Nonlinear manifold learning in functional magnetic resonance imaging uncovers a low-dimensional space of brain dynamics.
Ontology highlight
ABSTRACT:
SUBMITTER: Gao S
PROVIDER: S-EPMC8410525 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Purpose:To develop generic optimization strategies for image reconstruction using graphical processing units (GPUs) in magnetic resonance imaging (MRI) and to exemplarily report on our experience with a highly accelerated implementation of the nonlinear inversion (NLINV) algorithm for dynamic MRI with high frame rates. Methods:The NLINV algorithm is optimized and ported to run on a multi-GPU single-node server. The algorithm is mapped to multiple GPUs by decomposing the data domain along the channel dimension. Furthermore, the algorithm is decomposed along the temporal domain by relaxing a temporal regularization constraint, allowing the algorithm to work on multiple frames in parallel. Finally, an autotuning method is presented that is capable of combining different decomposition variants to achieve optimal algorithm performance in different imaging scenarios. Results:The algorithm is successfully ported to a multi-GPU system and allows online image reconstruction with high frame rates. Real-time reconstruction with low latency and frame rates up to 30 frames per second is demonstrated. Conclusion:Novel parallel decomposition methods are presented which are applicable to many iterative algorithms for dynamic MRI. Using these methods to parallelize the NLINV algorithm on multiple GPUs, it is possible to achieve online image reconstruction with high frame rates.
| S-EPMC5804376 | biostudies-literature
Project description:Multimodal integration between mass spectrometry imaging (MSI) and radiology-established modalities such as magnetic resonance imaging (MRI) would allow the investigations of key questions in complex biological systems such as the central nervous system. Such integration would provide complementary multiscale data to bridge the gap between molecular and anatomical phenotypes, potentially revealing new insights into molecular mechanisms underlying anatomical pathologies presented on MRI. Automatic coregistration between 3D MSI/MRI is a computationally challenging process due to dimensional complexity, MSI data sparsity, lack of direct spatial-correspondences, and nonlinear tissue deformation. Here, we present a new computational approach based on stochastic neighbor embedding to nonlinearly align 3D MSI to MRI data, identify and reconstruct biologically relevant molecular patterns in 3D, and fuse the MSI datacube to the MRI space. We demonstrate our method using multimodal high-spectral resolution matrix-assisted laser desorption ionization (MALDI) 9.4 T MSI and 7 T in vivo MRI data, acquired from a patient-derived, xenograft mouse brain model of glioblastoma following administration of the EGFR inhibitor drug of Erlotinib. Results show the distribution of some identified molecular ions of the EGFR inhibitor erlotinib, a phosphatidylcholine lipid, and cholesterol, which were reconstructed in 3D and mapped to the MRI space. The registration quality was evaluated on two normal mouse brains using the Dice coefficient for the regions of brainstem, hippocampus, and cortex. The method is generic and can therefore be applied to hyperspectral images from different mass spectrometers and integrated with other established in vivo imaging modalities such as computed tomography (CT) and positron emission tomography (PET).
| S-EPMC6691508 | biostudies-literature
Project description:BackgroundModern developments in single-cell sequencing technologies enable broad insights into cellular state. Single-cell RNA sequencing (scRNA-seq) can be used to explore cell types, states, and developmental trajectories to broaden our understanding of cellular heterogeneity in tissues and organs. Analysis of these sparse, high-dimensional experimental results requires dimension reduction. Several methods have been developed to estimate low-dimensional embeddings for filtered and normalized single-cell data. However, methods have yet to be developed for unfiltered and unnormalized count data that estimate uncertainty in the low-dimensional space. We present a nonlinear latent variable model with robust, heavy-tailed error and adaptive kernel learning to estimate low-dimensional nonlinear structure in scRNA-seq data.ResultsGene expression in a single cell is modeled as a noisy draw from a Gaussian process in high dimensions from low-dimensional latent positions. This model is called the Gaussian process latent variable model (GPLVM). We model residual errors with a heavy-tailed Student's t-distribution to estimate a manifold that is robust to technical and biological noise found in normalized scRNA-seq data. We compare our approach to common dimension reduction tools across a diverse set of scRNA-seq data sets to highlight our model's ability to enable important downstream tasks such as clustering, inferring cell developmental trajectories, and visualizing high throughput experiments on available experimental data.ConclusionWe show that our adaptive robust statistical approach to estimate a nonlinear manifold is well suited for raw, unfiltered gene counts from high-throughput sequencing technologies for visualization, exploration, and uncertainty estimation of cell states.
