Automatic Segmentation of the Dorsal Claustrum in Humans Using in vivo High-Resolution MRI

Berman, Shai; Schurr, Roey; Atlan, Gal; Citri, Ami; Mezer, Aviv

doi:10.1093/texcom/tgaa062

Cited by 9 publications

(13 citation statements)

References 69 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The relationship between the structural and functional aspects of the claustrum still requires extensive research to develop methods that would eliminate existing limitations. Currently, such methods are being developed, allowing for potentially larger-scale more precise studies of the claustrum [ 30 ].…”

Section: Resultsmentioning

confidence: 99%

“…The somatosensory, auditory, and visual regions are minimally connected to the cortical-claustral inputs [ 20 ]. Cortical-claustral contralateral projections are reported to be much denser than cortical-claustral ipsilateral projections [ 30 ]. The claustrum also receives projections from several subcortical structures including the mediodorsal thalamus, basolateral amygdala, and hippocampus [ 20 ].…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

The mystery of claustral neural circuits and recent updates on its role in neurodegenerative pathology

et al. 2021

View full text Add to dashboard Cite

Introduction The claustrum is a structure involved in formation of several cortical and subcortical neural microcircuits which may be involved in such functions as conscious sensations and rewarding behavior. The claustrum is regarded as a multi-modal information processing network. Pathology of the claustrum is seen in certain neurological disorders. To date, there are not enough comprehensive studies that contain accurate information regarding involvement of the claustrum in development of neurological disorders. Objective Our review aims to provide an update on claustrum anatomy, ontogenesis, cytoarchitecture, neural networks and their functional relation to the incidence of neurological diseases. Materials and methods A literature review was conducted using the Google Scholar, PubMed, NCBI MedLine, and eLibrary databases. Results Despite new methods that have made it possible to study the claustrum at the molecular, genetic and epigenetic levels, its functions and connectivity are still poorly understood. The anatomical location, relatively uniform cytoarchitecture, and vast network of connections suggest a divergent role of the claustrum in integration and processing of input information and formation of coherent perceptions. Several studies have shown changes in the appearance, structure and volume of the claustrum in neurodegenerative diseases, such as Parkinson’s disease (PD), Alzheimer’s disease (AD), autism, schizophrenia, and depressive disorders. Taking into account the structure, ontogenesis, and functions of the claustrum, this literature review offers insight into understanding the crucial role of this structure in brain function and behavior.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

The mystery of claustral neural circuits and recent updates on its role in neurodegenerative pathology

et al. 2021

View full text Add to dashboard Cite

show abstract

“…In fact, only BrainSuite, which is a tool for automated cortical parcellation and subcortical segmentation based on surface‐constrained volumetric registration of individual MR images of the brain to a manually labeled atlas, contains the claustrum as a ROI (Joshi, Shattuck, Thompson, & Leahy, 2007 ). However, this method has been shown to be rather unreliable, most likely due to the challenging anatomy of the claustrum (Berman, Schurr, Atlan, Citri, & Mezer, 2020 ). Very recently, an automated, rule‐based method using anatomical landmarks for claustrum segmentation has been published and showed improved segmentation accuracy compared to BrainSuite but still only less accuracy in comparison with manual annotations (Berman et al, 2020 ).…”

Section: Introductionmentioning

confidence: 99%

“…However, this method has been shown to be rather unreliable, most likely due to the challenging anatomy of the claustrum (Berman, Schurr, Atlan, Citri, & Mezer, 2020 ). Very recently, an automated, rule‐based method using anatomical landmarks for claustrum segmentation has been published and showed improved segmentation accuracy compared to BrainSuite but still only less accuracy in comparison with manual annotations (Berman et al, 2020 ). In conclusion, there is still the need for improved fast and reproducible, automated segmentation of the claustrum in order to enable its exploration in large MRI studies.…”

