CEREBRUM-7T: Fast and Fully Volumetric Brain Segmentation of 7 Tesla MR Volumes.
Ontology highlight
ABSTRACT:
SUBMITTER: Svanera M
PROVIDER: S-EPMC8559470 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Accurate segmentation of perivascular spaces (PVSs) is an important step for quantitative study of PVS morphology. However, since PVSs are the thin tubular structures with relatively low contrast and also the number of PVSs is often large, it is challenging and time-consuming for manual delineation of PVSs. Although several automatic/semi-automatic methods, especially the traditional learning-based approaches, have been proposed for segmentation of 3D PVSs, their performance often depends on the hand-crafted image features, as well as sophisticated preprocessing operations prior to segmentation (e.g., specially defined regions-of-interest (ROIs)). In this paper, a novel fully convolutional neural network (FCN) with no requirement of any specified hand-crafted features and ROIs is proposed for efficient segmentation of PVSs. Particularly, the original T2-weighted 7T magnetic resonance (MR) images are first filtered via a non-local Haar-transform-based line singularity representation method to enhance the thin tubular structures. Both the original and enhanced MR images are used as multi-channel inputs to complementarily provide detailed image information and enhanced tubular structural information for the localization of PVSs. Multi-scale features are then automatically learned to characterize the spatial associations between PVSs and adjacent brain tissues. Finally, the produced PVS probability maps are recursively loaded into the network as an additional channel of inputs to provide the auxiliary contextual information for further refining the segmentation results. The proposed multi-channel multi-scale FCN has been evaluated on the 7T brain MR images scanned from 20 subjects. The experimental results show its superior performance compared with several state-of-the-art methods.
| S-EPMC6430123 | biostudies-literature
Project description:Background and purposeAutomatic assessment of brain volumes is needed in research and clinical practice. Manual tracing is still the criterion standard but is time-consuming. It is important to validate the automatic tools to avoid the problems of clinical studies drawing conclusions on the basis of brain volumes estimated with methodologic errors. The objective of this study was to evaluate a new commercially available fully automatic software for MR imaging of brain volume assessment. Automatic and expert manual brain volumes were compared.Materials and methodsMR imaging (3T, axial T2 and FLAIR) was performed in 41 healthy elderly volunteers (mean age, 70 ± 6 years) and 20 patients with hydrocephalus (mean age, 73 ± 7 years). The software Q(Brain) was used to manually and automatically measure the following brain volumes: ICV, BTV, VV, and WMHV. The manual method has been previously validated and was used as the reference. Agreement between the manual and automatic methods was evaluated by using linear regression and Bland-Altman plots.ResultsThere were significant differences between the automatic and manual methods regarding all volumes. The mean differences were ICV = 49 ± 93 mL (mean ± 2SD, n = 61), BTV = 11 ± 70 mL, VV = -6 ± 10 mL, and WMHV = 2.4 ± 9 mL. The automatic calculations of brain volumes took approximately 2 minutes per investigation.ConclusionsThe automatic tool is promising and provides rapid assessment of brain volumes. However, the software needs improvement before it is incorporated into research or daily use. Manual segmentation remains the reference method.
| S-EPMC7965732 | biostudies-literature
Project description:PurposeTo demonstrate the capability of insertable inductively coupled volumetric coils for MR microscopy in a human 7T MR system.MethodsInsertable inductively coupled volume coils with diameters of 26 and 64 mm (D26 and D64 coils) targeted for monkey and mouse brain specimen sizes were designed and fabricated. These coils were placed inside the imaging volume of a transmit/receive knee coil without wired connections to the main system. Signal-to-noise ratio (SNR) evaluations were conducted with and without the insertable coils, and the g-factor maps of parallel imaging (PI) were also calculated for the D64 coil. Brain specimens were imaged using 3D T2∗ -weighted images with spatial resolution of isotropic 50 and 160 μm using D26 and D64 coils, respectively.ResultsRelative average (SD) SNRs compared with knee coil alone were 12.54 (0.30) and 2.37 (0.05) at the center for the D26 and D64 coils, respectively. The mean g-factors of PI with the D64 coil for the factor of 2 were less than 1.1 in the left-right and anterior-posterior directions, and around 1.5 in the superior-inferior direction or when the PI factor of 3 was used. Acceleration in two directions showed lower g-factors but suffered from intrinsic low SNR. Representative T2∗ -weighted images of the specimen showed structural details.ConclusionInductively coupled small diameter coils insertable to the knee coil demonstrated high SNR and modest PI capability. The concept was successfully used to visualize fine structures of the brain specimen. The insertable coils are easy to handle and enable MR microscopy in a human whole-body 7T MRI system.
