A Deep Network for Joint Registration and Reconstruction of Images with Pathologies

TL;DR

This paper introduces a deep learning model that jointly registers and reconstructs images with brain tumors, effectively handling pathological changes and improving registration accuracy compared to traditional methods.

Contribution

The work presents a novel deep learning framework that disentangles tumor effects from normal tissue for improved registration and reconstruction of pathological brain images.

Findings

Outperforms cost function masking in registration accuracy

Reconstructed images facilitate better longitudinal registration

Effective on both synthetic and real brain tumor scans

Abstract

Registration of images with pathologies is challenging due to tissue appearance changes and missing correspondences caused by the pathologies. Moreover, mass effects as observed for brain tumors may displace tissue, creating larger deformations over time than what is observed in a healthy brain. Deep learning models have successfully been applied to image registration to offer dramatic speed up and to use surrogate information (e.g., segmentations) during training. However, existing approaches focus on learning registration models using images from healthy patients. They are therefore not designed for the registration of images with strong pathologies for example in the context of brain tumors, and traumatic brain injuries. In this work, we explore a deep learning approach to register images with brain tumors to an atlas. Our model learns an appearance mapping from images with tumors to the atlas, while simultaneously predicting the transformation to atlas space. Using separate decoders, the network disentangles the tumor mass effect from the reconstruction of quasi-normal images. Results on both synthetic and real brain tumor scans show that our approach outperforms cost function masking for registration to the atlas and that reconstructed quasi-normal images can be used for better longitudinal registrations.