pBrain: A novel pipeline for Parkinson related brain structure segmentation

Manjón, José V.; Bertó, Alexa; Romero, José Enrique Gutiérrez; Lanuza, Enrique; Vivo-Hernando, Roberto; Robles, Fernando Aparici; Coupé, Pierrick

doi:10.1016/j.nicl.2020.102184

Cited by 13 publications

(11 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…FSL currently released a beta version of a toolbox called MIST, which is planned to provide tools to segment brainstem nuclei based on T1-weighted images in an upcoming release ( 65 ). Another possibility to segment nuclei in the brainstem and midbrain is an online processing pipeline called volBrain, which provides automated segmentation of deep gray matter nuclei, including substantia nigra, red nucleus, and subthalamic nucleus, based on T2-weighted images ( 66 ) – however, this is performed by the authors upon request, impeding large-scale applications.…”

Section: Distinct Magnetic Resonance Imaging-based Approaches For Stu...mentioning

confidence: 99%

Magnetic resonance imaging of the dopamine system in schizophrenia – A scoping review

et al. 2022

View full text Add to dashboard Cite

For decades, aberrant dopamine transmission has been proposed to play a central role in schizophrenia pathophysiology. These theories are supported by human in vivo molecular imaging studies of dopamine transmission, particularly positron emission tomography. However, there are several downsides to such approaches, for example limited spatial resolution or restriction of the measurement to synaptic processes of dopaminergic neurons. To overcome these limitations and to measure complementary aspects of dopamine transmission, magnetic resonance imaging (MRI)-based approaches investigating the macrostructure, metabolism, and connectivity of dopaminergic nuclei, i.e., substantia nigra pars compacta and ventral tegmental area, can be employed. In this scoping review, we focus on four dopamine MRI methods that have been employed in patients with schizophrenia so far: neuromelanin MRI, which is thought to measure long-term dopamine function in dopaminergic nuclei; morphometric MRI, which is assumed to measure the volume of dopaminergic nuclei; diffusion MRI, which is assumed to measure fiber-based structural connectivity of dopaminergic nuclei; and resting-state blood-oxygenation-level-dependent functional MRI, which is thought to measure functional connectivity of dopaminergic nuclei based on correlated blood oxygenation fluctuations. For each method, we describe the underlying signal, outcome measures, and downsides. We present the current state of research in schizophrenia and compare it to other disorders with either similar (psychotic) symptoms, i.e., bipolar disorder and major depressive disorder, or dopaminergic abnormalities, i.e., substance use disorder and Parkinson’s disease. Finally, we discuss overarching issues and outline future research questions.

show abstract

Section: Distinct Magnetic Resonance Imaging-based Approaches For Stu...mentioning

confidence: 99%

Magnetic resonance imaging of the dopamine system in schizophrenia – A scoping review

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Automatic segmentation software pBrain was used to automatically segment the SN, SubTN and RN from T2W scans (Manjón et al ., 2020) through the online volBrain platform (Manjón and Coupé, 2016). The software efficiently and accurately segments structures using multi-atlas label fusion technology on T2W scans as deep brain structures are more easily detectable on T2W scans than other imaging modalities (Manjón et al ., 2020). Prior to segmentation, T2W images were rigidly aligned to T1W images using FSL (FMRIB Software Library v6.0; https://fsl.fmrib.ox.ac.uk/fsl/fslwiki) FLIRT (Jenkinson et al ., 2002).…”

Section: Methodsmentioning

confidence: 99%

Midbrain structure volume, estimated myelin and functional connectivity in idiopathic generalised epilepsy

