Learning Deformable Registration of Medical Images with Anatomical Constraints
This addresses the need for anatomically plausible registration in medical image analysis, particularly for chest X-rays with high variability, representing an incremental improvement over existing deep learning methods.
The paper tackled the problem of producing anatomically plausible results in deformable medical image registration by incorporating anatomical priors as global constraints, showing that the proposed AC-RegNet model achieves more realistic and accurate results than state-of-the-art methods on chest X-ray datasets.
Deformable image registration is a fundamental problem in the field of medical image analysis. During the last years, we have witnessed the advent of deep learning-based image registration methods which achieve state-of-the-art performance, and drastically reduce the required computational time. However, little work has been done regarding how can we encourage our models to produce not only accurate, but also anatomically plausible results, which is still an open question in the field. In this work, we argue that incorporating anatomical priors in the form of global constraints into the learning process of these models, will further improve their performance and boost the realism of the warped images after registration. We learn global non-linear representations of image anatomy using segmentation masks, and employ them to constraint the registration process. The proposed AC-RegNet architecture is evaluated in the context of chest X-ray image registration using three different datasets, where the high anatomical variability makes the task extremely challenging. Our experiments show that the proposed anatomically constrained registration model produces more realistic and accurate results than state-of-the-art methods, demonstrating the potential of this approach.