Advertisement

Where Position Matters—Deep-Learning–Driven Normalization and Coregistration of Computed Tomography in the Postoperative Analysis of Deep Brain Stimulation

  • Marco Reisert
    Correspondence
    Address correspondence to: Marco Reisert, PhD, Department of Stereotactic and Functional Neurosurgery, Medical Center of Freiburg University, Breisacher Straße 64–79106 Freiburg i.Br., Germany.
    Affiliations
    Department of Stereotactic and Functional Neurosurgery, Medical Center of Freiburg University, Freiburg, Germany

    Medical Faculty of Freiburg University, Freiburg, Germany

    Department of Diagnostic and Interventional Radiology, Medical Physics, Medical Center–University of Freiburg, Freiburg, Germany
    Search for articles by this author
  • Bastian E.A. Sajonz
    Affiliations
    Department of Stereotactic and Functional Neurosurgery, Medical Center of Freiburg University, Freiburg, Germany

    Medical Faculty of Freiburg University, Freiburg, Germany
    Search for articles by this author
  • Timo S. Brugger
    Affiliations
    Department of Stereotactic and Functional Neurosurgery, Medical Center of Freiburg University, Freiburg, Germany

    Medical Faculty of Freiburg University, Freiburg, Germany
    Search for articles by this author
  • Peter C. Reinacher
    Affiliations
    Department of Stereotactic and Functional Neurosurgery, Medical Center of Freiburg University, Freiburg, Germany

    Medical Faculty of Freiburg University, Freiburg, Germany

    Fraunhofer Institute for Laser Technology, Aachen, Germany
    Search for articles by this author
  • Maximilian F. Russe
    Affiliations
    Medical Faculty of Freiburg University, Freiburg, Germany

    Department of Diagnostic and Interventional Radiology, Medical Physics, Medical Center–University of Freiburg, Freiburg, Germany
    Search for articles by this author
  • Elias Kellner
    Affiliations
    Medical Faculty of Freiburg University, Freiburg, Germany

    Department of Diagnostic and Interventional Radiology, Medical Physics, Medical Center–University of Freiburg, Freiburg, Germany
    Search for articles by this author
  • Henrik Skibbe
    Affiliations
    RIKEN, Center for Brain Science, Brain Image Analysis Unit, Saitama, Japan
    Search for articles by this author
  • Volker A. Coenen
    Affiliations
    Department of Stereotactic and Functional Neurosurgery, Medical Center of Freiburg University, Freiburg, Germany

    Medical Faculty of Freiburg University, Freiburg, Germany

    Center for Deep Brain Stimulation, Medical Center of Freiburg University, Freiburg, Germany
    Search for articles by this author
Published:November 21, 2022DOI:https://doi.org/10.1016/j.neurom.2022.10.042

      Abstract

      Introduction

      Recent developments in the postoperative evaluation of deep brain stimulation surgery on the group level warrant the detection of achieved electrode positions based on postoperative imaging. Computed tomography (CT) is a frequently used imaging modality, but because of its idiosyncrasies (high spatial accuracy at low soft tissue resolution), it has not been sufficient for the parallel determination of electrode position and details of the surrounding brain anatomy (nuclei). The common solution is rigid fusion of CT images and magnetic resonance (MR) images, which have much better soft tissue contrast and allow accurate normalization into template spaces. Here, we explored a deep-learning approach to directly relate positions (usually the lead position) in postoperative CT images to the native anatomy of the midbrain and group space.

      Materials and Methods

      Deep learning is used to create derived tissue contrasts (white matter, gray matter, cerebrospinal fluid, brainstem nuclei) based on the CT image; that is, a convolution neural network (CNN) takes solely the raw CT image as input and outputs several tissue probability maps. The ground truth is based on coregistrations with MR contrasts. The tissue probability maps are then used to either rigidly coregister or normalize the CT image in a deformable way to group space. The CNN was trained in 220 patients and tested in a set of 80 patients.

