INSPIRE: Intensity and spatial information-based deformable image registration
This work provides a general-purpose, high-performance deformable image registration method for medical image analysis, offering improved accuracy and robustness for researchers and clinicians working with retinal and brain MRI data.
This paper introduces INSPIRE, a deformable image registration method that combines intensity and spatial information with an elastic B-splines transformation model and inverse inconsistency penalization. It achieves top performance on 2D retinal image datasets, outperforming widely used reference methods, and provides the best overall performance compared to 17 other state-of-the-art methods on four 3D brain MRI benchmark datasets (2088 pairwise registrations).
We present INSPIRE, a top-performing general-purpose method for deformable image registration. INSPIRE brings distance measures which combine intensity and spatial information into an elastic B-splines-based transformation model and incorporates an inverse inconsistency penalization supporting symmetric registration performance. We introduce several theoretical and algorithmic solutions which provide high computational efficiency and thereby applicability of the proposed framework in a wide range of real scenarios. We show that INSPIRE delivers highly accurate, as well as stable and robust registration results. We evaluate the method on a 2D dataset created from retinal images, characterized by presence of networks of thin structures. Here INSPIRE exhibits excellent performance, substantially outperforming the widely used reference methods. {We also evaluate INSPIRE on the Fundus Image Registration Dataset (FIRE), which consists of 134 pairs of separately acquired retinal images. INSPIRE exhibits excellent performance on the FIRE dataset, substantially outperforming several domain-specific methods.} We also evaluate the method on four benchmark datasets of 3D magnetic resonance images of brains, for a total of 2088 pairwise registrations. A comparison with 17 other state-of-the-art methods reveals that INSPIRE provides the best overall performance. Code is available at http://github.com/MIDA-group/inspire