Weakly-supervised Biomechanically-constrained CT/MRI Registration of the Spine

TL;DR

This paper introduces a weakly-supervised deep learning method for registering CT and MRI spine images, ensuring vertebral rigidity and volume preservation, leading to more plausible and accurate multimodal spinal image fusion.

Contribution

The paper presents a novel anatomy-aware loss function for deep learning-based spine registration that leverages CT labels to improve transformation plausibility without sacrificing accuracy.

Findings

Adding anatomy-aware losses improves transformation plausibility.

The method maintains registration accuracy while enhancing biological plausibility.

Evaluation on 167 patient datasets demonstrates effectiveness.

Abstract

CT and MRI are two of the most informative modalities in spinal diagnostics and treatment planning. CT is useful when analysing bony structures, while MRI gives information about the soft tissue. Thus, fusing the information of both modalities can be very beneficial. Registration is the first step for this fusion. While the soft tissues around the vertebra are deformable, each vertebral body is constrained to move rigidly. We propose a weakly-supervised deep learning framework that preserves the rigidity and the volume of each vertebra while maximizing the accuracy of the registration. To achieve this goal, we introduce anatomy-aware losses for training the network. We specifically design these losses to depend only on the CT label maps since automatic vertebra segmentation in CT gives more accurate results contrary to MRI. We evaluate our method on an in-house dataset of 167 patients. Our results show that adding the anatomy-aware losses increases the plausibility of the inferred transformation while keeping the accuracy untouched.