McKavanagh

Ridzuan-Allen

Kreilkamp

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Background: Previous neuroimaging studies reported functional and structural impairments of the upper basal ganglia (specifically, the striatum) in idiopathic generalised epilepsy (IGE). However, these studies often overlook lower basal ganglia structures located in and adjacent to the midbrain due to poor contrast on clinically acquired volumetric T1-weighted scans. Here, we acquired 3D isotropic T1-weighted, T2-weighted and resting state functional MR images to investigate differences in volume, estimated myelin content and functional connectivity in three midbrain and midbrain-adjacent structures in patients with IGE: the substantia nigra (SN), subthalamic nuclei (SubTN) and red nuclei (RN). Methods: A total of 33 patients with IGE (23 refractory, 10 non-refractory) and 39 age and sex matched healthy controls underwent MR imaging. The SN, SubTN and RN were automatically segmented from T2-weighted images. Estimated median myelin content for each structure was determined using a previously described T1-weighted/T2-weighted ratio method. Functional connectivity analysis between midbrain structures and the rest of the brain was performed using seed-based resting state fMRI analysis and compared between participant groups using the CONN toolbox running in SPM12 (pFDR<0.05, cluster corrected). Results: An increased volume of the right RN was found in patients with IGE relative to healthy controls. Structural volumes of the right SubTN differed between patients with non- refractory and refractory IGE. No myelin alterations of midbrain structures were found in patients with IGE or between treatment outcome groups. Functional connectivity alterations were found for all midbrain regions in patients with IGE, including significantly decreased functional connectivity between the left SN and the thalamus compared to controls, and significantly increased functional connectivity observed between the right SubTN and the left superior frontal gyrus in patients with IGE relative to controls. Connectivity alterations specific to patients with non-refractory IGE were also found. Conclusion: We report volumetric and functional connectivity alterations of midbrain and lower basal ganglia structures in patients with IGE. We postulate that an increased structural volume of the RN in patients is due to increased iron deposition that impacts on T2-weighted contrast. These findings are consistent with previous experiential work demonstrating pathophysiological abnormalities of the lower basal ganglia in animal models of generalised epilepsy.

show abstract

“…The volBrain system is primarily based on a multi-atlas, patch-based segmentation method and utilizes training libraries as implemented in the volBrain online platform. The volBrain web platform has also added several brain structure segmentation methods such as CERES (CEREbellum Segmentation), 38 HIPS (HIPpocampus Segmentation), 39 and pBrain (Parkinson related deep nucleus segmentation), 40 which are all available from the volBrain platform.…”

Section: Major Software Tools and Their Methodologymentioning

confidence: 99%

A Review of Publicly Available Automatic Brain Segmentation Methodologies, Machine Learning Models, Recent Advancements, and Their Comparison

Singh

2021

Annals of Neurosciences

View full text Add to dashboard Cite

Background: The noninvasive study of the structure and functions of the brain using neuroimaging techniques is increasingly being used for its clinical and research perspective. The morphological and volumetric changes in several regions and structures of brains are associated with the prognosis of neurological disorders such as Alzheimer’s disease, epilepsy, schizophrenia, etc. and the early identification of such changes can have huge clinical significance. The accurate segmentation of three-dimensional brain magnetic resonance images into tissue types (i.e., grey matter, white matter, cerebrospinal fluid) and brain structures, thus, has huge importance as they can act as early biomarkers. The manual segmentation though considered the “gold standard” is time-consuming, subjective, and not suitable for bigger neuroimaging studies. Several automatic segmentation tools and algorithms have been developed over the years; the machine learning models particularly those using deep convolutional neural network (CNN) architecture are increasingly being applied to improve the accuracy of automatic methods. Purpose: The purpose of the study is to understand the current and emerging state of automatic segmentation tools, their comparison, machine learning models, their reliability, and shortcomings with an intent to focus on the development of improved methods and algorithms. Methods: The study focuses on the review of publicly available neuroimaging tools, their comparison, and emerging machine learning models particularly those based on CNN architecture developed and published during the last five years. Conclusion: Several software tools developed by various research groups and made publicly available for automatic segmentation of the brain show variability in their results in several comparison studies and have not attained the level of reliability required for clinical studies. The machine learning models particularly three dimensional fully convolutional network models can provide a robust and efficient alternative with relation to publicly available tools but perform poorly on unseen datasets. The challenges related to training, computation cost, reproducibility, and validation across distinct scanning modalities for machine learning models need to be addressed.

show abstract

pBrain: A novel pipeline for Parkinson related brain structure segmentation

Cited by 13 publications

References 26 publications

Magnetic resonance imaging of the dopamine system in schizophrenia – A scoping review

Magnetic resonance imaging of the dopamine system in schizophrenia – A scoping review

Midbrain structure volume, estimated myelin and functional connectivity in idiopathic generalised epilepsy

A Review of Publicly Available Automatic Brain Segmentation Methodologies, Machine Learning Models, Recent Advancements, and Their Comparison

Contact Info

Product

Resources

About