Neuroinformatics最新文献

The problem at hand is the significant global health challenge posed by children's diseases, where timely and accurate diagnosis is crucial for effective treatment and management. Conventional diagnosis techniques are typical, use tedious processes and generate inaccurate results since they are executed by human beings and cause delays in treatment that can be fatal. Considering these and other shortcomings there exists a need to have more efficient and accurate solutions based on artificial intelligence. Machine learning and more specifically, deep learning algorithms are of great help in analysing medical and clinical images to detect as well as classify diseases. In this paper, we propose a system for detecting various childhood diseases using a range of advanced Convolutional Neural Network models like EfficientNetB0, EfficientNetB3, Xception, InceptionV3, MobileNetV2, VGG19, DenseNet169, ResNet50V2, ResNet152V2, and the hybrid architecture InceptionResNetV2. These models are trained on MRI images of paediatric brain disorders to achieve high prediction accuracy. We use data visualization techniques such as segmentation and contour-based feature extraction to extract regions of interest before feeding the data into the models. The models are optimized using both ADAM and RMSprop optimizers. EfficientNetB0, when optimized with RMSprop, achieves an accuracy of 94.59%, a loss of 0.44, and an RMSE of 0.66. InceptionResNetV2, optimized with ADAM, achieves the highest accuracy of 97.59%, while EfficientNetB0 demonstrates the lowest loss (0.25) and RMSE (0.5). We also evaluate the models based on their precision, learning curves, recall, computational time, and F1 score, highlighting the effectiveness of AI-driven approaches for the diagnosis and management of children's diseases.

This study presents a thorough bibliometric analysis of Neuroinformatics over the past 20 years, offering insights into the journal's evolution at the intersection of neuroscience and computational science. Using advanced tools such as VOS viewer and methodologies like co-citation analysis, bibliographic coupling, and keyword co-occurrence, we examine trends in publication, citation patterns, and the journal's influence. Our analysis reveals enduring research themes like neuroimaging, data sharing, machine learning, and functional connectivity, which form the core of Neuroinformatics. These themes highlight the journal's role in addressing key challenges in neuroscience through computational methods. Emerging topics like deep learning, neuron reconstruction, and reproducibility further showcase the journal's responsiveness to technological advances. We also track the journal's rising impact, marked by a substantial growth in publications and citations, especially over the last decade. This growth underscores the relevance of computational approaches in neuroscience and the high-quality research the journal attracts. Key bibliometric indicators, such as publication counts, citation analysis, and the h-index, spotlight contributions from leading authors, papers, and institutions worldwide, particularly from the USA, China, and Europe. These metrics provide a clear view of the scientific landscape and collaboration patterns driving progress. This analysis not only celebrates Neuroinformatics's rich history but also offers strategic insights for future research, ensuring the journal remains a leader in innovation and advances both neuroscience and computational science.

Intracranial atherosclerotic stenosis (ICAS) and intracranial aneurysms are prevalent conditions in the cerebrovascular system. ICAS causes a narrowing of the arterial lumen, thereby restricting blood flow, while aneurysms involve the ballooning of blood vessels. Both conditions can lead to severe outcomes, such as stroke or vessel rupture, which can be fatal. Early detection is crucial for effective intervention. In this study, we introduced a method that combines classical computer vision techniques with deep learning to detect intracranial aneurysms and ICAS in time-of-flight magnetic resonance angiography images. The process began with skull-stripping, followed by an affine transformation to align the images to a common atlas space. We then focused on the region of interest, including the circle of Willis, by cropping the relevant area. A segmentation algorithm was used to isolate the arteries, after which a patch-wise residual neural network was applied across the image. A voting mechanism was then employed to identify the presence of atrophies. Our method achieved accuracies of 76.5% for aneurysms and 82.4% for ICAS. Notably, when occlusions were not considered, the accuracy for ICAS detection improved to 85.7%. While the algorithm performed well for localized pathological findings, it was less effective at detecting occlusions, which involved long-range dependencies in the MRIs. This limitation was due to the architectural design of the patch-wise deep learning approach. Regardless, this can, in the future, be mitigated in a multi-scale patch-wise algorithm.

