Automatic localization of the subthalamic nucleus on patient-specific clinical MRI by incorporating 7 T MRI and machine learning: Application in deep brain stimulation

Jinyoung Kim, Yuval Duchin, Reuben R. Shamir, Remi Patriat, Jerrold Vitek, Noam Harel, Guillermo Sapiro

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Deep brain stimulation (DBS) of the subthalamic nucleus (STN) has shown clinical potential for relieving the motor symptoms of advanced Parkinson's disease. While accurate localization of the STN is critical for consistent across-patients effective DBS, clear visualization of the STN under standard clinical MR protocols is still challenging. Therefore, intraoperative microelectrode recordings (MER) are incorporated to accurately localize the STN. However, MER require significant neurosurgical expertise and lengthen the surgery time. Recent advances in 7 T MR technology facilitate the ability to clearly visualize the STN. The vast majority of centers, however, still do not have 7 T MRI systems, and fewer have the ability to collect and analyze the data. This work introduces an automatic STN localization framework based on standard clinical MRIs without additional cost in the current DBS planning protocol. Our approach benefits from a large database of 7 T MRI and its clinical MRI pairs. We first model in the 7 T database, using efficient machine learning algorithms, the spatial and geometric dependency between the STN and its adjacent structures (predictors). Given a standard clinical MRI, our method automatically computes the predictors and uses the learned information to predict the patient-specific STN. We validate our proposed method on clinical T2W MRI of 80 subjects, comparing with experts-segmented STNs from the corresponding 7 T MRI pairs. The experimental results show that our framework provides more accurate and robust patient-specific STN localization than using state-of-the-art atlases. We also demonstrate the clinical feasibility of the proposed technique assessing the post-operative electrode active contact locations.

Original languageEnglish (US)
Pages (from-to)679-698
Number of pages20
JournalHuman Brain Mapping
Volume40
Issue number2
DOIs
StatePublished - Feb 1 2019

Fingerprint

Subthalamic Nucleus
Deep Brain Stimulation
Microelectrodes
Post and Core Technique
Databases
Machine Learning
Spatial Analysis
Atlases
Clinical Protocols
Parkinson Disease
Electrodes
Technology
Costs and Cost Analysis

Keywords

  • 7 T MR imaging
  • deep brain stimulation
  • machine learning
  • neuromodulation
  • patient-specific sub-region targeting
  • subthalamic nucleus

PubMed: MeSH publication types

  • Journal Article
  • Research Support, Non-U.S. Gov't
  • Research Support, N.I.H., Extramural

Cite this

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, Jinyoung; Duchin, Yuval; Shamir, Reuben R.; Patriat, Remi; Vitek, Jerrold; Harel, Noam; Sapiro, Guillermo.

In: Human Brain Mapping, Vol. 40, No. 2, 01.02.2019, p. 679-698.

Research output: Contribution to journalArticle

@article{9750a2219874404bbaa4b26446259e75,
title = "Automatic localization of the subthalamic nucleus on patient-specific clinical MRI by incorporating 7 T MRI and machine learning: Application in deep brain stimulation",
abstract = "Deep brain stimulation (DBS) of the subthalamic nucleus (STN) has shown clinical potential for relieving the motor symptoms of advanced Parkinson's disease. While accurate localization of the STN is critical for consistent across-patients effective DBS, clear visualization of the STN under standard clinical MR protocols is still challenging. Therefore, intraoperative microelectrode recordings (MER) are incorporated to accurately localize the STN. However, MER require significant neurosurgical expertise and lengthen the surgery time. Recent advances in 7 T MR technology facilitate the ability to clearly visualize the STN. The vast majority of centers, however, still do not have 7 T MRI systems, and fewer have the ability to collect and analyze the data. This work introduces an automatic STN localization framework based on standard clinical MRIs without additional cost in the current DBS planning protocol. Our approach benefits from a large database of 7 T MRI and its clinical MRI pairs. We first model in the 7 T database, using efficient machine learning algorithms, the spatial and geometric dependency between the STN and its adjacent structures (predictors). Given a standard clinical MRI, our method automatically computes the predictors and uses the learned information to predict the patient-specific STN. We validate our proposed method on clinical T2W MRI of 80 subjects, comparing with experts-segmented STNs from the corresponding 7 T MRI pairs. The experimental results show that our framework provides more accurate and robust patient-specific STN localization than using state-of-the-art atlases. We also demonstrate the clinical feasibility of the proposed technique assessing the post-operative electrode active contact locations.",
keywords = "7 T MR imaging, deep brain stimulation, machine learning, neuromodulation, patient-specific sub-region targeting, subthalamic nucleus",
author = "Jinyoung Kim and Yuval Duchin and Shamir, {Reuben R.} and Remi Patriat and Jerrold Vitek and Noam Harel and Guillermo Sapiro",
year = "2019",
month = "2",
day = "1",
doi = "10.1002/hbm.24404",
language = "English (US)",
volume = "40",
pages = "679--698",
journal = "Human Brain Mapping",
issn = "1065-9471",
publisher = "Wiley-Liss Inc.",
number = "2",

