As the name of our company already suggests, Im(age)Fusion and Registration is at the core of our expertise and deeply permeates our software architecture. In the context of medical image analysis, the term "registration" describes aligning image data from various sources, time, and modalities, into the same spatial coordinate system, such that the anatomy correctly matches and can be visualized and measured together accordingly.
To that end, we have cutting-edge technology for image-based registration, where the entire content of two or more images or volumes is used to assess the alignment of anatomical structures. The quality of alignment is quantified by a similarity measure or cost function, of which we have implemented many variants. In particular, signature patch-based techniques that overcome changes in appearance between imaging modalities with substantially different imaging physics, such as CT-Ultrasound and MRI-Ultrasound are available (cf. Wein2008, Wein2013). A transformation between the images to be matched is adjusted as to maximize such a similarity measure; here we have a large toolbox for non-linear optimization, using global and local techniques available. Transformations supported are rigid, affine, parametric deformable using free-form-deformations (FFD) or thin-plate-splines (TPS), and voxel-wise dense deformable. The latter is used with a Demons approach, where local similarity forces are computed and smoothed which iteratively update the deformation field.
At the same time, a powerful set of visualization and annotation tools support the analysis of fused data sets. Dedicated landmark-based evaluation may be used to thoroughly investigate registration accuracy. Measurements and segmented surfaces are transformed and linked to the registration results. Different blending, super-imposition and side-by-side display options allow for intuitive visual comparison. Last but not least, registered data sets may be re-sampled in the coordinate space of the reference data and exported as DICOM and other formats.
The above features enable clinicians and researchers to fuse image data from many different applications, including for example:
- CT time series registration for respiratory motion compensation, including contrasted studies;
- CT-Ultrasound and MRI-Ultrasound registration for neuro-surgery, prostate fusion, interventional oncology procedures for liver and kidney, general comparison of 3D ultrasound against CT and MRI;
- CT-MRI registration e.g. for radiotherapy planning or neurosurgery;
- Registration of multiple MRI scanning protocols to compensate patient motion;
- CT, CT-PET, CT-SPECT and MRI fusion at different treatment points for nuclear medicine.