scholarly journals Inferring Functional Neural Connectivity with Deep Residual Convolutional Networks

2017 ◽  
Author(s):  
Timothy W. Dunn ◽  
Peter K. Koo
Keyword(s):  
Network Architecture ◽  
Correlation Coefficients ◽  
Real Data ◽  
Future Application ◽  
Imaging Data ◽  
Multiple Gpus ◽  
Convolutional Networks ◽  
Model Free ◽  
Brain Imaging Data

Measuring synaptic connectivity in large neuronal populations remains a major goal of modern neuroscience. While this connectivity is traditionally revealed by anatomical methods such as electron microscopy, an efficient alternative is to computationally infer functional connectivity from recordings of neural activity. However, these statistical techniques still require further refinement before they can be reliably applied to real data. Here, we report significant improvements to a deep learning method for functional connectomics, as assayed on synthetic ChaLearn Connectomics data. The method, which integrates recent advances in convolutional neural network architecture and model-free partial correlation coefficients, outperforms published methods on competition data and can achieve over 90% precision at 1% recall on validation datasets. This suggests that future application of the model to in vivo whole-brain imaging data in larval zebrafish could reliably recover on the order of 106 synaptic connections with a 10% false discovery rate. The model also generalizes to networks with different underlying connection probabilities and should scale well when parallelized across multiple GPUs. The method offers real potential as a statistical complement to existing experiments and circuit hypotheses in neuroscience.

Dynamics of the Tracheal Airway and Its Influences on Respiratory Airflows: An Exemplar Study

2019 ◽  
Vol 141 (11) ◽  
Author(s):  
Bora Sul ◽  
Talissa Altes ◽  
Kai Ruppert ◽  
Kun Qing ◽  
Daniel S. Hariprasad ◽  
...  
Keyword(s):  
Morphological Changes ◽  
Minute Ventilation ◽  
Correlation Coefficients ◽  
Dynamic Imaging ◽  
Imaging Data ◽  
Cross Sectional ◽  
Mild Conditions ◽  
Large Airways ◽  
Magnetic Resonance Imaging Mri

Respiration is a dynamic process accompanied by morphological changes in the airways. Although deformation of large airways is expected to exacerbate pulmonary disease symptoms by obstructing airflow during increased minute ventilation, its quantitative effects on airflow characteristics remain unclear. Here, we used in vivo dynamic imaging and examined the effects of tracheal deformation on airflow characteristics under different conditions based on imaging data from a single healthy volunteer. First, we measured tracheal deformation profiles of a healthy lung using magnetic resonance imaging (MRI) during forced exhalation, which we simulated to characterize the subject-specific airflow patterns. Subsequently, for both inhalation and exhalation, we compared the airflows when the modeled deformation in tracheal cross-sectional area was 0% (rigid), 33% (mild), 50% (moderate), or 75% (severe). We quantified differences in airflow patterns between deformable and rigid airways by computing the correlation coefficients (R) and the root-mean-square of differences (Drms) between their velocity contours. For both inhalation and exhalation, airflow patterns were similar in all branches between the rigid and mild conditions (R > 0.9; Drms < 32%). However, airflow characteristics in the moderate and severe conditions differed markedly from those in the rigid and mild conditions in all lung branches, particularly for inhalation (moderate: R > 0.1, Drms < 76%; severe: R > 0.2, Drms < 96%). Our exemplar study supports the use of a rigid airway assumption to compute flows for mild deformation. For moderate or severe deformation, however, dynamic contraction should be considered, especially during inhalation, to accurately predict airflow and elucidate the underlying pulmonary pathology.

scholarly journals Increased contrast of the grey-white matter boundary in the motor, visual and auditory areas in Autism Spectrum Disorders

2019 ◽  
Author(s):  
Marion Fouquet ◽  
Nicolas Traut ◽  
Anita Beggiato ◽  
Richard Delorme ◽  
Thomas Bourgeron ◽  
...  
Keyword(s):  
White Matter ◽  
Data Exchange ◽  
Primary Motor Cortex ◽  
Autism Spectrum ◽  
Imaging Data ◽  
Sensory Motor ◽  
Magnetic Resonance Imaging Mri ◽  
Brain Imaging Data

AbstractThe contrast of the interface between the neocortical grey matter and the white matter is emerging as an important neuroimaging phenotype for several brain disorders. To date, a single in vivo study has analysed the cortical grey-to-white matter percent contrast (GWPC) on Magnetic Resonance Imaging (MRI), and has shown a significant decrease of this contrast in several areas in individuals with Autism Spectrum Disorder (ASD). Our goal was to replicate this study across a larger cohort, using the multicenter data from the Autism Brain Imaging Data Exchange 1 and 2 gathering data from 2,148 subjects. Multiple linear regression was used to study the effect of the diagnosis of ASD on the GWPC. Contrary to the first study, we found a statistically significant increase of GWPC among individuals with ASD in left auditory and bilateral visual sensory areas, as well as in the left primary motor cortex. These results were still statistically significant after inclusion of cortical thickness as covariate. There are numerous reports of sensory-motor atypicalities in patients with ASD, which may be the reason for the differences in GWPC that we observed. Further investigation could help us determine the potential role of a defect or a delay in intra-cortical myelination of sensory-motor regions in ASD. Code: https://github.com/neuroanatomy/GWPC.

