China
Africa
Explore chapters and articles related to this topic
Big Data Era in Magnetic Resonance Imaging of the Human Brain
Published in Ervin Sejdić, Tiago H. Falk, Signal Processing and Machine Learning for Biomedical Big Data, 2018
Xiaoyu Ding, Elisabeth de Castro Caparelli, Thomas J. Ross
Big data projects, such as the human connectome project (HCP), are building a more comprehensive map of the healthy human brain, while others, such as the 1000 functional connectome project, are addressing issues related to the reproducibility of findings across datasets and individuals. In addition, several data repositories (e.g., the Federal Interagency Traumatic Brain Injury Research [FITBIR] and the National Database for Autism Research [NDAR]) and virtual databases (e.g., the SchizConnect, which was designed to connect different data banks), as well as some longitudinal-multicenter studies (e.g., Alzheimer’s Disease Neuroimaging Initiative [ADNI] and IMAGEN), have been initiated to expand collaborative and advanced research in distinct fields in order to improve treatment outcome. In the following, these initiatives are presented in detail.
Axon-Inspired Communication Systems
Published in James E. Morris, Krzysztof Iniewski, Nanoelectronic Device Applications Handbook, 2017
Valeriu Beiu, Liren Zhang, Azam Beg, Walid Ibrahim, Mihai Tache
All of these results are supporting the scarcity of the long interconnects in the brain. The detailed map of the full set of neurons and synapses within the nervous system of an organism is known as a connectome (http://en.wikipedia.org/wiki/Connectome), and the National Institutes of Health is supporting the Human Connectome Project (http://www.humanconnectomeproject.org/), which started in 2011. In fact, the first comprehensive attempt to reverse-engineer the mammalian brain was started in 2005 as the EPFL/Blue Brain Project (http://bluebrain.epfl.ch/), and impressive simulation results of neocortical columns (about 10,000 biologically accurate individual neurons) have already been obtained (see Figure 15.2). The expectation is that the Blue Brain Project will be expanded and continued under the EU’s FET Flagship program as the Human Brain Project (http://www.humanbrainproject.eu/), a fact which has just been announced in January 2013 (http://www.nature.com/news/brain-simulation-and-graphene-projects-win-billion-euro-competition-1.12291).
The Deep Brain Connectome
Published in Yu Chen, Babak Kateb, Neurophotonics and Brain Mapping, 2017
Ifije E. Ohiorhenuan, Vance L. Fredrickson, Mark A. Liker
Launched in 2012, with an NIH-sponsored budget of approximately $40 million, the Human Connectome Project aims to create a wiring diagram of the human brain using high-resolution scanners and standardized protocols. Currently, the Human Connectome Project is gathering data on 1200 individuals using a combination of MRI modalities from high-resolution 3T and 7T magnetic resonance scanners. Despite being in its early stages, this project has already yielded some interesting insights that point to the potential impact of this dataset on our understanding of the human brain and behavior. For instance, it has been shown that an individual’s frontoparietal network both is a fingerprint, uniquely identifying him or her out of a population, and can be used to predict his or her fluid intelligence, a measure of reasoning and problem solving (Finn et al. 2015). Moreover, it has been demonstrated that certain connectivity patterns are associated with positive behavioral traits such as cognition, memory, years of education, and income level, while others are associated with negative behavioral traits such as substance use, rule-breaking, and aggression (Smith et al. 2015). Thus, even in its earliest stages, the human connectome can provide insights with far-reaching implications.
A novel approach to the analysis of spatial and functional data over complex domains
Published in Quality Engineering, 2020
Lila, Aston, and Sangalli (2016a) illustrates the method via an application to the study of high-dimensional neuroimaging signals associated with neuronal activity in the cerebral cortex. The dataset consists of resting state functional magnetic resonance imaging scans from about 500 healthy volunteers, and is made available by the Human Connectome Project (Van Essen et al. 2012). The left panel of Figure 3 shows a triangular mesh representing the cortical surface of a template brain. The scans of the various subjects are mapped to this template, to enable comparisons across subjects. The figure highlights the highly convoluted morphology of the cortex. While most neuroimaging analysis ignore the morphology of the cortical surface, there is nowadays a growing awareness of the need to include the complex brain morphology, to advance our still limited knowledge about brain functioning (see, e.g., Glasser et al. 2013, and references therein). This has generated a strong momentum in the international community for the development of methods able to accurately analyze data arising from these complex imaging scans. As mentioned in the Introduction, classical tools such as non-parametric smoothing have already been adapted to deal with data observed over two-dimensional curved domains, such as the cortex (see, e.g., Hagler, Saygin, and Sereno 2006; Chung et al. 2005, 2017). In this respect, Lila, Aston, and Sangalli (2016a) offers the first method for population studies.
Comparison analysis of local angular interpolation methods in diffusion MRI
Published in Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, 2022
Ines Ben Alaya, Majdi Jribi, Faouzi Ghorbel, Tarek Kraiem
Experiments on real data are performed to confirm the simulation results. The data of five healthy volunteers are from Human Connectome Project (HCP).4 images were obtained by a spin-echo echo-planar imaging sequence with repetition time 8800 ms, echo time 57 ms and 96 axial slices. Diffusion gradients with b = 3000 were applied in 64 directions uniformly distributed on a unit sphere. In Figure 6, we illustrate the procedure of evaluating interpolation methods in real data.
A Comprehensive Literature Review of Application of Artificial Intelligence in Functional Magnetic Resonance Imaging for Disease Diagnosis
Published in Applied Artificial Intelligence, 2021
Ali Nawaz, Attique Ur Rehman, Tahir Mohammad Ali, Zara Hayat, Aqsa Rahim, Uzair Khaleeq Uz Zaman, Amad Rizwan Ali
Recently, (Sheng et al. 2020) used a basic machine learning technique for distinguishing the AD, cognitive impairment (MCI) from HC. Specifically, a joint human connectome project multimodal parcellation (JHCPMMP) was used form Data preprocessing then logistic regression recursive feature elimination (LR-RFE) was used for feature selection and finally SVM, logistic regression, and KNN was applied for classification. The datasets used by them was ADNI. The maximum accuracy was obtained by using SVM, i.e., 89% for AD vs. MCI vs. HC.