach.

EM Texture Segmentation of Mammographic Images

We have investigated a combination of statistical modelling and expectation maximisation for a texture based approach to the segmentation of mammographic images. Texture modelling is based on the implicit incorporation of spatial information. Statistical modelling is used for data generalisation and noise removal purposes. Expectation maximisation modelling of the spatial information in combination with the statistical modelling are compared to expectation maximisation modelling based on single grey-level values. The developed segmentation results are used for two specific applications which are registration of mammographic images and mammographic risk assessment.

Tracking mammographic structures over time

A method to correspond linear structures in mammographic images is presented. Our approach is based on automatically establishing correspondence between linear structures which appear in images using robust features such as orientation, width and curvature extracted from those structures. The resulting correspondence is used to track linear structures and regions in mammographic images taken at different times. Medical image analysis [1] has been an important research subject in recent years where computer vision techniques have been successfully applied to develop detection and diagnosis systems, enhancement and training tools. The analysis of mammographic images is one of those fields and as such a very challenging one due to the complexity of the images and the subtle nature of the abnormalities. Detection of abnormal structures or architectural distortions in mammographic images can be performed by analysing different images of the same patient. Various approaches have been adopted which bring images into alignment in order to detect differences which are likely to be due to an abnormality. A large number of those methods are based on automatically corresponding extracted landmarks from mammographic images. Those landmarks include breast boundary [15, 20, 9], pectoral muscle [9], salient regions extracted using wavelets [14], iso-intensity contours [11] or steerable filters [20] and crossing points of horizontal and vertical structures [22]. This work presents an approach to the correspondence in mammographic images based on anatomical features which appear as linear structures in the images. The correspondence is used here to track linear structures in mammograms of the same patient over several years. Tracking of linear structures could be used to assess and model the development of architectural changes and abnormal structures. By being able to track regions back in time the available information will help to improve early detection of subtle abnormalities which are initially missed by radiologists. The tracking of objects in image sequences is a well-developed area [21]. However, in general this involves rigid objects (like cars [8]) or objects with a predictable behaviour (like humans [10] or animals [18]). Another difference with the current application is the fact that normally tracking is established using sequences of tens to hundreds of images and not only a few.

Mammographic x-ray and MR correspondence

This paper presents a novel approach to tackle the problem of multi- modality correspondence in mammography. More precisely, this work focuses on finding a methodology to correspond areas in X-ray and MR images of the same breast. If correspondence between modalities is achieved, this information can be combined into a model providing a better understanding of the region of interest. Initial results show the validity of our approach although further evaluation is needed.

Detection of the Central Mass of Spiculated Lesions - Signature Normalisation and Model Data Aspects

We describe a method for labelling image structure based on non-linear scale-orientation signatures which can be used as a basis for robust pixel classification. The effect of normalisation of the signatures is discussed as a means to improve classification robustness with respect to grey-level variations. In addition, model data selection and scale normalisation are investigated as a means to improve the robustness of detection with respect to the scale of structures.

Tracking of 3D structures in MR Mammography

This work presents a novel method to establish correspondence in MR images taken at different times which allows the tracking of regions of interest through time-series and dynamic MR studies. This is developed as an hybrid correspondence approach, where a correlation measure and a point based method are used. Evaluation results are obtained using simulated deformation of the breast volume. In addition, registration and tracking results using real data are shown.