Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Combining simple interactivity and machine learning: a separable deep learning approach to subthalamic nucleus localization and segmentation in MRI for deep brain stimulation surgical planning

Combining simple interactivity and machine learning: a separable deep learning approach to... Abstract.Purpose: Deep brain stimulation (DBS) is an interventional treatment for some neurological and neurodegenerative diseases. For example, in Parkinson’s disease, DBS electrodes are positioned at particular locations within the basal ganglia to alleviate the patient’s motor symptoms. These interventions depend greatly on a preoperative planning stage in which potential targets and electrode trajectories are identified in a preoperative MRI. Due to the small size and low contrast of targets such as the subthalamic nucleus (STN), their segmentation is a difficult task. Machine learning provides a potential avenue for development, but it has difficulty in segmenting such small structures in volumetric images due to additional problems such as segmentation class imbalance.Approach: We present a two-stage separable learning workflow for STN segmentation consisting of a localization step that detects the STN and crops the image to a small region and a segmentation step that delineates the structure within that region. The goal of this decoupling is to improve accuracy and efficiency and to provide an intermediate representation that can be easily corrected by a clinical user. This correction capability was then studied through a human–computer interaction experiment with seven novice participants and one expert neurosurgeon.Results: Our two-step segmentation significantly outperforms the comparative registration-based method currently used in clinic and approaches the fundamental limit on variability due to the image resolution. In addition, the human–computer interaction experiment shows that the additional interaction mechanism allowed by separating STN segmentation into two steps significantly improves the users’ ability to correct errors and further improves performance.Conclusions: Our method shows that separable learning not only is feasible for fully automatic STN segmentation but also leads to improved interactivity that can ease its translation into clinical use. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Journal of Medical Imaging SPIE

Combining simple interactivity and machine learning: a separable deep learning approach to subthalamic nucleus localization and segmentation in MRI for deep brain stimulation surgical planning

Download PDF
18 pages

Loading next page...
 
/lp/spie/combining-simple-interactivity-and-machine-learning-a-separable-deep-psPhicUNZ7
Publisher
SPIE
Copyright
© 2022 Society of Photo-Optical Instrumentation Engineers (SPIE)
ISSN
2329-4302
eISSN
2329-4310
DOI
10.1117/1.jmi.9.4.045001
Publisher site
See Article on Publisher Site

Abstract

Abstract.Purpose: Deep brain stimulation (DBS) is an interventional treatment for some neurological and neurodegenerative diseases. For example, in Parkinson’s disease, DBS electrodes are positioned at particular locations within the basal ganglia to alleviate the patient’s motor symptoms. These interventions depend greatly on a preoperative planning stage in which potential targets and electrode trajectories are identified in a preoperative MRI. Due to the small size and low contrast of targets such as the subthalamic nucleus (STN), their segmentation is a difficult task. Machine learning provides a potential avenue for development, but it has difficulty in segmenting such small structures in volumetric images due to additional problems such as segmentation class imbalance.Approach: We present a two-stage separable learning workflow for STN segmentation consisting of a localization step that detects the STN and crops the image to a small region and a segmentation step that delineates the structure within that region. The goal of this decoupling is to improve accuracy and efficiency and to provide an intermediate representation that can be easily corrected by a clinical user. This correction capability was then studied through a human–computer interaction experiment with seven novice participants and one expert neurosurgeon.Results: Our two-step segmentation significantly outperforms the comparative registration-based method currently used in clinic and approaches the fundamental limit on variability due to the image resolution. In addition, the human–computer interaction experiment shows that the additional interaction mechanism allowed by separating STN segmentation into two steps significantly improves the users’ ability to correct errors and further improves performance.Conclusions: Our method shows that separable learning not only is feasible for fully automatic STN segmentation but also leads to improved interactivity that can ease its translation into clinical use.

Journal

Journal of Medical Imaging – SPIE

Published: Jul 1, 2022

Keywords: subthalamic nucleus localization; subthalamic nucleus segmentation; convolutional neural networks; deep brain stimulation; separable machine learning; human–computer interaction

References

  • Deep-brain stimulation for Parkinson’s disease
    Okun, M. S.
  • PYDBS: an automated image processing workflow for deep brain stimulation surgery
    D’Albis, T.
  • Lead-DBS: a toolbox for deep brain stimulation electrode localizations and visualizations
    Horn, A.; Kühn, A. A.
  • Automated segmentation of basal ganglia and deep brain structures in MRI of Parkinson’s disease
    Haegelen, C.
  • Deep convolutional neural networks for brain image analysis on magnetic resonance imaging: a review
    Bernal, J.
  • Hough-CNN: deep learning for segmentation of deep brain regions in MRI and ultrasound
    Milletari, F.
  • 7t MRI subthalamic nucleus atlas for use with 3t MRI
    Milchenko, M.
  • Automatic localization of the subthalamic nucleus on patient-specific clinical MRI by incorporating 7 t MRI and machine learning: application in deep brain stimulation
    Kim, J.
  • Patient-specific anatomical model for deep brain stimulation based on 7 tesla MRI
    Duchin, Y.
  • Quantification of local geometric distortion in structural magnetic resonance images: application to ultra-high fields
    Lau, J. C.
  • Automated segmentation of midbrain structures in high-resolution susceptibility maps based on convolutional neural network and transfer learning
    Zhao, W.
  • Advanced normalization tools (ants)
    Avants, B. B.; Tustison, N.; Song, G.
  • BrainVISA: a complete software platform for neuroimaging
    Geffroy, D.
  • Localisation of the subthalamic nucleus in MRI via convolutional neural networks for deep brain stimulation planning
    Baxter, J. S. H.; Maguet, E.; Jannin, P.
  • U-Net: convolutional networks for biomedical image segmentation
    Ronneberger, O.; Fischer, P.; Brox, T.
  • Automatic multi-organ segmentation on abdominal CT with dense v-networks
    Gibson, E.
  • Segmentation of the subthalamic nucleus in MRI via convolutional neural networks for deep brain stimulation planning
    Baxter, J. S. H.; Maguet, E.; Jannin, P.
  • The semiotics of medical image segmentation
    Baxter, J. S. H.
  • Development of NASA-TLX (task load index): results of empirical and theoretical research
    Hart, S. G.; Staveland, L. E.
  • Comparison of automatic segmentation algorithms for the subthalamic nucleus
    Polanski, W. H.
  • Clinical deep brain stimulation region prediction using regression forests from high-field MRI
    Kim, J.
  • Deep double descent: where bigger models and more data hurt
    Nakkiran, P.
  • Individualized parcellation of the subthalamic nucleus in patients with Parkinson’s disease with 7T MRI
    Plantinga, B. R.
  • Semiautomatic segmentation of brain subcortical structures from high-field mri
    Kim, J.
  • Image guidance in deep brain stimulation surgery to treat Parkinson’s disease: a comprehensive review
    Xiao, Y.
  • Deep brain stimulation for Parkinson’s disease: patient selection and evaluation
    Lang, A. E.; Widner, H.
  • Sepaconvnet for localizing the subthalamic nucleus using one second micro-electrode recordings
    Peralta, M.
  • Brain shift: an error factor during implantation of deep brain stimulation electrodes
    Miyagi, Y.; Shima, F.; Sasaki, T.
  • Landmark-based elastic registration using approximating thin-plate splines
    Rohr, K.