Automatic cortical target point localisation in MRI for transcranial magnetic stimulation via a multi-resolution convolutional neural network

Abstract

Purpose

Transcranial magnetic stimulation (TMS) is a growing therapy for a variety of psychiatric and neurological disorders that arise from or are modulated by cortical regions of the brain represented by singular 3D target points. These target points are often determined manually with assistance from a pre-operative T1-weighted MRI, although there is growing interest in automatic target point localisation using an atlas. However, both approaches can be time-consuming which has an effect on the clinical workflow, and the latter does not take into account patient variability such as the varying number of cortical gyri where these targets are located.

Methods

This paper proposes a multi-resolution convolutional neural network for point localisation in MR images for a priori defined points in increasingly finely resolved versions of the input image. This approach is both fast and highly memory efficient, allowing it to run in high-throughput centres, and has the capability of distinguishing between patients with high levels of anatomical variability.

Results

Preliminary experiments have found the accuracy of this network to be \(7.26\pm 5.30\) mm, compared to \(9.39\pm 4.63\) mm for deformable registration and \(6.94\pm 5.10\) mm for a human expert. For most treatment points, the human expert and proposed CNN statistically significantly outperform registration, but neither statistically significantly outperforms the other, suggesting that the proposed network has human-level performance.

Conclusions

The human-level performance of this network indicates that it can improve TMS planning by automatically localising target points in seconds, avoiding more time-consuming registration or manual point localisation processes. This is particularly beneficial for out-of-hospital centres with limited computational resources where TMS is increasingly being administered.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4

Data availability

Data are not available for this study.

References

  1. 1.

    Ahdab R, Ayache S, Brugières P, Goujon C, Lefaucheur JP (2010) Comparison of “standard” and “navigated” procedures of TMS coil positioning over motor, premotor and prefrontal targets in patients with chronic pain and depression. Neurophysiol Clin/Clin Neurophysiol 40(1):27–36

    CAS  Article  Google Scholar 

  2. 2.

    Avants BB, Epstein CL, Grossman M, Gee JC (2008) Symmetric diffeomorphic image registration with cross-correlation: evaluating automated labeling of elderly and neurodegenerative brain. Med Image Anal 12(1):26–41

    CAS  Article  Google Scholar 

  3. 3.

    Baxter JSH, Maguet E, Jannin P (2020) Localisation of the subthalamic nucleus in MRI via convolutional neural networks for deep brain stimulation planning. In: Medical imaging 2020: image-guided procedures, robotic interventions, and modeling. vol. 11315. International Society for Optics and Photonics, p 113150M

  4. 4.

    Bulteau S, Beynel L, Marendaz C, Dall’Igna G, Peré M, Harquel S, Chauvin A, Guyader N, Sauvaget A, Vanelle JM, Polosan M, Bougerol T, Brunelin J, Szekely D (2019) Twice-daily neuronavigated intermittent theta burst stimulation for bipolar depression: a randomized sham-controlled pilot study. Neurophysiol Clin 49(5):371–375

    Article  Google Scholar 

  5. 5.

    Freitas C, Mondragón-Llorca H, Pascual-Leone A (2011) Noninvasive brain stimulation in Alzheimer’s disease: systematic review and perspectives for the future. Exp Gerontol 46(8):611–627

    PubMed  PubMed Central  Google Scholar 

  6. 6.

    Gibson E, Giganti F, Hu Y, Bonmati E, Bandula S, Gurusamy K, Davidson B, Pereira SP, Clarkson MJ, Barratt DC (2018) Automatic multi-organ segmentation on abdominal CT with dense V-networks. IEEE Trans Med Imaging 37(8):1822–1834

    Article  Google Scholar 

  7. 7.

    Harika-Germaneau G, Rachid F, Chatard A, Lafay-Chebassier C, Solinas M, Thirioux B, Millet B, Langbour N, Jaafari N (2019) Continuous theta burst stimulation over the supplementary motor area in refractory obsessive-compulsive disorder treatment: a randomized sham-controlled trial. Brain Stimul 12(6):1565–1571

    CAS  Article  Google Scholar 

  8. 8.

    Heimann T, Meinzer HP (2009) Statistical shape models for 3d medical image segmentation: a review. Med Image Anal 13(4):543–563

    Article  Google Scholar 

  9. 9.

    Johnson S, Summers J, Pridmore S (2006) Changes to somatosensory detection and pain thresholds following high frequency repetitive TMS of the motor cortex in individuals suffering from chronic pain. Pain 123(1–2):187–192

    Article  Google Scholar 

  10. 10.

