Understanding how the biological neural system accounts for human brain functions is an enduring preoccupation. Several powerful techniques have been proposed to map morphological, structural, and functional neuroimages to neurological diseases. Deep learning has recently been used to analyze neuroimages and is a powerful tool to improve our understanding of neurological diseases. In contrast to traditional machine learning algorithms, deep learning can detect abstract and complex patterns and automatically discover informative representations without the need for domain expert knowledge, allowing non-experts to use deep learning techniques effectively. Nowadays, faster image acquisition with increased resolution, along with the availability of publicly available neuroimaging datasets, facilitate the potential of applying deep learning to larger neuroimaging datasets. Still, deep learning methods for neuroimaging analysis are under-explored and not optimized.
This research topic aims to explore the development of deep learning techniques for neuroimaging-based neurological disease analysis. We seek studies applying and designing deep learning algorithms for neuroimage analysis and to investigate the correlation between neuroimaging and neurological diseases across a range of specialties.
Our goal is to address the following questions:
• What are the challenges and corresponding solutions of deep learning applied to neuroimages?
• How can we preprocess data and evaluate results to avoid model overfitting and data contamination?
• What are the key neuroimaging-based features that affect deep learning outputs?
• How can we utilize deep learning to better understand neurological disorders?
Sample topics include:
• Novel deep learning algorithms and pipeline design for neuroimage analysis
• Deep learning applications for the diagnosis of neurological disorders
• Brain biomarker discovery using deep learning
• Deep learning regression models for prognostic value prediction
• Deep learning-based causal modeling for disease
• Deep learning-based multi-modal data fusion to characterize neurological disorders
• Deep learning-based toolkits and software development for neuroimage analysis
• Benchmarks for deep learning in neuroimaging
• Reviews of recent advancements in related topics
Article Types we would like to receive in the Research Topic are Original Research, Systematic Review, Methods, Review, Mini Review, Hypothesis and Theory, Perspective, Data Report, Brief Research Report, Opinion and Technology and Code.
Imaging-focused articles are welcome to be submitted to the Brain Imaging and Stimulation section.
Understanding how the biological neural system accounts for human brain functions is an enduring preoccupation. Several powerful techniques have been proposed to map morphological, structural, and functional neuroimages to neurological diseases. Deep learning has recently been used to analyze neuroimages and is a powerful tool to improve our understanding of neurological diseases. In contrast to traditional machine learning algorithms, deep learning can detect abstract and complex patterns and automatically discover informative representations without the need for domain expert knowledge, allowing non-experts to use deep learning techniques effectively. Nowadays, faster image acquisition with increased resolution, along with the availability of publicly available neuroimaging datasets, facilitate the potential of applying deep learning to larger neuroimaging datasets. Still, deep learning methods for neuroimaging analysis are under-explored and not optimized.
This research topic aims to explore the development of deep learning techniques for neuroimaging-based neurological disease analysis. We seek studies applying and designing deep learning algorithms for neuroimage analysis and to investigate the correlation between neuroimaging and neurological diseases across a range of specialties.
Our goal is to address the following questions:
• What are the challenges and corresponding solutions of deep learning applied to neuroimages?
• How can we preprocess data and evaluate results to avoid model overfitting and data contamination?
• What are the key neuroimaging-based features that affect deep learning outputs?
• How can we utilize deep learning to better understand neurological disorders?
Sample topics include:
• Novel deep learning algorithms and pipeline design for neuroimage analysis
• Deep learning applications for the diagnosis of neurological disorders
• Brain biomarker discovery using deep learning
• Deep learning regression models for prognostic value prediction
• Deep learning-based causal modeling for disease
• Deep learning-based multi-modal data fusion to characterize neurological disorders
• Deep learning-based toolkits and software development for neuroimage analysis
• Benchmarks for deep learning in neuroimaging
• Reviews of recent advancements in related topics
Article Types we would like to receive in the Research Topic are Original Research, Systematic Review, Methods, Review, Mini Review, Hypothesis and Theory, Perspective, Data Report, Brief Research Report, Opinion and Technology and Code.
Imaging-focused articles are welcome to be submitted to the Brain Imaging and Stimulation section.