      Results

      Rigorous validation of such an approach is difficult because of the lack of ground truth. We examined the agreements between the classical and proposed approaches and considered the spread of implantation locations across a group of identically implanted subjects, which serves as an indicator of the accuracy of the lead localization procedure. The proposed procedure agrees well with current magnetic resonance imaging–based techniques, and the spread is comparable or even lower.

      Conclusions

      Postoperative CT imaging alone is sufficient for accurate localization of the midbrain nuclei and normalization to the group space. In the context of group analysis, it seems sufficient to have a single postoperative CT image of good quality for inclusion. The proposed approach will allow researchers and clinicians to include cases that were not previously suitable for analysis.

      Keywords

      To read this article in full you will need to make a payment

      Purchase one-time access:

      Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online access
      One-time access price info
      • For academic or personal research use, select 'Academic and Personal'
      • For corporate R&D use, select 'Corporate R&D Professionals'

      Subscribe:

      Subscribe to
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect

      References

        • Coenen V.A.
        • Abdel-Rahman A.
        • McMaster J.
        • Bogod N.
        • Honey C.R.
        Minimizing brain shift during functional neurosurgical procedures—a simple burr hole technique that can decrease CSF loss and intracranial air.
        Cent Eur Neurosurg. 2011; 72: 181-185
        • Miyagi Y.
        • Shima F.
        • Sasaki T.
        Brain shift: an error factor during implantation of deep brain stimulation electrodes.
        J Neurosurg. 2007; 107: 989-997
        • Horn A.
        • Li N.
        • Dembek T.A.
        • et al.
        Lead-DBS v2: towards a comprehensive pipeline for deep brain stimulation imaging.
        NeuroImage. 2019; 184: 293-316
        • Schönecker T.
        • Kupsch A.
        • Kühn A.A.
        • Schneider G.H.
        • Hoffmann K.T.
        Automated optimization of subcortical cerebral MR imaging—atlas coregistration for improved postoperative electrode localization in deep brain stimulation.
        AJNR Am J Neuroradiol. 2009; 30: 1914-1921
        • Onofrey J.A.
        • Staib L.H.
        • Papademetris X.
        Learning intervention-induced deformations for non-rigid MR-CT registration and electrode localization in epilepsy patients.
        NeuroImage Clin. 2016; 10: 291-301https://doi.org/10.1016/j.nicl.2015.12.001
        • Bot M.
        • van den Munckhof P.
        • Bakay R.
        • Stebbins G.
        • Verhagen Metman L.V.
        Accuracy of intraoperative computed tomography during deep brain stimulation procedures: comparison with postoperative magnetic resonance imaging.
        Stereotact Funct Neurosurg. 2017; 95: 183-188
        • Mirzadeh Z.
        • Chapple K.
        • Lambert M.
        • Dhall R.
        • Ponce F.A.
        Validation of CT-MRI fusion for intraoperative assessment of stereotactic accuracy in DBS surgery.
        Mov Disord. 2014; 29: 1788-1795
        • Thani N.B.
        • Bala A.
        • Swann G.B.
        • Lind C.R.
        Accuracy of postoperative computed tomography and magnetic resonance image fusion for assessing deep brain stimulation electrodes.
        Neurosurgery. 2011; 69 ([discussion: 214]): 207-214
        • Burke J.F.
        • Tanzillo D.
        • Starr P.A.
        • Lim D.A.
        • Larson P.S.
        CT and MRI image fusion error: an analysis of co-registration error using commercially available deep brain stimulation surgical planning software.
        Stereotact Funct Neurosurg. 2021; 99: 196-202
        • Geevarghese R.
        • O’Gorman Tuura R.
        • Lumsden D.E.
        • Samuel M.
        • Ashkan K.
        Registration accuracy of CT/MRI fusion for localisation of deep brain stimulation electrode position: an imaging study and systematic review.
