Autism spectrum disorder (ASD) is an intricate neuropsychiatric brain disorder characterized by social deficits and repetitive behaviors. Deep learning approaches have been applied in clinical or behavioral identifica...
详细信息
Autism spectrum disorder (ASD) is an intricate neuropsychiatric brain disorder characterized by social deficits and repetitive behaviors. Deep learning approaches have been applied in clinical or behavioral identification of ASD;most erstwhile models are inadequate in their capacity to exploit the data richness. On the other hand, classification techniques often solely rely on region-based summary and/or functional connectivity analysis of functional magnetic resonance imaging (fMRI). Besides, biomedical data modeling to analyze big data related to ASD is still perplexing due to its complexity and heterogeneity. Single volume image consideration has not been previously investigated in classification purposes. By deeming these challenges, in this work, firstly, we design an image generator to generate single volume brain images from the whole-brain image by considering the voxel time point of each subject separately. Then, to classify ASD and typical control participants, we evaluate four deep learning approaches with their corresponding ensemble classifiers comprising one amended Convolutional Neural Network (CNN). Finally, to check out the data variability, we apply the proposed CNN classifier with leave-one-site-out 5-fold cross-validation across the sites and validate our findings by comparing with literature reports. We showcase our approach on large-scale multi-site brain imaging dataset (ABIDE) by considering four preprocessing pipelines, which outperforms the state-of-the-art methods. Hence, it is robust and consistent.
The continuous growth of experimental data generated by Next Generation Sequencing (NGS) machines has led to the adoption of advanced techniques to intelligently manage them. The advent of the Big data era posed new c...
详细信息
ISBN:
(纸本)9783030276843;9783030276836
The continuous growth of experimental data generated by Next Generation Sequencing (NGS) machines has led to the adoption of advanced techniques to intelligently manage them. The advent of the Big data era posed new challenges that led to the development of novel methods and tools, which were initially born to face with computational science problems, but which nowadays can be widely applied on biomedicaldata. In this work, we address two biomedicaldata management issues: (i) how to reduce the redundancy of genomic and clinical data, and (ii) how to make this big amount of data easily accessible. Firstly, we propose an approach to optimally organize genomic and clinical data by taking into account data redundancy and propose a method able to save as much space as possible by exploiting the power of no-SQL technologies. Then, we propose design principles for organizing biomedicaldata and make them easily accessible through the development of a collection of Application Programming Interfaces (APIs), in order to provide a flexible framework that we called OpenOmics. To prove the validity of our approach, we apply it on data extracted from The Genomic data Commons repository. OpenOmics is free and open source for allowing everyone to extend the set of provided APIs with new features that may be able to answer specific biological questions. They are hosted on GitHub at the following address https://***/fabio-cumbo/open-omicsapi/, publicly queryable at http://***/openomics/api/routes, and their documentation is available at https://***/.
暂无评论