| S-EPMC7374962 | biostudies-literature
Project description:INTRODUCTION:Visualization of the retroplacental clear space (RPCS) may provide critical insight into the development of abnormally invasive placenta (AIP). In this pre-clinical study, we characterized the appearance of the RPCS on magnetic resonance imaging (MRI) during the second half of gestation using a liposomal gadolinium contrast agent (liposomal-Gd). MATERIALS AND METHODS:Studies were performed in fifteen pregnant C57BL/6 mice at 10, 12, 14, 16, and 18 days of gestation. MRI was performed on a 1T permanent magnet scanner. Pre-contrast and post-contrast images were acquired using T1-weighted gradient-recalled echo (T1w-GRE) and T2-weighted fast spin echo (T2w-FSE) sequences. Animals were euthanized after imaging and feto-placental units harvested for histological examination. Visualization of the RPCS was scored by a maternal-fetal radiologist and quantified by measuring the contrast-to-noise ratio (CNR) on T1w images. Feto-placental features were segmented for analysis of volumetric changes during gestation. RESULTS:Contrast-enhanced T1w images enabled the visualization of structural changes in placental development between days 10-18 of gestation. Although the placental margin on the fetal side was clearly visible at all time points, the RPCS was partially visible at day 10 of gestation, and clearly visible by day 12. Hematoxylin and eosin (H&E) staining of the placental tissue corroborated MRI findings of structural and morphological changes in the placenta. CONCLUSIONS:Contrast-enhanced MR imaging using liposomal-Gd enabled adequate visualization of the retroplacental clear space starting at day 12 of gestation. The agent also enabled characterization of placental structure and morphological changes through gestation.
| S-EPMC6400291 | biostudies-literature
Project description:Genome wide DNA methylation profiling of normal and tumour prostate samples. The Illumina Infinium MethylationEPIC Human DNA methylation oligonucleotide beads was used to obtain DNA methylation profiles across approximately 850,000 CpGs. Comparative assessment was carried out.
2018-12-01 | GSE101908 | GEO
Project description:Despite maximally-safe resection of the MRI-defined contrast-enhanced (CE) central tumor area and chemo-radiotherapy, most glioblastoma patients relapse within one year in peritumor FLAIR regions. Spectroscopic MRI (MRSI) can discriminate metabolic tumor areas with higher recurrence potential as CNI+ regions (Choline/N-acetyl-aspartate Index>2) can predict relapse sites. As relapses are mainly imputed to glioblastoma stem-like cells (GSC), CNI+ areas might be GSC-enriched. We conducted a prospective trial in 16 GBM patients subjected to preoperative MRSI/MRI and surgery/chemo-radiotherapy to investigate GSC content in CNI+ versus CNI- biopsies from CE/FLAIR. Biopsy characterization by RNAseq revealed that FLAIR/CNI+ areas were enriched in stem-related gene signature, but also in pathways related to DNA repair, adhesion/migration and mitochondrial bioenergetics.
2023-11-03 | GSE239379 | GEO
Project description:Extraction of murine cardiac functional parameters on a beat-by-beat basis is limited with the existing imaging modalities due to insufficient three-dimensional temporal resolution. Faster volumetric imaging methods enabling in vivo characterization of functional parameters are poised to advance cardiovascular research and provide a better understanding of the mechanisms underlying cardiac diseases. We present a new approach based on analyzing contrast-enhanced optoacoustic (OA) images acquired at high volumetric frame rate without using cardiac gating or other approaches for motion correction. We apply an acute murine myocardial infarction model optimized for acquisition of artifact-free optoacoustic imaging data to study cardiovascular hemodynamics. Infarcted hearts (n = 21) could be clearly differentiated from healthy controls (n = 9) based on a significantly higher pulmonary transit time (PTT) (2.25 [2.00-2.41] s versus 1.34 [1.25-1.67] s, p = 0.0235), while no statistically significant difference was observed in the heart rate (318 [252-361] bpm versus 264 [252-320] bpm, p = 0.3129). Nevertheless, nonlinear heartbeat dynamics was stronger in the healthy hearts, as evidenced by the third harmonic component in the heartbeat spectra. MRI data acquired from the same mice further revealed that the PTT increases with the size of infarction and similarly increases with reduced ejection fraction. Moreover, an inverse relationship between infarct PTT and time post-surgery was found, which suggests the occurrence of cardiac healing. In combination with the proven ability of optoacoustics to track targeted probes within the injured myocardium, our method can depict cardiac anatomy, function, and molecular signatures, with both high spatial and temporal resolution. Volumetric four-dimensional optoacoustic characterization of cardiac dynamics with supreme temporal resolution can capture cardiovascular dynamics on a beat-by-beat basis in mouse models of myocardial ischemia.