    Kim WJ, Min YS, Yang EJ, Paik NJ (2014) Neuronavigated vs. conventional repetitive transcranial magnetic stimulation method for virtual Lesioning on the Broca’s area. Neuromodul Technol Neural Interface 17(1):16–21

    Article  Google Scholar 

  11. 11.

    Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems. pp 1097–1105

  12. 12.

    Lefaucheur JP, Aleman A, Baeken C, Benninger DH, Brunelin J, Di Lazzaro V, Filipović SR, Grefkes C, Hasan A, Hummel FC, Jääskeläinen SK, Kimiskidis VK, Koch G, Langguth B, Nyffeler T, Oliviero A, Padberg F, Poulet E, Rossi S, Rossini PM, Rothwell JC, Schönfeldt-Lecuona C, Siebner HR, Slotema CW, Stagg CJ, Valls-Sole J, Ziemann U, Paulus W, Garcia-Larrea L (2020) Evidence-based guidelines on the therapeutic use of repetitive transcranial magnetic stimulation (RTMS): an update (2014–2018). Clin Neurophysiol 131(2):474–528

    Article  Google Scholar 

  13. 13.

    Pennisi G, Ferri R, Lanza G, Cantone M, Pennisi M, Puglisi V, Malaguarnera G, Bella R (2011) Transcranial magnetic stimulation in Alzheimer’s disease: a neurophysiological marker of cortical hyperexcitability. J Neural Transm 118(4):587–598

    CAS  Article  Google Scholar 

  14. 14.

    Ren S, He K, Girshick R, Sun J (2015) Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in neural information processing systems. pp 91–99

  15. 15.

    Ronneberger O, Fischer P, Brox T (2015) U-NET: convolutional networks for biomedical image segmentation. In: International conference on medical image computing and computer-assisted intervention. Springer, pp 234–241

  16. 16.

    Rusjan PM, Barr MS, Farzan F, Arenovich T, Maller JJ, Fitzgerald PB, Daskalakis ZJ (2010) Optimal transcranial magnetic stimulation coil placement for targeting the dorsolateral prefrontal cortex using novel magnetic resonance image-guided neuronavigation. Hum Brain Mapp 31(11):1643–1652

    PubMed  PubMed Central  Google Scholar 

  17. 17.

    Summers JJ, Kagerer FA, Garry MI, Hiraga CY, Loftus A, Cauraugh JH (2007) Bilateral and unilateral movement training on upper limb function in chronic stroke patients: a TMS study. J Neurol Sci 252(1):76–82

    Article  Google Scholar 

  18. 18.

    Vignaud P, Damasceno C, Poulet E, Brunelin J (2019) Impaired modulation of corticospinal excitability in drug-free patients with major depressive disorder: a theta-burst stimulation study. Front Hum Neurosci 13:72

    CAS  Article  Google Scholar 

  19. 19.

    Weise K, Numssen O, Thielscher A, Hartwigsen G, Knösche TR (2020) A novel approach to localize cortical TMS effects. Neuroimage 209:116486

    Article  Google Scholar 

Download references

Acknowledgements

John S. H. Baxter is supported by the Institut des Neurosciences Cliniques de Rennes (INCR) and the Natural Sciences and Engineering Research Council of Canada (NSERC) through the Post-Doctoral Fellowship (PDF) program. Quoc Anh Bui is funded through a financial support from Région Bretagne. Ehouarn Maguet is also supported INCR. The authors would like to thank X. Morandi, C. Nauczyciel, B. Le Goff, and J.-P. N’Guyen for the annotation of the non-motor treatment points. The authors would also like to thank J.-P. N’Guyen and H. Hodaj for their assistance in annotating the chronic pain treatment points along with J.-P. Lefaucheur.

Funding

No funding was received to assist in the preparation of this manuscript.

Author information

Affiliations

Authors

Corresponding author

Correspondence to John S. H. Baxter.

Ethics declarations

Conflict of interest

S. Croci, A. Delmas and L. Bredoux are employees of SYNEIKA. The remaining authors have no financial or non-financial conflicts of interest.

Ethical approval

All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and with the 1964 Helsinki declaration and its later amendments or comparable ethical standards.

Informed consent

Informed consent was obtained from all individual participants included in the study.

Code availability

Code is currently not made available.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Baxter, J.S.H., Bui, Q.A., Maguet, E. et al. Automatic cortical target point localisation in MRI for transcranial magnetic stimulation via a multi-resolution convolutional neural network. Int J CARS 16, 1077–1087 (2021). https://doi.org/10.1007/s11548-021-02386-1

Download citation

Keywords

  • Transcranial magnetic stimulation
  • Deep learning
  • Convolutional neural networks