}

TY - JOUR

T1 - Automatic localization of the subthalamic nucleus on patient-specific clinical MRI by incorporating 7 T MRI and machine learning

T2 - Application in deep brain stimulation

AU - Kim, Jinyoung

AU - Duchin, Yuval

AU - Shamir, Reuben R.

AU - Patriat, Remi

AU - Vitek, Jerrold

AU - Harel, Noam

AU - Sapiro, Guillermo

PY - 2019/2/1

Y1 - 2019/2/1

N2 - Deep brain stimulation (DBS) of the subthalamic nucleus (STN) has shown clinical potential for relieving the motor symptoms of advanced Parkinson's disease. While accurate localization of the STN is critical for consistent across-patients effective DBS, clear visualization of the STN under standard clinical MR protocols is still challenging. Therefore, intraoperative microelectrode recordings (MER) are incorporated to accurately localize the STN. However, MER require significant neurosurgical expertise and lengthen the surgery time. Recent advances in 7 T MR technology facilitate the ability to clearly visualize the STN. The vast majority of centers, however, still do not have 7 T MRI systems, and fewer have the ability to collect and analyze the data. This work introduces an automatic STN localization framework based on standard clinical MRIs without additional cost in the current DBS planning protocol. Our approach benefits from a large database of 7 T MRI and its clinical MRI pairs. We first model in the 7 T database, using efficient machine learning algorithms, the spatial and geometric dependency between the STN and its adjacent structures (predictors). Given a standard clinical MRI, our method automatically computes the predictors and uses the learned information to predict the patient-specific STN. We validate our proposed method on clinical T2W MRI of 80 subjects, comparing with experts-segmented STNs from the corresponding 7 T MRI pairs. The experimental results show that our framework provides more accurate and robust patient-specific STN localization than using state-of-the-art atlases. We also demonstrate the clinical feasibility of the proposed technique assessing the post-operative electrode active contact locations.

AB - Deep brain stimulation (DBS) of the subthalamic nucleus (STN) has shown clinical potential for relieving the motor symptoms of advanced Parkinson's disease. While accurate localization of the STN is critical for consistent across-patients effective DBS, clear visualization of the STN under standard clinical MR protocols is still challenging. Therefore, intraoperative microelectrode recordings (MER) are incorporated to accurately localize the STN. However, MER require significant neurosurgical expertise and lengthen the surgery time. Recent advances in 7 T MR technology facilitate the ability to clearly visualize the STN. The vast majority of centers, however, still do not have 7 T MRI systems, and fewer have the ability to collect and analyze the data. This work introduces an automatic STN localization framework based on standard clinical MRIs without additional cost in the current DBS planning protocol. Our approach benefits from a large database of 7 T MRI and its clinical MRI pairs. We first model in the 7 T database, using efficient machine learning algorithms, the spatial and geometric dependency between the STN and its adjacent structures (predictors). Given a standard clinical MRI, our method automatically computes the predictors and uses the learned information to predict the patient-specific STN. We validate our proposed method on clinical T2W MRI of 80 subjects, comparing with experts-segmented STNs from the corresponding 7 T MRI pairs. The experimental results show that our framework provides more accurate and robust patient-specific STN localization than using state-of-the-art atlases. We also demonstrate the clinical feasibility of the proposed technique assessing the post-operative electrode active contact locations.

KW - 7 T MR imaging

KW - deep brain stimulation

KW - machine learning

KW - neuromodulation

KW - patient-specific sub-region targeting

KW - subthalamic nucleus

UR - http://www.scopus.com/inward/record.url?scp=85055738420&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85055738420&partnerID=8YFLogxK

U2 - 10.1002/hbm.24404

DO - 10.1002/hbm.24404

M3 - Article

C2 - 30379376

AN - SCOPUS:85055738420

VL - 40

SP - 679

EP - 698

JO - Human Brain Mapping

JF - Human Brain Mapping

SN - 1065-9471

IS - 2

ER -