Multimodal Deformable Image Registration for Long-COVID Analysis Based on Progressive Alignment and Multi-perspective Loss

Long COVID is characterized by persistent symptoms, particularly pulmonaryimpairment, which necessitates advanced imaging for accurate diagnosis.Hyperpolarised Xenon-129 MRI (XeMRI) offers a promising avenue by visualisinglung ventilation, perfusion, as well as gas transfer. Integrating functionaldata from XeMRI with structural data from Computed Tomography (CT) is crucialfor comprehensive analysis and effective treatment strategies in long COVID,requiring precise data alignment from those complementary imaging modalities.To this end, CT-MRI registration is an essential intermediate step, given thesignificant challenges posed by the direct alignment of CT and Xe-MRI.Therefore, we proposed an end-to-end multimodal deformable image registrationmethod that achieves superior performance for aligning long-COVID lung CT andproton density MRI (pMRI) data. Moreover, our method incorporates a novelMulti-perspective Loss (MPL) function, enhancing state-of-the-art deep learningmethods for monomodal registration by making them adaptable for multimodaltasks. The registration results achieve a Dice coefficient score of 0.913,indicating a substantial improvement over the state-of-the-art multimodal imageregistration techniques. Since the XeMRI and pMRI images are acquired in thesame sessions and can be roughly aligned, our results facilitate subsequentregistration between XeMRI and CT, thereby potentially enhancing clinicaldecision-making for long COVID management.