Towards Realtime Multimodal Fusion for Image-Guided Interventions Using Self-similarities

• DOI: 10.1007/978-3-642-40811-3_24
• Publication Date: 2013-09-20T06:09:07Z
• Authors: Mattias Paul Hein...; Mark Jenkinson; Bartlomiej W. Papież; Sir Michael Brady; Julia A. Schnabel
• Keywords: Brain Neoplasms; 610; Image Enhancement; Magnetic Resonance Imaging; Multimodal Imaging; Neurosurgical Procedures; multimodal similarity; 004; Pattern Recognition, Automated; 03 medical and health sciences; discrete optimisation; 0302 clinical medicine; Surgery, Computer-Assisted; Computer Systems; Subtraction Technique; Image Interpretation, Computer-Assisted; Humans; neurosurgery; Algorithms

Image-guided interventions often rely on deformable multimodal registration to align pre-treatment and intra-operative scans. There are a number of requirements for automated image registration for this task, such as a robust similarity metric for scans of different modalities with different noise distributions and contrast, an efficient optimisation of the cost function to enable fast registration for this time-sensitive application, and an insensitive choice of registration parameters to avoid delays in practical clinical use. In this work, we build upon the concept of structural image representation for multi-modal similarity. Discriminative descriptors are densely extracted for the multi-modal scans based on the "self-similarity context". An efficient quantised representation is derived that enables very fast computation of point-wise distances between descriptors. A symmetric multi-scale discrete optimisation with diffusion reguIarisation is used to find smooth transformations. The method is evaluated for the registration of 3D ultrasound and MRI brain scans for neurosurgery and demonstrates a significantly reduced registration error (on average 2.1 mm) compared to commonly used similarity metrics and computation times of less than 30 seconds per 3D registration.