| S-EPMC9297907 | biostudies-literature
Project description:PurposeThis paper describes a novel method to automatically segment the human brainstem into midbrain and pons, called labs: Landmark-based Automated Brainstem Segmentation. LABS processes high-resolution structural magnetic resonance images (MRIs) according to a revised landmark-based approach integrated with a thresholding method, without manual interaction.MethodsThis method was first tested on morphological T1-weighted MRIs of 30 healthy subjects. Its reliability was further confirmed by including neurological patients (with Alzheimer's Disease) from the ADNI repository, in whom the presence of volumetric loss within the brainstem had been previously described. Segmentation accuracies were evaluated against expert-drawn manual delineation. To evaluate the quality of LABS segmentation we used volumetric, spatial overlap and distance-based metrics.ResultsThe comparison between the quantitative measurements provided by LABS against manual segmentations revealed excellent results in healthy controls when considering either the midbrain (DICE measures higher that 0.9; Volume ratio around 1 and Hausdorff distance around 3) or the pons (DICE measures around 0.93; Volume ratio ranging 1.024-1.05 and Hausdorff distance around 2). Similar performances were detected for AD patients considering segmentation of the pons (DICE measures higher that 0.93; Volume ratio ranging from 0.97-0.98 and Hausdorff distance ranging 1.07-1.33), while LABS performed lower for the midbrain (DICE measures ranging 0.86-0.88; Volume ratio around 0.95 and Hausdorff distance ranging 1.71-2.15).ConclusionsOur study represents the first attempt to validate a new fully automated method for in vivo segmentation of two anatomically complex brainstem subregions. We retain that our method might represent a useful tool for future applications in clinical practice.
| S-EPMC3904850 | biostudies-literature
Project description:Although neuroimaging is essential for prompt and proper management of traumatic brain injury (TBI), there is a regrettable and acute lack of robust methods for the visualization and assessment of TBI pathophysiology, especially for of the purpose of improving clinical outcome metrics. Until now, the application of automatic segmentation algorithms to TBI in a clinical setting has remained an elusive goal because existing methods have, for the most part, been insufficiently robust to faithfully capture TBI-related changes in brain anatomy. This article introduces and illustrates the combined use of multimodal TBI segmentation and time point comparison using 3D Slicer, a widely-used software environment whose TBI data processing solutions are openly available. For three representative TBI cases, semi-automatic tissue classification and 3D model generation are performed to perform intra-patient time point comparison of TBI using multimodal volumetrics and clinical atrophy measures. Identification and quantitative assessment of extra- and intra-cortical bleeding, lesions, edema, and diffuse axonal injury are demonstrated. The proposed tools allow cross-correlation of multimodal metrics from structural imaging (e.g., structural volume, atrophy measurements) with clinical outcome variables and other potential factors predictive of recovery. In addition, the workflows described are suitable for TBI clinical practice and patient monitoring, particularly for assessing damage extent and for the measurement of neuroanatomical change over time. With knowledge of general location, extent, and degree of change, such metrics can be associated with clinical measures and subsequently used to suggest viable treatment options.
| S-EPMC3218448 | biostudies-literature
Project description:A novel deep learning based model called Multi-Planar Spatial Convolutional Neural Network (MPS-CNN) is proposed for effective, automated segmentation of different sub-regions viz. peritumoral edema (ED), necrotic core (NCR), enhancing and non-enhancing tumor core (ET/NET), from multi-modal MR images of the brain. An encoder-decoder type CNN model is designed for pixel-wise segmentation of the tumor along three anatomical planes (axial, sagittal, and coronal) at the slice level. These are then combined, by incorporating a consensus fusion strategy with a fully connected Conditional Random Field (CRF) based post-refinement, to produce the final volumetric segmentation of the tumor and its constituent sub-regions. Concepts, such as spatial-pooling and unpooling are used to preserve the spatial locations of the edge pixels, for reducing segmentation error around the boundaries. A new aggregated loss function is also developed for effectively handling data imbalance. The MPS-CNN is trained and validated on the recent Multimodal Brain Tumor Segmentation Challenge (BraTS) 2018 dataset. The Dice scores obtained for the validation set for whole tumor (WT :NCR/NE +ET +ED), tumor core (TC:NCR/NET +ET), and enhancing tumor (ET) are 0.90216, 0.87247, and 0.82445. The proposed MPS-CNN is found to perform the best (based on leaderboard scores) for ET and TC segmentation tasks, in terms of both the quantitative measures (viz. Dice and Hausdorff). In case of the WT segmentation it also achieved the second highest accuracy, with a score which was only 1% less than that of the best performing method.
| S-EPMC6993215 | biostudies-literature
Project description:The study objective was to investigate the performance of a dedicated convolutional neural network (CNN) optimized for wrist cartilage segmentation from 2D MR images. CNN utilized a planar architecture and patch-based (PB) training approach that ensured optimal performance in the presence of a limited amount of training data. The CNN was trained and validated in 20 multi-slice MRI datasets acquired with two different coils in 11 subjects (healthy volunteers and patients). The validation included a comparison with the alternative state-of-the-art CNN methods for the segmentation of joints from MR images and the ground-truth manual segmentation. When trained on the limited training data, the CNN outperformed significantly image-based and PB-U-Net networks. Our PB-CNN also demonstrated a good agreement with manual segmentation (Sørensen-Dice similarity coefficient [DSC] = 0.81) in the representative (central coronal) slices with a large amount of cartilage tissue. Reduced performance of the network for slices with a very limited amount of cartilage tissue suggests the need for fully 3D convolutional networks to provide uniform performance across the joint. The study also assessed inter- and intra-observer variability of the manual wrist cartilage segmentation (DSC = 0.78-0.88 and 0.9, respectively). The proposed deep learning-based segmentation of the wrist cartilage from MRI could facilitate research of novel imaging markers of wrist osteoarthritis to characterize its progression and response to therapy.