scholarly journals Active Learning of Cortical Connectivity from Two-Photon Imaging Data

2018 ◽  
Author(s):  
Martín Bertrán ◽  
Natalia Martínez ◽  
Ye Wang ◽  
David Dunson ◽  
Guillermo Sapiro ◽  
...  
Keyword(s):  
Active Learning ◽  
Small World ◽  
Real Data ◽  
Sensory Stimulation ◽  
Imaging Data ◽  
Population Activity ◽  
Two Photon ◽  
Photon Imaging ◽  
Two Photon Imaging

AbstractUnderstanding how groups of neurons interact within a network is a fundamental question in system neuroscience. Instead of passively observing the ongoing activity of a network, we can typically perturb its activity, either by external sensory stimulation or directly via techniques such as two-photon optogenetics. A natural question is how to use such perturbations to identify the connectivity of the network efficiently. Here we introduce a method to infer sparse connectivity graphs from in-vivo, two-photon imaging of population activity in response to external stimuli. A novel aspect of the work is the introduction of a recommended distribution, incrementally learned from the data, to optimally refine the inferred network.. Unlike existing system identification techniques, this “active learning” method automatically focuses its attention on key undiscovered areas of the network, instead of targeting global uncertainty indicators like parameter variance. We show how active learning leads to faster inference while, at the same time, provides confidence intervals for the network parameters. We present simulations on artificial small-world networks to validate the methods and apply the method to real data. Analysis of frequency of motifs recovered show that cortical networks are consistent with a small-world topology model.

scholarly journals ABLE: an Activity-Based Level Set Segmentation Algorithm for Two-Photon Calcium Imaging Data

2017 ◽  
Author(s):  
Stephanie Reynolds ◽  
Therese Abrahamsson ◽  
Renaud Schuck ◽  
P. Jesper Sjöström ◽  
Simon R. Schultz ◽  
...  
Keyword(s):  
Level Set ◽  
Calcium Imaging ◽  
Cell Shape ◽  
Active Contours ◽  
Real Data ◽  
Imaging Data ◽  
Similar Time ◽  
Two Photon

AbstractWe present an algorithm for detecting the location of cells from two-photon calcium imaging data. In our framework, multiple coupled active contours evolve, guided by a model-based cost function, to identify cell boundaries. An active contour seeks to partition a local region into two subregions, a cell interior and ex-terior, in which all pixels have maximally ‘similar’ time courses. This simple, local model allows contours to be evolved predominantly independently. When contours are sufficiently close, their evolution is coupled, in a manner that permits overlap. We illustrate the ability of the proposed method to demix overlapping cells on real data. The proposed framework is flexible, incorporating no prior information regarding a cell’s morphology or stereotypical temporal activity, which enables the detection of cells with diverse properties. We demonstrate algorithm performance on a challenging mouse in vitro dataset, containing synchronously spiking cells, and a manually labelled mouse in vivo dataset, on which ABLE achieves a 67.5% success rate.Significance statementTwo-photon calcium imaging enables the study of brain activity during learning and behaviour at single-cell resolution. To decode neuronal spiking activity from the data, algorithms are first required to detect the location of cells in the video. It is still common for scientists to perform this task manually, as the heterogeneity in cell shape and frequency of cellular overlap impede automatic segmentation algorithms. We developed a versatile algorithm based on a popular image segmentation approach (the Level Set Method) and demonstrated its capability to overcome these challenges. We include no assumptions on cell shape or stereotypical temporal activity. This lends our framework the flexibility to be applied to new datasets with minimal adjustment.

[18F]-florbetaben PET/CT Imaging in the Alzheimer’s Disease Mouse Model APPswe/PS1dE9

2018 ◽  
Vol 16 (1) ◽  
pp. 49-55 ◽  
Author(s):  
J. Stenzel ◽  
C. Rühlmann ◽  
T. Lindner ◽  
S. Polei ◽  
S. Teipel ◽  
...  
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Mouse Model ◽  
New Drugs ◽  
Imaging Data ◽  
Wild Type ◽  
Preclinical Research ◽  
Standardized Uptake Values ◽  
Pet Ct

