We demonstrate that the functional networks learned by the LSTM model are more strongly associated with the task activity and dynamics compared to other approaches.
Heterogeneous presentation of a neurological disorder suggests potential differences in the underlying pathophysiological changes that occur in the brain.
Neural ordinary differential equations (Neural ODEs) are a new family of deep-learning models with continuous depth.
Ranked #18 on Image Generation on ImageNet 64x64
We propose an interpretable GNN framework with a novel salient region selection mechanism to determine neurological brain biomarkers associated with disorders.
no code implementations • 5 Jun 2020 • Markus D. Schirmer, Archana Venkataraman, Islem Rekik, Minjeong Kim, Stewart H. Mostofsky, Mary Beth Nebel, Keri Rosch, Karen Seymour, Deana Crocetti, Hassna Irzan, Michael Hütel, Sebastien Ourselin, Neil Marlow, Andrew Melbourne, Egor Levchenko, Shuo Zhou, Mwiza Kunda, Haiping Lu, Nicha C. Dvornek, Juntang Zhuang, Gideon Pinto, Sandip Samal, Jennings Zhang, Jorge L. Bernal-Rusiel, Rudolph Pienaar, Ai Wern Chung
A second set of 100 subjects (50 neurotypical controls, 25 ADHD, and 25 ASD with ADHD comorbidity) was used for testing.
This work proposes a pipeline to predict treatment response to intra-arterial therapy of patients with Hepatocellular Carcinoma (HCC) for improved therapeutic decision-making.
The addition of the generative model constrains the network to learn functional communities represented by the LSTM nodes that are both consistent with the data generation as well as useful for the classification task.
We can determine the decision boundary of a linear classifier in the feature space; since the transform is invertible, we can invert the decision boundary from the feature space to the input space.
For the DA task, our DALACE model outperformed CycleGAN, TD-GAN , and DADR with DSC of 0. 847 compared to 0. 721, 0. 793 and 0. 806.
Here, we model the whole brain fMRI as a graph, which preserves geometrical and temporal information and use a Graph Neural Network (GNN) to learn from the graph-structured fMRI data.
First, images from each domain are embedded into two spaces, a shared domain-invariant content space and a domain-specific style space.
Recently deep learning methods have achieved success in the classification task of ASD using fMRI data.
Our pipeline can be generalized to other graph feature importance interpretation problems.
Cooperative game theory is advantageous here because it directly considers the interaction between features and can be applied to any machine learning method, making it a novel, more accurate way of determining instance-wise biomarker importance from deep learning models.
Therefore, in this work, we address the problem of interpreting reliable biomarkers associated with identifying ASD; specifically, we propose a 2-stage method that classifies ASD and control subjects using fMRI images and interprets the saliency features activated by the classifier.
We propose predicting patient response to PRT from baseline task-based fMRI by the novel application of a random forest and tree bagging strategy.