Learning Human Cognition via fMRI Analysis Using 3D CNN and Graph Neural Network

2019 ◽  
pp. 93-101
Author(s):  
Xiuyan Ni ◽  
Tian Gao ◽  
Tingting Wu ◽  
Jin Fan ◽  
Chao Chen
Keyword(s):  
Neural Network ◽  
Human Cognition ◽  
Fmri Analysis ◽  
3D Cnn

scholarly journals A 3D-CNN model with CT-based parametric response mapping for classifying COPD subjects

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Thao Thi Ho ◽  
Taewoo Kim ◽  
Woo Jin Kim ◽  
Chang Hyun Lee ◽  
Kum Ju Chae ◽  
...  
Keyword(s):  
Neural Network ◽  
Pulmonary Function Tests ◽  
Airway Disease ◽  
Chronic Obstructive ◽  
Respiratory Disorder ◽  
Obstructive Pulmonary Disease ◽  
Response Mapping ◽  
Small Airway Disease ◽  
3D Cnn ◽  
Parametric Response

AbstractChronic obstructive pulmonary disease (COPD) is a respiratory disorder involving abnormalities of lung parenchymal morphology with different severities. COPD is assessed by pulmonary-function tests and computed tomography-based approaches. We introduce a new classification method for COPD grouping based on deep learning and a parametric-response mapping (PRM) method. We extracted parenchymal functional variables of functional small airway disease percentage (fSAD%) and emphysema percentage (Emph%) with an image registration technique, being provided as input parameters of 3D convolutional neural network (CNN). The integrated 3D-CNN and PRM (3D-cPRM) achieved a classification accuracy of 89.3% and a sensitivity of 88.3% in five-fold cross-validation. The prediction accuracy of the proposed 3D-cPRM exceeded those of the 2D model and traditional 3D CNNs with the same neural network, and was comparable to that of 2D pretrained PRM models. We then applied a gradient-weighted class activation mapping (Grad-CAM) that highlights the key features in the CNN learning process. Most of the class-discriminative regions appeared in the upper and middle lobes of the lung, consistent with the regions of elevated fSAD% and Emph% in COPD subjects. The 3D-cPRM successfully represented the parenchymal abnormalities in COPD and matched the CT-based diagnosis of COPD.

Automatic segmentation of lung tumors on CT images based on a 2D & 3D hybrid convolutional neural network

2021 ◽  
pp. 20210038
Author(s):  
Wutian Gan ◽  
Hao Wang ◽  
Hengle Gu ◽  
Yanhua Duan ◽  
Yan Shao ◽  
...  
Keyword(s):  
Neural Network ◽  
Lung Cancer ◽  
Lung Tumor ◽  
Ct Images ◽  
Hybrid Network ◽  
Evaluation Metrics ◽  
Tumor Segmentation ◽  
Tumor Delineation ◽  
3D Cnn ◽  
The Individual

Objective: A stable and accurate automatic tumor delineation method has been developed to facilitate the intelligent design of lung cancer radiotherapy process. The purpose of this paper is to introduce an automatic tumor segmentation network for lung cancer on CT images based on deep learning. Methods: In this paper, a hybrid convolution neural network (CNN) combining 2D CNN and 3D CNN was implemented for the automatic lung tumor delineation using CT images. 3D CNN used V-Net model for the extraction of tumor context information from CT sequence images. 2D CNN used an encoder–decoder structure based on dense connection scheme, which could expand information flow and promote feature propagation. Next, 2D features and 3D features were fused through a hybrid module. Meanwhile, the hybrid CNN was compared with the individual 3D CNN and 2D CNN, and three evaluation metrics, Dice, Jaccard and Hausdorff distance (HD), were used for quantitative evaluation. The relationship between the segmentation performance of hybrid network and the GTV volume size was also explored. Results: The newly introduced hybrid CNN was trained and tested on a dataset of 260 cases, and could achieve a median value of 0.73, with mean and stand deviation of 0.72 ± 0.10 for the Dice metric, 0.58 ± 0.13 and 21.73 ± 13.30 mm for the Jaccard and HD metrics, respectively. The hybrid network significantly outperformed the individual 3D CNN and 2D CNN in the three examined evaluation metrics (p < 0.001). A larger GTV present a higher value for the Dice metric, but its delineation at the tumor boundary is unstable. Conclusions: The implemented hybrid CNN was able to achieve good lung tumor segmentation performance on CT images. Advances in knowledge: The hybrid CNN has valuable prospect with the ability to segment lung tumor.

scholarly journals Transfer Learning for Predicting Conversion from Mild Cognitive Impairment to Dementia of Alzheimer’s Type based on 3D-Convolutional Neural Network

