Automatic segmentation of the striatum and globus pallidus using MIST: Multimodal Image Segmentation Tool

Visser, E.; Keuken, Max C.; Douaud, Gwenaëlle; Gaura, Véronique; Bachoud‐Lévi, Anne‐Catherine; Rémy, Philippe; Forstmann, Birte U.; Jenkinson, Mark

doi:10.1016/j.neuroimage.2015.10.013

Cited by 70 publications

(86 citation statements)

References 57 publications

(65 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, a high quality 7 T atlas obtained from elderly subjects was registered onto the 3 T MRI template averaged on PD patient’s data (Milchenko et al, 2018). Automated methods to segment brain subcortical structures using 7 T MRI have been proposed, leveraging sufficient intensity information from multiple MR contrasts (Kim, Lenglet, Duchin, Sapiro, & Harel, 2014; Visser, Keuken, Douaud, et al, 2016; Visser, Keuken, Forstmann, et al, 2016). The clinical feasibility of 7 T MRI for localization of the STN has been previously demonstrated (Duchin, Abosch, Yacoub, Sapiro, & Harel, 2012).…”

Section: Introductionmentioning

confidence: 99%

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

Kim¹,

Duchin²,

Shamir³

et al. 2018

Human Brain Mapping

View full text Add to dashboard Cite

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.

show abstract

Section: Introductionmentioning

confidence: 99%

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

Kim¹,

Duchin²,

Shamir³

et al. 2018

Human Brain Mapping

View full text Add to dashboard Cite

show abstract

“…Recently, Cobzas et al [53] used QSM together with T1w images in a multi-atlas approach, where more than one atlas was used and the segmented labels were fused into one final segmentation, yielding higher subcortical segmentation accuracy than by applying FIRST to T1w images. Unlike the multi-atlas approach and the multimodal image segmentation tool (MIST) [54], our proposed approach of replacing the T1w image by a dedicated hybrid contrast image does not require creating atlases or modifying the FIRST algorithm including its sophisticated training data. The proposed hybrid contrast approach is not restricted to the use of susceptibility maps and can, in principle, incorporate also other image contrasts with distinct SGM contrast (e.g., R 2 * maps, T 2 or T 2 * weighted images, fractional anisotropy [FA] maps from diffusion tensor imaging [DTI]).…”

Section: Discussionmentioning

confidence: 99%

An improved FSL-FIRST pipeline for subcortical gray matter segmentation to study abnormal brain anatomy using quantitative susceptibility mapping (QSM)

Feng

Deistung

Dwyer

et al. 2017

Magnetic Resonance Imaging

View full text Add to dashboard Cite

Accurate and robust segmentation of subcortical gray matter (SGM) nuclei is required in many neuroimaging applications. FMRIB's Integrated Registration and Segmentation Tool (FIRST) is one of the most popular software tools for automated subcortical segmentation based on T1-weighted (T1w) images. In this work, we demonstrate that FIRST tends to produce inaccurate SGM segmentation results in the case of abnormal brain anatomy, such as present in atrophied brains, due to a poor spatial match of the subcortical structures with the training data in the MNI space as well as due to insufficient contrast of SGM structures on T1w images. Consequently, such deviations from the average brain anatomy may introduce analysis bias in clinical studies, which may not always be obvious and potentially remain unidentified. To improve the segmentation of subcortical nuclei, we propose to use FIRST in combination with a special Hybrid image Contrast (HC) and Non-Linear (nl) registration module (HC-nlFIRST), where the hybrid image contrast is derived from T1w images and magnetic susceptibility maps to create subcortical contrast that is similar to that in the Montreal Neurological Institute (MNI) template. In our approach, a nonlinear registration replaces FIRST’s default linear registration, yielding a more accurate alignment of the input data to the MNI template. We evaluated our method on 82 subjects with particularly abnormal brain anatomy, selected from a database of more than 2000 clinical cases. Qualitative and quantitative analyses revealed that HC-nlFIRST provides improved segmentation compared to the default FIRST method.

show abstract

“…Our method did not show better segmentation performance measured by IBSR dataset than FreeSurfer. In addition, while our approach was dependent on the training using manual segmentation, another recently developed automatic segmentation tool based on multimodal images (MIST) did not require a manually labeled training set (Visser et al, 2016), which could be flexible for various types of MR data. It also showed higher accuracy for the striatum segmentation than conventional methods though we could not compare it with our approach as our dataset has only T1-weighted images.…”

Section: Discussionmentioning

confidence: 99%

Fast and robust segmentation of the striatum using deep convolutional neural networks

Choi¹,

Jin

2016

Journal of Neuroscience Methods

View full text Add to dashboard Cite

h i g h l i g h t s• We describe a new method for stratium segmentation.• We employ two serial deep convolutional neural networks (CNN).• Segmentation accuracy of deep CNN is comparable with that of previous methods.• The processing time of the new method is much faster than previous methods. a r t i c l e i n f o a b s t r a c tBackground: Automated segmentation of brain structures is an important task in structural and functional image analysis. We developed a fast and accurate method for the striatum segmentation using deep convolutional neural networks (CNN). New method: T1 magnetic resonance (MR) images were used for our CNN-based segmentation, which require neither image feature extraction nor nonlinear transformation. We employed two serial CNN, Global and Local CNN: The Global CNN determined approximate locations of the striatum. It performed a regression of input MR images fitted to smoothed segmentation maps of the striatum. From the output volume of Global CNN, cropped MR volumes which included the striatum were extracted. The cropped MR volumes and the output volumes of Global CNN were used for inputs of Local CNN. Local CNN predicted the accurate label of all voxels. Segmentation results were compared with a widely used segmentation method, FreeSurfer. Results: Our method showed higher Dice Similarity Coefficient (DSC) (0.893 ± 0.017 vs. 0.786 ± 0.015) and precision score (0.905 ± 0.018 vs. 0.690 ± 0.022) than FreeSurfer-based striatum segmentation (p = 0.06). Our approach was also tested using another independent dataset, which showed high DSC (0.826 ± 0.038) comparable with that of FreeSurfer.Comparison with existing method Segmentation performance of our proposed method was comparable with that of FreeSurfer. The running time of our approach was approximately three seconds. Conclusion: We suggested a fast and accurate deep CNN-based segmentation for small brain structures which can be widely applied to brain image analysis.

show abstract

Automatic segmentation of the striatum and globus pallidus using MIST: Multimodal Image Segmentation Tool

Cited by 70 publications

References 57 publications

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

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

An improved FSL-FIRST pipeline for subcortical gray matter segmentation to study abnormal brain anatomy using quantitative susceptibility mapping (QSM)

Fast and robust segmentation of the striatum using deep convolutional neural networks

Contact Info

Product

Resources

About