Deep learning (DL) has revolutionized the field of artificial intelligence by enabling computational models consisting of multiple processing layers to learn abstract representations of data. While conventional machine learning methods have been limited for decades by the need of an expert knowledge to design sophisticated feature extraction algorithms to transform raw data into a suitable form for classification, deep leaning methods, as representation-learning techniques, enable the learning model to be directly fed with raw data in order to discover the representations needed for classification.
Currently, an intensive research effort is being devoted to the development of novel neuroimaging techniques to better understand the mechanisms of the Central Nervous System (CNS) and to early recognize age-related neural diseases. The vast amount of data provided by large multicentre studies currently investigating new biomarkers for age-related neural diseases represents an opportunity for the development of more accurate deep learning models of neurodegeneration enabling the early recognition, as well as, the characterization of the progressive course of neural disorders.
The aim of this Research Topic to be published in Frontiers in Aging Neuroscience is to present the current state of the art in the theory and practice of deep learning computational modeling techniques in aging neuroscience with special emphasis to advance in our understanding of the mechanisms of Central Nervous System aging and age-related neural diseases.
We welcome original DL contributions from scientists carrying out research that ranges from neuropsychological and behavioral to clinical neuroimaging (including structural and functional MRI, various nuclear PET and SPECT modalities, DTI, infrared spectroscopy, EEG advanced techniques) related but not limited to:
• DL models to understand the mechanisms of the CNS
• DL techniques for early diagnosis and prognosis age-related neural diseases
• DL methods for preprocessing raw data in brain imaging
• Analysis, visualization and optimization of deep neural networks in aging neuroscience
• New trends in deep neural network architecture design
• DL regression methods in aging neuroscience
Deep learning (DL) has revolutionized the field of artificial intelligence by enabling computational models consisting of multiple processing layers to learn abstract representations of data. While conventional machine learning methods have been limited for decades by the need of an expert knowledge to design sophisticated feature extraction algorithms to transform raw data into a suitable form for classification, deep leaning methods, as representation-learning techniques, enable the learning model to be directly fed with raw data in order to discover the representations needed for classification.
Currently, an intensive research effort is being devoted to the development of novel neuroimaging techniques to better understand the mechanisms of the Central Nervous System (CNS) and to early recognize age-related neural diseases. The vast amount of data provided by large multicentre studies currently investigating new biomarkers for age-related neural diseases represents an opportunity for the development of more accurate deep learning models of neurodegeneration enabling the early recognition, as well as, the characterization of the progressive course of neural disorders.
The aim of this Research Topic to be published in Frontiers in Aging Neuroscience is to present the current state of the art in the theory and practice of deep learning computational modeling techniques in aging neuroscience with special emphasis to advance in our understanding of the mechanisms of Central Nervous System aging and age-related neural diseases.
We welcome original DL contributions from scientists carrying out research that ranges from neuropsychological and behavioral to clinical neuroimaging (including structural and functional MRI, various nuclear PET and SPECT modalities, DTI, infrared spectroscopy, EEG advanced techniques) related but not limited to:
• DL models to understand the mechanisms of the CNS
• DL techniques for early diagnosis and prognosis age-related neural diseases
• DL methods for preprocessing raw data in brain imaging
• Analysis, visualization and optimization of deep neural networks in aging neuroscience
• New trends in deep neural network architecture design
• DL regression methods in aging neuroscience