Explainable unsupervised multi-modal image registration using deep networks

TL;DR

This paper introduces an explainable deep learning framework for unsupervised multi-modal MRI image registration, capable of handling both affine and non-rigid deformations, with improved interpretability over existing methods.

Contribution

The work presents a novel Grad-CAM-based explainability approach integrated into an unsupervised deep learning model for multi-modal MRI registration, enhancing transparency and generalizability.

Findings

Achieved superior registration performance compared to standard methods.

Demonstrated full explainability of the deep learning model.

Validated the approach's potential for broader medical imaging applications.

Abstract

Clinical decision making from magnetic resonance imaging (MRI) combines complementary information from multiple MRI sequences (defined as 'modalities'). MRI image registration aims to geometrically 'pair' diagnoses from different modalities, time points and slices. Both intra- and inter-modality MRI registration are essential components in clinical MRI settings. Further, an MRI image processing pipeline that can address both afine and non-rigid registration is critical, as both types of deformations may be occuring in real MRI data scenarios. Unlike image classification, explainability is not commonly addressed in image registration deep learning (DL) methods, as it is challenging to interpet model-data behaviours against transformation fields. To properly address this, we incorporate Grad-CAM-based explainability frameworks in each major component of our unsupervised multi-modal and multi-organ image registration DL methodology. We previously demonstrated that we were able to reach superior performance (against the current standard Syn method). In this work, we show that our DL model becomes fully explainable, setting the framework to generalise our approach on further medical imaging data.