Corpus ID: 196197911

Deep learning frameworks for functional and structural medical image analysis

  title={Deep learning frameworks for functional and structural medical image analysis},
  author={Yu Zhao},
  • Yu Zhao
  • Published 1 December 2018
  • Computer Science
Medical image analysis plays an important role for understanding both human psychology and physiology. Human body functional and structural information can be recorded using different medical imaging techniques. As for functional image analysis, understanding the organizational architecture of human brain function has been of intense interest since the inception of human neuroscience. In-vivo Functional Magnetic Resonance Imaging (fMRI) technology enabled the investigation of the human brainโ€ฆย Expand


Modeling Task fMRI Data Via Deep Convolutional Autoencoder
A new neural network structure based on CNN is developed, called deep convolutional auto-encoder (DCAE), in order to take the advantages of both data-driven approach and CNNโ€™s hierarchical feature abstraction ability for the purpose of learning mid-level and high-level features from complex, large-scale tfMRI time series in an unsupervised manner. Expand
Automatic Recognition of fMRI-Derived Functional Networks Using 3-D Convolutional Neural Networks
This study designs, applies, and evaluates a deep 3-D CNN framework for automatic, effective, and accurate classification and recognition of large number of functional brain networks reconstructed by sparse representation of whole-brain fMRI signals and provides a new deep learning approach for modeling functional connectomes based on fMRI data. Expand
A novel framework for groupwise registration of fMRI images based on common functional networks
  • Yu Zhao, Shu Zhang, +5 authors Tianming Liu
  • Computer Science, Medicine
  • 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)
  • 2017
This work proposes a novel computational framework for simultaneous groupwise fMRI image registration by utilizing those common functional networks as references for spatial alignments using Independent Component Analysis (ICA). Expand
Modeling 4D fMRI Data via Spatio-Temporal Convolutional Neural Networks (ST-CNN)
The proposed ST-CNN is evaluated by the task of identifying the Default Mode Network (DMN) from fMRI data and it has the sufficient generalizability to identify the DMN from different populations of data as well as different cognitive tasks. Expand
Recurrent Neural Networks for Spatiotemporal Dynamics of Intrinsic Networks from fMRI Data
Recurrent neural networks (RNNs) are combined with an ICA objective to overcome shortcomings of temporal ICA in lack of dynamics and subject-wise/temporal variability of spatial maps, but without abandoning the fundamental strengths of ICA. Expand
Modeling Task FMRI Data via Supervised Stochastic Coordinate Coding
A novel supervised stochastic coordinate coding SCC algorithm is proposed for fMRI data analysis, in which certain brain networks are learned with supervised information such as temporal patterns of task designs and spatial patterns of network templates, while other networks are learning automatically from the data. Expand
Sparse representation of whole-brain fMRI signals for identification of functional networks
Experimental results have shown that this novel methodology can uncover multiple functional networks that can be well characterized and interpreted in spatial, temporal and frequency domains based on current brain science knowledge. Expand
Exploring the brain network: A review on resting-state fMRI functional connectivity
Our brain is a network. It consists of spatially distributed, but functionally linked regions that continuously share information with each other. Interestingly, recent advances in the acquisitionโ€ฆ Expand
Identifying functional networks via sparse coding of whole brain FMRI signals
  • J. Lv, Xi Jiang, +10 authors Tianming Liu
  • Computer Science
  • 2013 6th International IEEE/EMBS Conference on Neural Engineering (NER)
  • 2013
This paper presents a novel, alternative methodology of identifying multiple functional networks via sparse representation of whole-brain task-based fMRI signals via an effective online dictionary learning algorithm and results have shown that this novel methodology can uncover multiplefunctional networks that can be characterized and interpreted in spatial, temporal and frequency domains. Expand
Constructing fineโ€granularity functional brain network atlases via deep convolutional autoencoder
This work presents a promising deep learning and big data analysis solution for modeling functional connectomes, with fine granularities, based on fMRI data and shows that the technique can effectively identify abnormal small networks in brain injury patients in comparison with controls. Expand