| S-EPMC5695143 | biostudies-literature
Project description:In ferromagnetic nanostructures domain walls as emergent entities separate uniformly magnetized regions. They are describable as quasi particles and can be controlled by magnetic fields or spin-polarized currents. Below critical driving forces domain walls are rigid conserving their spin structure. Like other quasi particles internal excitations influence the domain wall dynamics above a critical velocity known as the Walker breakdown. This complex nonlinear motion has not been observed directly. Here we present direct time-resolved x-ray microscopy of structural transformations of domain walls during motion. Although governed by nonlinear dynamics the displacement of the wall on the observed time scale can still be described by an analytical model. Using a reduced dynamical domain-wall width the model enables us to determine the mass of a vortex wall experimentally. Further we observe the creation and the mutual annihilation of domain walls. The intrinsic nanometer length and nanosecond time-scales are determined directly.
| S-EPMC3636512 | biostudies-literature
Project description:(1) Background: Transfer learning refers to machine learning techniques that focus on acquiring knowledge from related tasks to improve generalization in the tasks of interest. In magnetic resonance imaging (MRI), transfer learning is important for developing strategies that address the variation in MR images from different imaging protocols or scanners. Additionally, transfer learning is beneficial for reutilizing machine learning models that were trained to solve different (but related) tasks to the task of interest. The aim of this review is to identify research directions, gaps in knowledge, applications, and widely used strategies among the transfer learning approaches applied in MR brain imaging; (2) Methods: We performed a systematic literature search for articles that applied transfer learning to MR brain imaging tasks. We screened 433 studies for their relevance, and we categorized and extracted relevant information, including task type, application, availability of labels, and machine learning methods. Furthermore, we closely examined brain MRI-specific transfer learning approaches and other methods that tackled issues relevant to medical imaging, including privacy, unseen target domains, and unlabeled data; (3) Results: We found 129 articles that applied transfer learning to MR brain imaging tasks. The most frequent applications were dementia-related classification tasks and brain tumor segmentation. The majority of articles utilized transfer learning techniques based on convolutional neural networks (CNNs). Only a few approaches utilized clearly brain MRI-specific methodology, and considered privacy issues, unseen target domains, or unlabeled data. We proposed a new categorization to group specific, widely-used approaches such as pretraining and fine-tuning CNNs; (4) Discussion: There is increasing interest in transfer learning for brain MRI. Well-known public datasets have clearly contributed to the popularity of Alzheimer's diagnostics/prognostics and tumor segmentation as applications. Likewise, the availability of pretrained CNNs has promoted their utilization. Finally, the majority of the surveyed studies did not examine in detail the interpretation of their strategies after applying transfer learning, and did not compare their approach with other transfer learning approaches.
| S-EPMC8321322 | biostudies-literature
Project description:With the advent of MR guided radiotherapy, internal organ motion can be imaged simultaneously during treatment. In this study, we evaluate the feasibility of pancreas MRI segmentation using state-of-the-art segmentation methods.T2 weighted HASTE and T1 weighted VIBE images were acquired on 3 patients and 2 healthy volunteers for a total of 12 imaging volumes. A novel dictionary learning (DL) method was used to segment the pancreas and compared to t mean-shift merging (MSM), distance regularized level set (DRLS), graph cuts (GC) and the segmentation results were compared to manual contours using Dice's index (DI), Hausdorff distance and shift of the-center-of-the-organ (SHIFT).All VIBE images were successfully segmented by at least one of the auto-segmentation method with DI >0.83 and SHIFT ≤2 mm using the best automated segmentation method. The automated segmentation error of HASTE images was significantly greater. DL is statistically superior to the other methods in Dice's overlapping index. For the Hausdorff distance and SHIFT measurement, DRLS and DL performed slightly superior to the GC method, and substantially superior to MSM. DL required least human supervision and was faster to compute.Our study demonstrated potential feasibility of automated segmentation of the pancreas on MRI images with minimal human supervision at the beginning of imaging acquisition. The achieved accuracy is promising for organ localization.
| S-EPMC5113135 | biostudies-other