Learning Deformable Registration of Medical Images with Anatomical Constraints

Abstract

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.

Accepted for publication in Neural Networks (Elsevier). Source code and resulting segmentation masks for the NIH Chest-XRay14 dataset with estimated quality index available at https://github.com/lucasmansilla/ACRN_Chest_X-ray_IA

References in corpus (1)

• Fully Convolutional Networks for Semantic Segmentation

Cited by in corpus (8)

• Deep Learning for Chest X-ray Analysis: A Survey
• Medical image registration using unsupervised deep neural network: A scoping literature review
• CheXmask: a large-scale dataset of anatomical segmentation masks for multi-center chest x-ray images
• MDReg-Net: Multi-resolution diffeomorphic image registration using fully convolutional networks with deep self-supervision
• Anatomy-Aware Cardiac Motion Estimation
• Employing similarity to highlight differences: On the impact of anatomical assumptions in chest X-ray registration methods
• CAR-Net: Unsupervised Co-Attention Guided Registration Network for Joint Registration and Structure Learning
• MICS : Multi-steps, Inverse Consistency and Symmetric deep learning registration network