Literature DB >> 34784539

Deformable MR-CT image registration using an unsupervised, dual-channel network for neurosurgical guidance.

R Han1, C K Jones2, J Lee3, P Wu1, P Vagdargi4, A Uneri1, P A Helm5, M Luciano6, W S Anderson6, J H Siewerdsen7.   

Abstract

PURPOSE: The accuracy of minimally invasive, intracranial neurosurgery can be challenged by deformation of brain tissue - e.g., up to 10 mm due to egress of cerebrospinal fluid during neuroendoscopic approach. We report an unsupervised, deep learning-based registration framework to resolve such deformations between preoperative MR and intraoperative CT with fast runtime for neurosurgical guidance.
METHOD: The framework incorporates subnetworks for MR and CT image synthesis with a dual-channel registration subnetwork (with synthesis uncertainty providing spatially varying weights on the dual-channel loss) to estimate a diffeomorphic deformation field from both the MR and CT channels. An end-to-end training is proposed that jointly optimizes both the synthesis and registration subnetworks. The proposed framework was investigated using three datasets: (1) paired MR/CT with simulated deformations; (2) paired MR/CT with real deformations; and (3) a neurosurgery dataset with real deformation. Two state-of-the-art methods (Symmetric Normalization and VoxelMorph) were implemented as a basis of comparison, and variations in the proposed dual-channel network were investigated, including single-channel registration, fusion without uncertainty weighting, and conventional sequential training of the synthesis and registration subnetworks.
RESULTS: The proposed method achieved: (1) Dice coefficient = 0.82±0.07 and TRE = 1.2 ± 0.6 mm on paired MR/CT with simulated deformations; (2) Dice coefficient = 0.83 ± 0.07 and TRE = 1.4 ± 0.7 mm on paired MR/CT with real deformations; and (3) Dice = 0.79 ± 0.13 and TRE = 1.6 ± 1.0 mm on the neurosurgery dataset with real deformations. The dual-channel registration with uncertainty weighting demonstrated superior performance (e.g., TRE = 1.2 ± 0.6 mm) compared to single-channel registration (TRE = 1.6 ± 1.0 mm, p < 0.05 for CT channel and TRE = 1.3 ± 0.7 mm for MR channel) and dual-channel registration without uncertainty weighting (TRE = 1.4 ± 0.8 mm, p < 0.05). End-to-end training of the synthesis and registration subnetworks also improved performance compared to the conventional sequential training strategy (TRE = 1.3 ± 0.6 mm). Registration runtime with the proposed network was ∼3 s.
CONCLUSION: The deformable registration framework based on dual-channel MR/CT registration with spatially varying weights and end-to-end training achieved geometric accuracy and runtime that was superior to state-of-the-art baseline methods and various ablations of the proposed network. The accuracy and runtime of the method may be compatible with the requirements of high-precision neurosurgery.
Copyright © 2021 Elsevier B.V. All rights reserved.

Entities:  

Keywords:  Deformable registration; Image synthesis; Inter-modality registration; Unsupervised learning

Mesh:

Year:  2021        PMID: 34784539     DOI: 10.1016/j.media.2021.102292

Source DB:  PubMed          Journal:  Med Image Anal        ISSN: 1361-8415            Impact factor:   8.545


  1 in total

1.  Dual attention network for unsupervised medical image registration based on VoxelMorph.

Authors:  Yong-Xin Li; Hui Tang; Wei Wang; Xiu-Feng Zhang; Hang Qu
Journal:  Sci Rep       Date:  2022-09-28       Impact factor: 4.996

  1 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.