| S-EPMC7784718 | biostudies-literature
Project description:IntroductionUltra-high field MR imaging offers marked gains in signal-to-noise ratio, spatial resolution, and contrast which translate to improved pathological and anatomical sensitivity. These benefits are particularly relevant for the neonatal brain which is rapidly developing and sensitive to injury. However, experience of imaging neonates at 7T has been limited due to regulatory, safety, and practical considerations. We aimed to establish a program for safely acquiring high resolution and contrast brain images from neonates on a 7T system.MethodsImages were acquired from 35 neonates on 44 occasions (median age 39 + 6 postmenstrual weeks, range 33 + 4 to 52 + 6; median body weight 2.93 kg, range 1.57 to 5.3 kg) over a median time of 49 mins 30 s. Peripheral body temperature and physiological measures were recorded throughout scanning. Acquired sequences included T2 weighted (TSE), Actual Flip angle Imaging (AFI), functional MRI (BOLD EPI), susceptibility weighted imaging (SWI), and MR spectroscopy (STEAM).ResultsThere was no significant difference between temperature before and after scanning (p = 0.76) and image quality assessment compared favorably to state-of-the-art 3T acquisitions. Anatomical imaging demonstrated excellent sensitivity to structures which are typically hard to visualize at lower field strengths including the hippocampus, cerebellum, and vasculature. Images were also acquired with contrast mechanisms which are enhanced at ultra-high field including susceptibility weighted imaging, functional MRI, and MR spectroscopy.DiscussionWe demonstrate safety and feasibility of imaging vulnerable neonates at ultra-high field and highlight the untapped potential for providing important new insights into brain development and pathological processes during this critical phase of early life.
| S-EPMC10830693 | biostudies-literature
Project description:Large-scale longitudinal studies of regional brain volume require reliable quantification using automated segmentation and labeling. However, repeated MR scanning of the same subject, even if using the same scanner and acquisition parameters, does not result in identical images due to small changes in image orientation, changes in prescan parameters, and magnetic field instability. These differences may lead to appreciable changes in estimates of volume for different structures. This study examined scan-rescan reliability of automated segmentation algorithms for measuring several subcortical regions, using both within-day and across-day comparison sessions in a group of 23 normal participants. We found that the reliability of volume measures including percent volume difference, percent volume overlap (Dice's coefficient), and intraclass correlation coefficient (ICC), varied substantially across brain regions. Low reliability was observed in some structures such as the amygdala (ICC = 0.6), with higher reliability (ICC = 0.9) for other structures such as the thalamus and caudate. Patterns of reliability across regions were similar for automated segmentation with FSL/FIRST and FreeSurfer (longitudinal stream). Reliability was associated with the volume of the structure, the ratio of volume to surface area for the structure, the magnitude of the interscan interval, and the method of segmentation. Sample size estimates for detecting changes in brain volume for a range of likely effect sizes also differed by region. Thus, longitudinal research requires a careful analysis of sample size and choice of segmentation method combined with a consideration of the brain structure(s) of interest and the magnitude of the anticipated effects.
| S-EPMC3782252 | biostudies-literature
Project description:Arthritis patients develop hand bone loss, which leads to destruction and functional impairment of the affected joints. High resolution peripheral quantitative computed tomography (HR-pQCT) allows the quantification of volumetric bone mineral density (vBMD) and bone microstructure in vivo with an isotropic voxel size of 82 micrometres. However, image-processing to obtain bone characteristics is a time-consuming process as it requires semi-automatic segmentation of the bone. In this work, a fully automatic vBMD measurement pipeline for the metacarpal (MC) bone using deep learning methods is introduced. Based on a dataset of HR-pQCT volumes with MC measurements for 541 patients with arthritis, a segmentation network is trained. The best network achieves an intersection over union as high as 0.94 and a Dice similarity coefficient of 0.97 while taking only 33 s to process a whole patient yielding a speedup between 2.5 and 4.0 for the whole workflow. Strong correlation between the vBMD measurements of the expert and of the automatic pipeline are achieved for the average bone density with 0.999 (Pearson) and 0.996 (Spearman's rank) with [Formula: see text] for all correlations. A qualitative assessment of the network predictions and the manual annotations yields a 65.9% probability that the expert favors the network predictions. Further, the steps to integrate the pipeline into the clinical workflow are shown. In order to make these workflow improvements available to others, we openly share the code of this work.
| S-EPMC8102473 | biostudies-literature