• Corpus ID: 239016728

DBSegment: Fast and robust segmentation of deep brain structures - Evaluation of transportability across acquisition domains

  title={DBSegment: Fast and robust segmentation of deep brain structures - Evaluation of transportability across acquisition domains},
  author={Mehri Baniasadi and Mikkel V Petersen and Jorge Gonçalves and Andreas Horn and Vanja Vlasov and Frank Hertel and Andreas Dominik Husch},
Segmenting deep brain structures from magnetic resonance images is important for patient diagnosis, surgical planning, and research. Most current state-of-the-art solutions follow a segmentation-byregistration approach, where subject MRIs are mapped to a template with well-defined segmentations. However, registration-based pipelines are time-consuming, thus, limiting their clinical use. This paper uses deep learning to provide a robust and efficient deep brain segmentation solution. The method… 

Figures and Tables from this paper


QuickNAT: A fully convolutional network for quick and accurate segmentation of neuroanatomy
QuickNAT, a fully convolutional, densely connected neural network that segments a MRI brain scan in 20 s, is introduced and achieves superior segmentation accuracy and reliability in comparison to state‐of‐the‐art methods, while being orders of magnitude faster.
Deep neural networks for anatomical brain segmentation
  • A. D. Brébisson, G. Montana
  • Computer Science, Mathematics
    2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
  • 2015
To the knowledge, this technique is the first to tackle the anatomical segmentation of the whole brain using deep neural networks and it does not require any non-linear registration of the MR images.
Generation and evaluation of an ultra-high-field atlas with applications in DBS planning
An unbiased average template is generated that provides better visualization of deep brain nuclei and an increase in accuracy over single-template and lower field strength atlases in atlas-based segmentation and DBS target localization tasks.
M-net: A Convolutional Neural Network for deep brain structure segmentation
The M-net is proposed, an end-to-end trainable Convolutional Neural Network architecture for segmenting deep (human) brain structures from Magnetic Resonance Images (MRI) and is at least 3 times faster than other methods in segmenting a new volume which is attractive for clinical use.
An improved FSL-FIRST pipeline for subcortical gray matter segmentation to study abnormal brain anatomy using quantitative susceptibility mapping (QSM).
This work proposes 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.
Deep Learning for Brain MRI Segmentation: State of the Art and Future Directions
An overview of current deep learning-based segmentation approaches for quantitative brain MRI is provided and a critical assessment of the current state and likely future developments and trends is provided.
Multi-atlas segmentation of subcortical brain structures via the AutoSeg software pipeline
A multi-atlas segmentation scheme with a novel graph-based atlas selection technique is proposed to extend a single- atlas-based segmentation toolkit entitled AutoSeg, which is an open-source, extensible C++ based software pipeline employing BatchMake for its pipeline scripting.
Hough-CNN: Deep learning for segmentation of deep brain regions in MRI and ultrasound
A novel approach to perform segmentation by leveraging the abstraction capabilities of convolutional neural networks (CNNs) based on Hough voting, which is robust, multi-region, flexible and can be easily adapted to different modalities is proposed.
Localisation of the subthalamic nucleus in MRI via convolutional neural networks for deep brain stimulation planning
A convolutional neural network is presented that is capable of learning the process of subthalamic nucleus segmentation from pre-operative clinical strength MR images with an accuracy of 58:2 ± 12:1% Dice which is within the Dice range of a one-voxel translation or dilation from the reference manual segmentation.
Improving intersubject image registration using tissue-class information benefits robustness and accuracy of multi-atlas based anatomical segmentation
The modified approach (MAPER, multi- atlas propagation with enhanced registration) extends the applicability of multi-atlas based automatic whole-brain segmentation to subjects with ventriculomegaly, as seen in normal aging as well as in numerous neurodegenerative diseases.