2019 ◽  
Author(s):  
Jinhyeong Bae ◽  
Jane Stocks ◽  
Ashley Heywood ◽  
Youngmoon Jung ◽  
Lisanne Jenkins ◽  
...  
Keyword(s):  
Neural Network ◽  
Cognitive Impairment ◽  
Mild Cognitive Impairment ◽  
Cognitive Decline ◽  
Convolutional Neural Network ◽  
Transfer Learning ◽  
Brain Regions ◽  
Pharmacological Intervention ◽  
Dementia Of Alzheimer’S Type ◽  
3D Cnn

AbstractDementia of Alzheimer’s Type (DAT) is associated with a devastating and irreversible cognitive decline. As a pharmacological intervention has not yet been developed to reverse disease progression, preventive medicine will play a crucial role for patient care and treatment planning. However, predicting which patients will progress to DAT is difficult as patients with Mild Cognitive Impairment (MCI) could either convert to DAT (MCI-C) or not (MCI-NC). In this paper, we develop a deep learning model to address the heterogeneous nature of DAT development. Structural magnetic resonance imaging was utilized as a single biomarker, and a three-dimensional convolutional neural network (3D-CNN) was developed. The 3D-CNN was trained using transfer learning from the classification of Normal Control and DAT scans at the source task. This was applied to the target task of classifying MCI-C and MCI-NC scans. The model results in 82.4% classification accuracy, which outperforms current models in the field. Furthermore, by implementing an occlusion map approach, we visualize key brain regions that significantly contribute to the prediction of MCI-C and MCI-NC. Results show the hippocampus, amygdala, cerebellum, and pons regions as significant to prediction, which are consistent with current understanding of disease. Finally, the model’s prediction value is significantly correlated with rates of change in clinical assessment scores, indicating the model is able to predict an individual patient’s future cognitive decline. This information, in conjunction with the identified anatomical features, will aid in building a personalized therapeutic strategy for individuals with MCI. This model could also be useful for selection of participants for clinical trials.

scholarly journals Multimodal Ensemble Deep Learning to Predict Disruptive Behavior Disorders in Children

2021 ◽  
Vol 15 ◽  
Author(s):  
Sreevalsan S. Menon ◽  
K. Krishnamurthy
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Disruptive Behavior ◽  
Behavior Disorders ◽  
Child Behavior Checklist ◽  
Disruptive Behavior Disorders ◽  
Fmri Data ◽  
Typically Developing ◽  
Oppositional Defiant ◽  
3D Cnn

Oppositional defiant disorder and conduct disorder, collectively referred to as disruptive behavior disorders (DBDs), are prevalent psychiatric disorders in children. Early diagnosis of DBDs is crucial because they can increase the risks of other mental health and substance use disorders without appropriate psychosocial interventions and treatment. However, diagnosing DBDs is challenging as they are often comorbid with other disorders, such as attention-deficit/hyperactivity disorder, anxiety, and depression. In this study, a multimodal ensemble three-dimensional convolutional neural network (3D CNN) deep learning model was used to classify children with DBDs and typically developing children. The study participants included 419 females and 681 males, aged 108–131 months who were enrolled in the Adolescent Brain Cognitive Development Study. Children were grouped based on the presence of DBDs (n = 550) and typically developing (n = 550); assessments were based on the scores from the Child Behavior Checklist and on the Schedule for Affective Disorders and Schizophrenia for School-age Children-Present and Lifetime version for DSM-5. The diffusion, structural, and resting-state functional magnetic resonance imaging (rs-fMRI) data were used as input data to the 3D CNN. The model achieved 72% accuracy in classifying children with DBDs with 70% sensitivity, 72% specificity, and an F1-score of 70. In addition, the discriminative power of the classifier was investigated by identifying the cortical and subcortical regions primarily involved in the prediction of DBDs using a gradient-weighted class activation mapping method. The classification results were compared with those obtained using the three neuroimaging modalities individually, and a connectome-based graph CNN and a multi-scale recurrent neural network using only the rs-fMRI data.

scholarly journals A New Approach to Preform Design in Metal Forging Processes Based on the Convolution Neural Network

2021 ◽  
Vol 11 (17) ◽  
pp. 7948
Author(s):  
Seungro Lee ◽  
Luca Quagliato ◽  
Donghwi Park ◽  
Inwoo Kwon ◽  
Juhyun Sun ◽  
...  
Keyword(s):  
Neural Network ◽  
Design Methodology ◽  
Three Dimensional ◽  
Convolution Neural Network ◽  
Design System ◽  
Preform Design ◽  
Plane Symmetric ◽  
Innovative Methodology ◽  
Quarter Plane ◽  
3D Cnn