Section: Introductionmentioning

confidence: 99%

“…In the testing stage, CNNs perform automated segmentation on unseen images yielding rather high accuracies even for tiny structures such as white‐matter lesions (Li et al, 2018 ). Recently, a clustering‐based approach was proposed to segment the dorsal claustrum (Berman et al, 2020 ) and achieved <60% Dice coefficient when compared with manual segmentations. Yet DL‐based approaches, which leverage large‐scale datasets, have not been explored and can potentially improve segmentation accuracy.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automated claustrum segmentation in human brain MRI using deep learning

Menegaux

Schmitz‐Koep

et al. 2021

Human Brain Mapping

View full text Add to dashboard Cite

In the last two decades, neuroscience has produced intriguing evidence for a central role of the claustrum in mammalian forebrain structure and function. However, relatively few in vivo studies of the claustrum exist in humans. A reason for this may be the delicate and sheet-like structure of the claustrum lying between the insular cortex and the putamen, which makes it not amenable to conventional segmentation methods. Recently, Deep Learning (DL) based approaches have been successfully introduced for automated segmentation of complex, subcortical brain structures. In the following, we present a multi-view DL-based approach to segment the claustrum in T1-weighted MRI scans. We trained and evaluated the proposed method in 181 individuals, using bilateral manual claustrum annotations by an expert neuroradiologist as reference standard. Cross-validation experiments yielded median volumetric similarity, robust Hausdorff distance, and Dice score of 93.3%, 1.41 mm, and 71.8%, respectively, representing equal or superior segmentation performance compared to human intra-rater reliability. The leaveone-scanner-out evaluation showed good transferability of the algorithm to images from unseen scanners at slightly inferior performance. Furthermore, we found that DL-based claustrum segmentation benefits from multi-view information and requires a sample size of around 75 MRI scans in the training set. We conclude that the developed algorithm allows for robust automated claustrum segmentation and thus yields considerable potential for facilitating MRI-based research of the human claustrum. The software and models of our method are made publicly available.

show abstract

Efficient Claustrum Segmentation in T2-weighted Neonatal Brain MRI Using Transfer Learning from Adult Scans

Neubauer

Wendt

et al. 2022

Clin Neuroradiol

View full text Add to dashboard Cite

Purpose Intrauterine claustrum and subplate neuron development have been suggested to overlap. As premature birth typically impairs subplate neuron development, neonatal claustrum might indicate a specific prematurity impact; however, claustrum identification usually relies on expert knowledge due to its intricate structure. We established automated claustrum segmentation in newborns. Methods We applied a deep learning-based algorithm for segmenting the claustrum in 558 T2-weighted neonatal brain MRI of the developing Human Connectome Project (dHCP) with transfer learning from claustrum segmentation in T1-weighted scans of adults. The model was trained and evaluated on 30 manual bilateral claustrum annotations in neonates. Results With only 20 annotated scans, the model yielded median volumetric similarity, robust Hausdorff distance and Dice score of 95.9%, 1.12 mm and 80.0%, respectively, representing an excellent agreement between the automatic and manual segmentations. In comparison with interrater reliability, the model achieved significantly superior volumetric similarity (p = 0.047) and Dice score (p < 0.005) indicating stable high-quality performance. Furthermore, the effectiveness of the transfer learning technique was demonstrated in comparison with nontransfer learning. The model can achieve satisfactory segmentation with only 12 annotated scans. Finally, the model’s applicability was verified on 528 scans and revealed reliable segmentations in 97.4%. Conclusion The developed fast and accurate automated segmentation has great potential in large-scale study cohorts and to facilitate MRI-based connectome research of the neonatal claustrum. The easy to use models and codes are made publicly available.

show abstract

Automatic Segmentation of the Dorsal Claustrum in Humans Using in vivo High-Resolution MRI

Cited by 9 publications

References 69 publications

The mystery of claustral neural circuits and recent updates on its role in neurodegenerative pathology

The mystery of claustral neural circuits and recent updates on its role in neurodegenerative pathology

Automated claustrum segmentation in human brain MRI using deep learning

Efficient Claustrum Segmentation in T2-weighted Neonatal Brain MRI Using Transfer Learning from Adult Scans

Contact Info

Product

Resources

About