Deformable image registration with deep network priors: a study on longitudinal PET images

TL;DR

This paper introduces MIRRBA, a deep architecture-based deformable registration method that uses deep priors without requiring training data, significantly improving registration accuracy and lesion shrinking in longitudinal PET images.

Contribution

MIRRBA leverages deep pyramidal architectures as regularizers for image registration, eliminating the need for training datasets and enhancing registration performance.

Findings

MIRRBA outperforms supervised deep learning models in Dice scores.

MIRRBA more than doubles the lesion shrinking rate compared to conventional methods.

Deep architectures effectively regularize deformation fields in registration.

Abstract

Longitudinal image registration is challenging and has not yet benefited from major performance improvements thanks to deep-learning. Inspired by Deep Image Prior, this paper introduces a different use of deep architectures as regularizers to tackle the image registration question. We propose a subject-specific deformable registration method called MIRRBA, relying on a deep pyramidal architecture to be the prior parametric model constraining the deformation field. Diverging from the supervised learning paradigm, MIRRBA does not require a learning database, but only the pair of images to be registered to optimize the network's parameters and provide a deformation field. We demonstrate the regularizing power of deep architectures and present new elements to understand the role of the architecture in deep learning methods for registration. Hence, to study the impact of the network parameters, we ran our method with different architectural configurations on a private dataset of 110 metastatic breast cancer full-body PET images with manual segmentations of the brain, bladder and metastatic lesions. We compared it against conventional iterative registration approaches and supervised deep learning-based models. Global and local registration accuracies were evaluated using the detection rate and the Dice score respectively, while registration realism was evaluated using the Jacobian's determinant. Moreover, we computed the ability of the different methods to shrink vanishing lesions with the disappearing rate. MIRRBA significantly improves the organ and lesion Dice scores of supervised models. Regarding the disappearing rate, MIRRBA more than doubles the best performing conventional approach SyNCC score. Our work therefore proposes an alternative way to bridge the performance gap between conventional and deep learning-based methods and demonstrates the regularizing power of deep architectures.