The brain is composed of a dense and ramified vascular network of arteries, veins and capillaries of various sizes. One way to assess the risk of cerebrovascular pathologies is to use computational models to predict the physiological effects of reduced blood supply and correlate these responses with observations of brain damage. Therefore, it is crucial to establish a detailed 3D organization of the brain vasculature, which could be used to develop more accurate in silico models. To this end, we have adapted our functional ultrasound imaging platform, previously designed for recording large scale activity, to enable rapid and reproducible acquisition, segmentation and reconstruction of the cortical vasculature. For the first time, it allows us to digitize the cortical $\sim 100$ - $\mu$ m3 spatial resolution. Unlike most available strategies, our approach can be performed in vivo within minutes. Moreover, it is easy to implement since it requires neither exogenous contrast agents nor long post-processing time. Therefore, we performed a cortex-wide reconstruction of the vasculature and its quantitative analysis, including i) classification of descending arteries versus ascending veins in more than 1500 vessels/animal and ii) rapid estimation of their length. Importantly, we confirmed the relevance of our approach in a model of cortical stroke, which allows rapid visualization of the ischemic lesion. This development contributes to extending the capabilities of ultrasound neuroimaging to better understand cerebrovascular pathologies such as stroke, vascular cognitive impairment and brain tumors, and is highly scalable for the clinic.

In order to construct a clinical classification prediction model for hydrocephalus after intercerebral haemorrhage(ICH) to guide clinical treatment decisions, this paper retrospectively analyses the clinical data of 844 cases of ICH and hydrocephalus inpatients admitted to Yueyang People's Hospital from May 2019 to October 2022, of which 95 cases of hydrocephalus occurred after ICH and no hydrocephalus in 749 cases. The following indicators were compared between the two groups of patients: gender, age, Glasgow Coma Scale(GCS)score, whether the amount of bleeding was greater than 30 ml, whether it broke into the ventricle or not, modified Graeb score(MGS), modified Rankin Scale (MRS) score, whether surgery was performed or not, red blood cells, white blood cells, and platelets. After variable screening, the following six variables were selected: GCS score, MGS, MRS score, whether the bleeding volume was greater than 30 ml, whether it broke into the ventricle or not, and whether surgery was performed or not were modelled and analysed using logistic regression model and support vector machine model in machine learning. The results showed that under the same conditions, the accuracy of the support vector machine model was 0.89 and F1 was 0.838 ,the value of the AUC of the support vector machine model is 0.888; the accuracy of the logistic regression model was 0.902 and F1 was 0.89, the value of the AUC of the support vector machine model is 0.903. Compared with the group without hydrocephalus, patients in the group with hydrocephalus had bleeding volume greater than 30 ml, haemorrhage into the ventricles of the brain, and had undergone surgery in the brain, and the difference was statistically significant (P 0.001). Statistical analysis showed that GCS score ≤ 8.8, modified Graeb score (MGS) ≥ 10 and MRS score ≥ 3 were independent risk factors for the development of hydrocephalus after spontaneous ventricular haemorrhage. Therefore, patients with lower GCS score, higher modified Graeb score, higher MRS score, bleeding volume > 30 ml, haemorrhage into the ventricles of the brain, and experience of having undergone surgery in the brain should be operated on early to remove the intraventricular haematoma in order to reduce the incidence of hydrocephalus.

A reader of the peer-reviewed neuroscience literature will often encounter expressions like the following: 'the brain is a dynamic system', 'the brain is a complex network', or 'the brain is a highly metabolic organ'. These expressions attempt to define the essential functions and properties of the mammalian or human brain in a simple phrase or sentence, sometimes using metaphors or analogies. We sought to survey the most common phrases of the form 'the brain is…' in the biomedical literature to provide insights into current conceptualizations of the brain. Utilizing text analytic tools applied to a large sample (> 4 million) of peer-reviewed full-text articles and abstracts, we extracted several thousand phrases of the form 'the brain is…' and identified over a dozen frequently appearing phrases. The most used phrases included metaphors (e.g., the brain as a 'information processor' or 'prediction machine') and descriptions of essential functions (e.g., 'a central organ of stress adaptation') or properties (e.g., 'a highly vascularized organ'). Comparison of these phrases with those involving other bodily organs (e.g. the heart, liver, etc.) highlighted common phrases between the brain and other organs, such as the heart as a 'complex, dynamic system'. However, the brain was unique among organs in the number and diversity of analogies ascribed to it. The results of our analysis underscore the diversity of qualities and functions attributed to the brain in the biomedical literature and suggest a range of conceptualizations that defy unification.