Background: Positron-emission-tomography (PET) using 18F labeled florbetaben allows noninvasive in vivo-assessment of amyloid-beta (Aβ), a pathological hallmark of Alzheimer’s disease (AD). In preclinical research, [<sup>18</sup>F]-florbetaben-PET has already been used to test the amyloid-lowering potential of new drugs, both in humans and in transgenic models of cerebral amyloidosis. The aim of this study was to characterize the spatial pattern of cerebral uptake of [<sup>18</sup>F]-florbetaben in the APPswe/ PS1dE9 mouse model of AD in comparison to histologically determined number and size of cerebral Aβ plaques. Methods: Both, APPswe/PS1dE9 and wild type mice at an age of 12 months were investigated by smallanimal PET/CT after intravenous injection of [<sup>18</sup>F]-florbetaben. High-resolution magnetic resonance imaging data were used for quantification of the PET data by volume of interest analysis. The standardized uptake values (SUVs) of [<sup>18</sup>F]-florbetaben in vivo as well as post mortem cerebral Aβ plaque load in cortex, hippocampus and cerebellum were analyzed. Results: Visual inspection and SUVs revealed an increased cerebral uptake of [<sup>18</sup>F]-florbetaben in APPswe/ PS1dE9 mice compared with wild type mice especially in the cortex, the hippocampus and the cerebellum. However, SUV ratios (SUVRs) relative to cerebellum revealed only significant differences in the hippocampus between the APPswe/PS1dE9 and wild type mice but not in cortex; this differential effect may reflect the lower plaque area in the cortex than in the hippocampus as found in the histological analysis. Conclusion: The findings suggest that histopathological characteristics of Aβ plaque size and spatial distribution can be depicted in vivo using [<sup>18</sup>F]-florbetaben in the APPswe/PS1dE9 mouse model.

scholarly journals An Ad Hoc Random Initialization Deep Neural Network Architecture for Discriminating Malignant Breast Cancer Lesions in Mammographic Images

2019 ◽  
Vol 2019 ◽  
pp. 1-9 ◽  
Author(s):  
Andrea Duggento ◽  
Marco Aiello ◽  
Carlo Cavaliere ◽  
Giuseppe L. Cascella ◽  
Davide Cascella ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Network Architecture ◽  
Ad Hoc ◽  
False Negative ◽  
Selection Criterion ◽  
Current Status ◽  
Clinical Image ◽  
Imaging Data ◽  
Breast Cancer Death ◽  
Random Initialization

Breast cancer is one of the most common cancers in women, with more than 1,300,000 cases and 450,000 deaths each year worldwide. In this context, recent studies showed that early breast cancer detection, along with suitable treatment, could significantly reduce breast cancer death rates in the long term. X-ray mammography is still the instrument of choice in breast cancer screening. In this context, the false-positive and false-negative rates commonly achieved by radiologists are extremely arduous to estimate and control although some authors have estimated figures of up to 20% of total diagnoses or more. The introduction of novel artificial intelligence (AI) technologies applied to the diagnosis and, possibly, prognosis of breast cancer could revolutionize the current status of the management of the breast cancer patient by assisting the radiologist in clinical image interpretation. Lately, a breakthrough in the AI field has been brought about by the introduction of deep learning techniques in general and of convolutional neural networks in particular. Such techniques require no a priori feature space definition from the operator and are able to achieve classification performances which can even surpass human experts. In this paper, we design and validate an ad hoc CNN architecture specialized in breast lesion classification from imaging data only. We explore a total of 260 model architectures in a train-validation-test split in order to propose a model selection criterion which can pose the emphasis on reducing false negatives while still retaining acceptable accuracy. We achieve an area under the receiver operatic characteristics curve of 0.785 (accuracy 71.19%) on the test set, demonstrating how an ad hoc random initialization architecture can and should be fine tuned to a specific problem, especially in biomedical applications.

scholarly journals Fractional ridge regression: a fast, interpretable reparameterization of ridge regression

GigaScience ◽  
2020 ◽  
Vol 9 (12) ◽  
Author(s):  
Ariel Rokem ◽  
Kendrick Kay
Keyword(s):  
Ridge Regression ◽  
Large Scale ◽  
Imaging Data ◽  
Regularization Technique ◽  
Large Scale Data ◽  
Novel Approach ◽  
Manual Exploration ◽  
L2 Norm ◽  
Software Implementations ◽  
Brain Imaging Data

