Modeling Task fMRI Data Via Deep Convolutional Autoencoder

Huang, Heng; Hu, Xintao; Zhao, Yu; Makkie, Milad; Dong, Qinglin; Zhao, Shijie; Guo, Lei; Liu, Tianming

doi:10.1109/tmi.2017.2715285

Cited by 149 publications

(50 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In section 4, we will explain how asynchronous gradient computation reduces the model's training time by communicating and updating parameters values. A non-distributed version of DCA model is elaborated in [43].…”

Section: Previous Workmentioning

confidence: 99%

“…The advantages of choosing ReLU in our study is first to reduce the possibility of vanishing gradient and second to represent the signal sparsely as we later use the sparse representation of the hidden layer for data validation. A fully connected layer is used at the end of the encoder to match the encoder final hidden layer feature size with the input signal and to ensure that the hidden states are learned with a full receptive field of input as we use it as the final desired output of the model as mentioned in [43].…”

Section: Encodermentioning

confidence: 99%

“…For the sake of simplicity and page limitation, we do not explain the theoretical brain model analysis and reconstruction error analysis. Further details of this comparison can be found at Huang et al work [43]. Furthermore, we visualized the filters in each layer.…”

Section: Learned Features Validation and Visualizationmentioning

confidence: 99%

See 2 more Smart Citations

Fast and scalable distributed deep convolutional autoencoder for fMRI big data analytics

et al. 2019

Self Cite

View full text Add to dashboard Cite

In recent years, analyzing task-based fMRI (tfMRI) data has become an essential tool for understanding brain function and networks. However, due to the sheer size of tfMRI data, its intrinsic complex structure, and lack of ground truth of underlying neural activities, modeling tfMRI data is hard and challenging. Previously proposed data modeling methods including Independent Component Analysis (ICA) and Sparse Dictionary Learning only provided shallow models based on blind source separation under the strong assumption that original fMRI signals could be linearly decomposed into time series components with corresponding spatial maps. Given the Convolutional Neural Network (CNN) successes in learning hierarchical abstractions from low-level data such as tfMRI time series, in this work we propose a novel scalable distributed deep CNN autoencoder model and apply it for fMRI big data analysis. This model aims to both learn the complex hierarchical structures of the tfMRI big data and to leverage the processing power of multiple GPUs in a distributed fashion. To deploy such a model, we have created an enhanced processing pipeline on the top of Apache Spark and Tensorflow, leveraging from a large cluster of GPU nodes over cloud. Experimental results from applying the model on the Human Connectome Project (HCP) data show that the proposed model is efficient and scalable toward tfMRI big data modeling and analytics, thus enabling data-driven extraction of hierarchical neuroscientific information from massive fMRI big data.

show abstract

Section: Previous Workmentioning

confidence: 99%

Section: Encodermentioning

confidence: 99%

See 1 more Smart Citation

Fast and scalable distributed deep convolutional autoencoder for fMRI big data analytics

et al. 2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…Deep learning has achieved great success in various applications in computer vision (Ding and Tao, 2018) and medical imaging processing and analysis Huang et al, 2018b;Zhu et al, 2018a;Parisot et al, 2018). In a recent lung cancer detection challenge organized by Kaggle, most top-scored models were based on a deep convolutional neural network (CNN).…”

Section: ⅰ Introductionmentioning

confidence: 99%

Predicting lung nodule malignancies by combining deep convolutional neural network and handcrafted features

Li¹,

Xu²,

Li³

et al. 2019

Phys. Med. Biol.

View full text Add to dashboard Cite

To predict lung nodule malignancy with a high sensitivity and specificity, we propose a fusion algorithm that combines handcrafted features (HF) into the features learned at the output layer of a 3D deep convolutional neural network (CNN). First, we extracted twenty-nine handcrafted features, including nine intensity features, eight geometric features, and twelve texture features based on grey-level co-occurrence matrix (GLCM) averaged from five grey levels, four distances and thirteen directions. We then trained 3D CNNs modified from three 2D CNN architectures (AlexNet, VGG-16 Net and Multi-crop Net) to extract the CNN features learned at the output layer. For each 3D CNN, the CNN features combined with the 29 handcrafted features were used as the input for the support vector machine (SVM) coupled with the sequential forward feature selection (SFS) method to select the optimal feature subset and construct the classifiers. The fusion algorithm takes full advantage of the handcrafted features and the highest level CNN features learned at the output layer. It can overcome the disadvantage of the handcrafted features that may not fully reflect the unique characteristics of a particular lesion by combining the intrinsic CNN features. Meanwhile, it also alleviates the requirement of a large scale annotated dataset for the CNNs based on the complementary of handcrafted features. The patient cohort includes 431 malignant nodules and 795 benign nodules extracted from the LIDC/IDRI database. For each investigated CNN architecture, the proposed fusion algorithm achieved the highest AUC, accuracy, sensitivity, and specificity scores among all competitive classification models.

show abstract

“…While researchers have started exploring the application of DL methods to the analysis of functional Magnetic Resonance Imaging (fMRI) data (e.g., [12]), their application to whole-brain fMRI data is still limited (e.g., [5,6]). Mainly, due to the small sample sizes and high dimensionality of fMRI datasets (and a lack of interpretability of DL models [7]).…”

Section: Introductionmentioning

confidence: 99%

Deep Transfer Learning for Whole-Brain FMRI Analyses

Thomas

Müller

Samek

2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

The application of deep learning (DL) models to the decoding of cognitive states from whole-brain functional Magnetic Resonance Imaging (fMRI) data is often hindered by the small sample size and high dimensionality of these datasets. Especially, in clinical settings, where patient data are scarce. In this work, we demonstrate that transfer learning represents a solution to this problem. Particularly, we show that a DL model, which has been previously trained on a large openly available fMRI dataset of the Human Connectome Project, outperforms a model variant with the same architecture, but which is trained from scratch, when both are applied to the data of a new, unrelated fMRI task. Even further, the pre-trained DL model variant is already able to correctly decode 67.51% of the cognitive states from a test dataset with 100 individuals, when fine-tuned on a dataset of the size of only three subjects.

show abstract

Modeling Task fMRI Data Via Deep Convolutional Autoencoder

Cited by 149 publications

References 34 publications

Fast and scalable distributed deep convolutional autoencoder for fMRI big data analytics

Fast and scalable distributed deep convolutional autoencoder for fMRI big data analytics

Predicting lung nodule malignancies by combining deep convolutional neural network and handcrafted features

Deep Transfer Learning for Whole-Brain FMRI Analyses

Contact Info

Product

Resources

About