Long-range axons are fundamental to brain connectivity and functional organization, enabling communication between different brain regions. Recent advances in experimental techniques have yielded a substantial number of whole-brain axonal reconstructions. While previous computational generative models of neurons have predominantly focused on dendrites, generating realistic axonal morphologies is more challenging due to their distinct targeting. In this study, we present a novel algorithm for axon synthesis that combines algebraic topology with the Steiner tree algorithm, an extension of the minimum spanning tree, to generate both the local and long-range compartments of axons. We demonstrate that our computationally generated axons closely replicate experimental data in terms of their morphological properties. This approach enables the generation of biologically accurate long-range axons that span large distances and connect multiple brain regions, advancing the digital reconstruction of the brain. Ultimately, our approach opens up new possibilities for large-scale in-silico simulations, advancing research into brain function and disorders.

This paper introduces the Automated Lesion and Feature Extraction (ALFE) pipeline, an open-source, Python-based pipeline that consumes MR images of the brain and produces anatomical segmentations, lesion segmentations, and human-interpretable imaging features describing the lesions in the brain. ALFE pipeline is modeled after the neuroradiology workflow and generates features that can be used by physicians for quantitative analysis of clinical brain MRIs and for machine learning applications. The pipeline uses a decoupled design which allows the user to customize the image processing, image registrations, and AI segmentation tools without the need to change the business logic of the pipeline. In this manuscript, we give an overview of ALFE, present the main aspects of ALFE pipeline design philosophy, and present case studies.

The position and orientation of transcranial magnetic stimulation (TMS) coil, which we collectively refer to as coil placement, significantly affect both the assessment and modulation of cortical excitability. TMS electric field (E-field) simulation can be used to identify optimal coil placement. However, the present E-field simulation required a laborious segmentation and meshing procedure to determine optimal coil placement. We intended to create a framework that would enable us to offer optimal coil placement without requiring the segmentation and meshing procedure. We constructed the stimulation effects map (SEM) framework using the CASIA dataset for optimal coil placement. We used leave-one-subject-out cross-validation to evaluate the consistency of the optimal coil placement and the target regions determined by SEM for the 74 target ROIs in MRI data from the CASIA, HCP15 and HCP100 datasets. Additionally, we contrasted the E-norms determined by optimal coil placements using SEM and auxiliary dipole method (ADM) based on the DP and CASIA II datasets. We provided optimal coil placement in 'head-anatomy-based' (HAC) polar coordinates and MNI coordinates for the target region. The results also demonstrated the consistency of the SEM framework for the 74 target ROIs. The normal E-field determined by SEM was more significant than the value received by ADM. We created the SEM framework using the CASIA database to determine optimal coil placement without segmentation or meshing. We provided optimal coil placement in HAC and MNI coordinates for the target region. The validation of several target ROIs from various datasets demonstrated the consistency of the SEM approach. By streamlining the process of finding optimal coil placement, we intended to make TMS assessment and therapy more convenient.

Neuropixels probes contain thousands of electrodes across one or more shanks and are sufficiently small to allow chronic recording of neural activity in freely behaving small animals. However, the joint increase in the number of electrodes and miniaturization of the probe package has led to a compromise in which groups of electrodes share a single read-out channel and only a fraction of the electrodes can be read out at any given time. Experimenters then face the challenge of selecting a subset of electrodes (i.e., channel map) that both covers the brain regions of interest and adheres to the restrictions of the underlying hardware. Here, we present NeuroCarto, a Python toolkit and GUI to simplify the construction of a custom channel map for Neuropixels probes. We describe a general iterative approach to select electrodes and provide a specific implementation that allows experimenters to specify a blueprint of regions of interest along the probe shanks and the desired local electrode density. NeuroCarto assists in generating a channel map from the blueprint and visualizes potential read-out channel conflicts. We showcase the utility of NeuroCarto in an experimental workflow to simultaneously record from the dorsal and ventral hippocampus with 4-shank Neuropixels 2.0 probes in freely moving mice.