Abstract Background Ridge regression is a regularization technique that penalizes the L2-norm of the coefficients in linear regression. One of the challenges of using ridge regression is the need to set a hyperparameter (α) that controls the amount of regularization. Cross-validation is typically used to select the best α from a set of candidates. However, efficient and appropriate selection of α can be challenging. This becomes prohibitive when large amounts of data are analyzed. Because the selected α depends on the scale of the data and correlations across predictors, it is also not straightforwardly interpretable. Results The present work addresses these challenges through a novel approach to ridge regression. We propose to reparameterize ridge regression in terms of the ratio γ between the L2-norms of the regularized and unregularized coefficients. We provide an algorithm that efficiently implements this approach, called fractional ridge regression, as well as open-source software implementations in Python and matlab (https://github.com/nrdg/fracridge). We show that the proposed method is fast and scalable for large-scale data problems. In brain imaging data, we demonstrate that this approach delivers results that are straightforward to interpret and compare across models and datasets. Conclusion Fractional ridge regression has several benefits: the solutions obtained for different γ are guaranteed to vary, guarding against wasted calculations; and automatically span the relevant range of regularization, avoiding the need for arduous manual exploration. These properties make fractional ridge regression particularly suitable for analysis of large complex datasets.

scholarly journals Effectiveness and mechanisms of adipose-derived stem cell therapy in animal models of Parkinson’s disease: a systematic review and meta-analysis

2021 ◽  
Vol 10 (1) ◽  
Author(s):  
Keya Li ◽  
Xinyue Li ◽  
Guiying Shi ◽  
Xuepei Lei ◽  
Yiying Huang ◽  
...  
Keyword(s):  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Animal Models ◽  
Therapeutic Option ◽  
Meta Analysis ◽  
Future Application ◽  
Neuroprotective Effects ◽  
Standard Mean Difference ◽  
Study Characteristics

AbstractAnimal models provide an opportunity to assess the optimal treatment way and the underlying mechanisms of direct clinical application of adipose-derived stem cells (ADSCs). Previous studies have evaluated the effects of primitive and induced ADSCs in animal models of Parkinson’s disease (PD). Here, eight databases were systematically searched for studies on the effects and in vivo changes caused by ADSC intervention. Quality assessment was conducted using a 10-item risk of bias tool. For the subsequent meta-analysis, study characteristics were extracted and effect sizes were computed. Ten out of 2324 published articles (n = 169 animals) were selected for further meta-analysis. After ADSC therapy, the rotation behavior (10 experiments, n = 156 animals) and rotarod performance (3 experiments, n = 54 animals) were improved (P < 0.000 01 and P = 0.000 3, respectively). The rotation behavior test reflected functional recovery, which may be due to the neurogenesis from neuronally differentiated ADSCs, resulting in a higher pooled effect size of standard mean difference (SMD) (− 2.59; 95% CI, − 3.57 to − 1.61) when compared to that of primitive cells (− 2.18; 95% CI, − 3.29 to − 1.07). Stratified analyses by different time intervals indicated that ADSC intervention exhibited a long-term effect. Following the transplantation of ADSCs, tyrosine hydroxylase-positive neurons recovered in the lesion area with pooled SMD of 13.36 [6.85, 19.86]. Transplantation of ADSCs is a therapeutic option that shows long-lasting effects in animal models of PD. The potential mechanisms of ADSCs involve neurogenesis and neuroprotective effects. The standardized induction of neural form of transplanted ADSCs can lead to a future application in clinical practice.

scholarly journals The relationship between hippocampal-dependent task performance and hippocampal grey matter myelination and iron content

2021 ◽  
Vol 5 ◽  
pp. 239821282110119
Author(s):  
Ian A. Clark ◽  
Martina F. Callaghan ◽  
Nikolaus Weiskopf ◽  
Eleanor A. Maguire
Keyword(s):  
Individual Differences ◽  
Autobiographical Memory ◽  
Task Performance ◽  
Iron Content ◽  
Grey Matter ◽  
Cognitive Task ◽  
Spatial Navigation ◽  
Imaging Data ◽  
Future Thinking

Individual differences in scene imagination, autobiographical memory recall, future thinking and spatial navigation have long been linked with hippocampal structure in healthy people, although evidence for such relationships is, in fact, mixed. Extant studies have predominantly concentrated on hippocampal volume. However, it is now possible to use quantitative neuroimaging techniques to model different properties of tissue microstructure in vivo such as myelination and iron. Previous work has linked such measures with cognitive task performance, particularly in older adults. Here we investigated whether performance on scene imagination, autobiographical memory, future thinking and spatial navigation tasks was associated with hippocampal grey matter myelination or iron content in young, healthy adult participants. Magnetic resonance imaging data were collected using a multi-parameter mapping protocol (0.8 mm isotropic voxels) from a large sample of 217 people with widely-varying cognitive task scores. We found little evidence that hippocampal grey matter myelination or iron content were related to task performance. This was the case using different analysis methods (voxel-based quantification, partial correlations), when whole brain, hippocampal regions of interest, and posterior:anterior hippocampal ratios were examined, and across different participant sub-groups (divided by gender and task performance). Variations in hippocampal grey matter myelin and iron levels may not, therefore, help to explain individual differences in performance on hippocampal-dependent tasks, at least in young, healthy individuals.

Sign in / Sign up

Export Citation Format

Share Document