Image fusion for dynamic contrast enhanced magnetic resonance imaging

In this paper, image fusion based on Kernel Principal Component Analysis (KPCA) is proposed for the first time. It is demonstrated that a priori knowledge about the data domain can be easily incorporated into the parametrisation of the KPCA, leading to task-oriented visualisations of the multivariate data. The results of the fusion process are compared with those of the well-known and established standard linear Principal Component Analysis (PCA) by means of temporal sequences of 3D MRI volumes from six patients who took part in a breast cancer screening study.The PCA and KPCA algorithms are able to integrate information from a sequence of MRI volumes into informative gray value or colour images. By incorporating a priori knowledge, the fusion process can be automated and optimised in order to visualise suspicious lesions with high contrast to normal tissue.Our machine learning based image fusion approach maps the full signal space of a temporal DCE-MRI sequence to a single meaningful visualisation with good tissue/lesion contrast and thus supports the radiologist during manual image evaluation.In recent years, multivariate imaging techniques have become an important source of information to aid diagnosis in many medical fields. One example is the dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) technique [1,2]. After the administration of a gadolinium-based contrast agent, a sequence of d 3D MRI volumes is recorded from a certain part of the body (see Fig. 1). Thus, each spatial coordinate p = (x, y, z) in the volume can be associated with a temporal kinetic pattern vector which is regarded as a point in a signal space (see Fig. 2). The examination of these temporal kinetic patterns at different spatial coordinates in the volume allows the observer to infer information about local tissue types and states (see Fig. 3) [3].Today, much effort is spent on enhancing the capabilities of the imaging techniques e.g. increasing the spatial and temporal resolut