        Stereotact Funct Neurosurg. 2016; 94: 159-163
        • O’Gorman R.L.
        • Jarosz J.M.
        • Samuel M.
        • Clough C.
        • Selway R.P.
        • Ashkan K.
        CT/MR image fusion in the postoperative assessment of electrodes implanted for deep brain stimulation.
        Stereotact Funct Neurosurg. 2009; 87: 205-210
        • Reddy M.G.
        • Reddy P.V.N.
        • Reddy P.R.
        Segmentation of fused MR and CT images using DL-CNN with PGK and NLEM filtered AACGK-FCM.
        Biomed Signal Process Control. 2021; 68102618https://doi.org/10.1016/j.bspc.2021.102618
        • Zhao C.
        • Carass A.
        • Lee J.
        • He Y.
        • Prince J.L.
        Whole brain segmentation and labeling from CT using synthetic MR images.
        in: Wang Q. Shi Y. Suk H.I. Suzuki K. Machine Learning in Medical Imaging. Springer International Publishing, 2017: 291-298https://doi.org/10.1007/978-3-319-67389-9_34
        • Van De Leemput S.C.
        • Meijs M.
        • Patel A.
        • Meijer F.J.A.
        • Van Ginneken B.
        • Manniesing R.
        Multiclass brain tissue segmentation in 4D CT using convolutional neural networks.
        IEEE Access. 2019; 7: 51557-51569https://doi.org/10.1109/ACCESS.2019.2910348
        • Zadeh Shirazi A.
        • Fornaciari E.
        • McDonnell M.D.
        • et al.
        The application of deep convolutional neural networks to brain cancer images: a survey.
        J Pers Med. 2020; 10: 224
        • Srikrishna M.
        • Pereira J.B.
        • Heckemann R.A.
        • et al.
        Deep learning from MRI-derived labels enables automatic brain tissue classification on human brain CT.
        NeuroImage. 2021; 244118606https://doi.org/10.1016/j.neuroimage.2021.118606
        • Onofrey J.A.
        • Staib L.H.
        • Papademetris X.
        Segmenting the brain surface from CT images with artifacts using locally oriented appearance and dictionary learning.
        IEEE Trans Med Imaging. 2019; 38: 596-607https://doi.org/10.1109/TMI.2018.2868045
        • Coenen V.A.
        • Sajonz B.
        • Prokop T.
        • et al.
        The dentato-rubro-thalamic tract as the potential common deep brain stimulation target for tremor of various origin: an observational case series.
        Acta Neurochir (Wien). 2020; 162: 1053-1066
        • Coenen V.A.
        • Sajonz B.
        • Reisert M.
        • et al.
        Tractography-assisted deep brain stimulation of the superolateral branch of the medial forebrain bundle (slMFB DBS) in major depression.
        NeuroImage Clin. 2018; 20: 580-593
        • Reinacher P.C.
        • Várkuti B.
        • Krüger M.T.
        • et al.
        Automatic segmentation of the subthalamic nucleus: a viable option to support planning and visualization of patient-specific targeting in deep brain stimulation.
        Oper Neurosurg (Hagerstown). 2019; 17: 497-502
        • Coenen V.A.
        • Rijntjes M.
        • Sajonz B.
        • et al.
        Bilateral globus pallidus internus deep brain stimulation in a case of progressive dystonia in mohr-tranebjaerg syndrome with bilateral cochlear implants.
        J Neurol Surg A Cent Eur Neurosurg. 2019; 80: 44-48
        • Avants B.B.
        • Tustison N.J.
        • Song G.
        • Cook P.A.
        • Klein A.
        • Gee J.C.
        A reproducible evaluation of ANTs similarity metric performance in brain image registration.
        Neuroimage. 2011; 54: 2033-2044
        • Çiçek Ö.
        • Abdulkadir A.
        • Lienkamp S.S.
        • Brox T.
        • Ronneberger O.
        3D U-Net: learning dense volumetric segmentation from sparse annotation.
        in: International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, 2016: 424-432
        • Ashburner J.
        • Barnes G.
        • Chen C.C.
        • et al.
        SPM12 Manual.
        Wellcome Centre for Human Neuroimaging, 2014
        • Fonov V.
        • Evans A.C.
        • Botteron K.
        • et al.
        Unbiased average age-appropriate atlases for pediatric studies.
        Neuroimage. 2011; 54: 313-327

      Comments