Deep learning methods and applications in neuroimaging
摘要截稿:
全文截稿: 2019-02-01
影响因子: 2.214
期刊难度:
CCF分类: 无
中科院JCR分区:
• 大类 : 医学 - 4区
• 小类 : 生化研究方法 - 3区
• 小类 : 神经科学 - 4区
Overview
Deep learning (DL) has gained considerable attention in the scientific community, breaking benchmark records in many areas such as speech and visual recognition. The core of DL is the ability to exploit hierarchical feature representations learned solely from data, instead of features designed by hand according to domain-specific knowledge. Recently, deep models have recently made significant advances, outperforming regular classification models in multiple domains such as medical diagnoses. However, the incorporation of deep learning approaches in neuroimaging is still a challenging and promising direction. Currently, advances in medical imaging technologies have enabled image acquisition at faster rates and with increased resolution. Also, multiple accessible international brain imaging datasets online facilitate the generation of neuroimaging big data. All above provide wonderful testbeds for the advanced computerized tools, especially deep learning approaches. This special issue (SI) request original work which addresses ongoing challenges and new developments in the use of deep learning techniques for neuroimaging analyses. The list of possible topics includes, but not limited to:
- Transfer learning and fine-tuning methods in neuroimaging analysis
- Convolutional/Recurrent Neural Networks (CNNs, RNNs) in diseases diagnosis
- Other deep learning networks (e.g., GAN) in diseases diagnosis
- Semantic segmentation of medical images
- Image reconstruction (e.g. MRI)
- (Multi-modal) image registration with deep learning
- Interventional image analysis with deep learning (e.g. image-guided surgery)
- Integration of MRI and clinical data
- Learning with sparse data/labels
- Unsupervised deep learning in neuroimaging
- Data augmentation for neuroimaging data
- End-to-end learning for prognosis and treatment selection based on neuroimaging data
- Deep learning models of the visual system
- Meta-heuristic techniques for fine-tuning parameter in deep learning-based architectures
- Systematic evaluation of deep learning algorithms using neuroimaging data