This study presents an innovative methodology for preform design in metal forging processes based on the convolution neural network (CNN) algorithm. The proposed approach extracts the features of inputted forging product geometries and utilizes them to derive the corresponding preform shapes by employing weight arrays (filters) determined during the convolutional operations. The filters are progressively updated during the training process, emulating the learning steps of a process engineer responsible for the design of preform shapes for the forging processes. The design system is composed of multiple three-dimensional (3D) CNN sub-models, which can automatically derive individual 3D preform design candidates. It also implies that the 3D surfaces of preforms are easily acquired, which is important for the forging industry. The proposed preform design methodology was validated by applying it to two-dimensional (2D) axisymmetric shapes, one-quarter plane-symmetric 3D shapes, and two other industrial cases. In all the considered cases, the design methodology achieved substantial reductions in the forging load without forging defects, proving its reliability and effectiveness for application in metal forging processes.

scholarly journals BrainGNN: Interpretable Brain Graph Neural Network for fMRI Analysis

2020 ◽  
Author(s):  
Xiaoxiao Li ◽  
Yuan Zhou ◽  
Siyuan Gao ◽  
Nicha Dvornek ◽  
Muhan Zhang ◽  
...  
Keyword(s):  
Neural Network ◽  
Image Analysis ◽  
Medical Image Analysis ◽  
Special Property ◽  
Brain Regions ◽  
Magnetic Resonance Images ◽  
Group Level ◽  
Human Connectome Project ◽  
Fmri Analysis ◽  
Community Clustering

AbstractUnderstanding how certain brain regions relate to a specific neurological disorder or cognitive stimuli has been an important area of neuroimaging research. We propose BrainGNN, a graph neural network (GNN) framework to analyze functional magnetic resonance images (fMRI) and discover neurological biomarkers. Considering the special property of brain graphs, we design novel ROI-aware graph convolutional (Ra-GConv) layers that leverage the topological and functional information of fMRI. Motivated by the need for transparency in medical image analysis, our BrainGNN contains ROI-selection pooling layers (R-pool) that highlight salient ROIs (nodes in the graph), so that we can infer which ROIs are important for prediction. Furthermore, we propose regularization terms - unit loss, topK pooling (TPK) loss and group-level consistency (GLC) loss - on pooling results to encourage reasonable ROI-selection and provide flexibility to preserve either individual- or group-level patterns. We apply the BrainGNN framework on two independent fMRI datasets: Autism Spectral Disorder (ASD) fMRI dataset and Human Connectome Project (HCP) 900 Subject Release. We investigate different choices of the hyperparameters and show that BrainGNN outperforms the alternative fMRI image analysis methods in terms of four different evaluation metrics. The obtained community clustering and salient ROI detection results show high correspondence with the previous neuroimaging-derived evidence of biomarkers for ASD and specific task states decoded for HCP.

scholarly journals Intelligent Identification of MoS2 Nanostructures with Hyperspectral Imaging by 3D-CNN

Nanomaterials ◽  
2020 ◽  
Vol 10 (6) ◽  
pp. 1161 ◽  
Author(s):  
Kai-Chun Li ◽  
Ming-Yen Lu ◽  
Hong Thai Nguyen ◽  
Shih-Wei Feng ◽  
Sofya B. Artemkina ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Hyperspectral Imaging ◽  
2D Materials ◽  
Image Resolution ◽  
Superior Performance ◽  
Color Contrast ◽  
Synthesis Methods ◽  
Specific Substrate ◽  
3D Cnn

Increasing attention has been paid to two-dimensional (2D) materials because of their superior performance and wafer-level synthesis methods. However, the large-area characterization, precision, intelligent automation, and high-efficiency detection of nanostructures for 2D materials have not yet reached an industrial level. Therefore, we use big data analysis and deep learning methods to develop a set of visible-light hyperspectral imaging technologies successfully for the automatic identification of few-layers MoS2. For the classification algorithm, we propose deep neural network, one-dimensional (1D) convolutional neural network, and three-dimensional (3D) convolutional neural network (3D-CNN) models to explore the correlation between the accuracy of model recognition and the optical characteristics of few-layers MoS2. The experimental results show that the 3D-CNN has better generalization capability than other classification models, and this model is applicable to the feature input of the spatial and spectral domains. Such a difference consists in previous versions of the present study without specific substrate, and images of different dynamic ranges on a section of the sample may be administered via the automatic shutter aperture. Therefore, adjusting the imaging quality under the same color contrast conditions is unnecessary, and the process of the conventional image is not used to achieve the maximum field of view recognition range of ~1.92 mm2. The image resolution can reach ~100 nm and the detection time is 3 min per one image.

Sign in / Sign up

Export Citation Format

Share Document