Improving the Diagnosis of Psychiatric Disorders with Self-Supervised Graph State Space Models

Gazzar, Ahmed El; Thomas, Rajat Mani; Wingen, Guido van

doi:10.48550/arxiv.2206.03331

Cited by 2 publications

(2 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, graph explainability techniques [Ying et al, 2019, Huang et al, 2022 could be utilized to find potential functional connectivity biomarkers for phenotypes and psychiatric disorders. The application of graph self-supervised learning techniques Fedorov et al [2021], , Peng et al [2022] and graph normative modelling [Gazzar et al, 2022] on non-clinical datasets would assist in learning representations that could further be transferred to a downstream clinical tasks. Graph augmentation methods Zhao et al [2021] could boost the statistical power of the clinical datasets and assist in solving the problem of labeled data scarcity and regularize overfitting.…”

Section: Discussionmentioning

confidence: 99%

Benchmarking Graph Neural Networks for FMRI analysis

El‐Gazzar¹,

Thomas²,

Wingen³

2022

Preprint

View full text Add to dashboard Cite

Graph Neural Networks (GNNs) have emerged as a powerful tool to learn from graph-structured data. A paramount example of such data is the brain, which operates as a network, from the microscale of neurons, to the macro-scale of regions. This organization deemed GNNs a natural tool of choice to model brain activity, and have consequently attracted a lot of attention in the neuroimaging community. Yet, the advantage of adopting these models over conventional methods has not yet been assessed in a systematic way to gauge if GNNs are capable of leveraging the underlying structure of the data to improve learning. In this work, we study and evaluate the performance of five popular GNN architectures in diagnosing major depression disorder and autism spectrum disorder in two multi-site clinical datasets, and sex classification on the UKBioBank, from functional brain scans under a general uniform framework. Our results show that GNNs fail to outperform kernel-based and structure-agnostic deep learning models, in which 1D CNNs outperform the other methods in all scenarios. We highlight that creating optimal graph structures for functional brain data is a major bottleneck hindering the performance of GNNs, where existing works use arbitrary measures to define the edges resulting in noisy graphs. We therefore propose to integrate graph diffusion into existing architectures and show that it can alleviate this problem and improve their performance. Our results call for increased moderation and rigorous validation when evaluating graph methods and advocate for more data-centeric approaches in developing GNNs for functional neuroimaging applications. 1

show abstract

Section: Discussionmentioning

confidence: 99%

Benchmarking Graph Neural Networks for FMRI analysis

El‐Gazzar¹,

Thomas²,

Wingen³

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Here, we compare the results yielded by our method with SOTA methods that also use fMRI data from the REST-MDD dataset. Several studies (Gallo et al, 2021;Yan et al, 2019) achieved accuracy ranging from 61% to 63% in MDD versus HC classification on REST-MDD, and a latest research (Gazzar et al, 2022) obtained an accuracy of 63%. It can be observed that the results of these SOTA studies are not that promising, suggesting that there is a great challenge in performing the fMRI-based MDD detection task on REST-MDD.…”

Section: Comparison With Exiting Studiesmentioning

confidence: 99%

Unsupervised contrastive graph learning for resting‐state functional MRI analysis and brain disorder detection

Wang,

Chu,

Wang

et al. 2023

Human Brain Mapping

View full text Add to dashboard Cite

Resting‐state functional magnetic resonance imaging (rs‐fMRI) helps characterize regional interactions that occur in the human brain at a resting state. Existing research often attempts to explore fMRI biomarkers that best predict brain disease progression using machine/deep learning techniques. Previous fMRI studies have shown that learning‐based methods usually require a large amount of labeled training data, limiting their utility in clinical practice where annotating data is often time‐consuming and labor‐intensive. To this end, we propose an unsupervised contrastive graph learning (UCGL) framework for fMRI‐based brain disease analysis, in which a pretext model is designed to generate informative fMRI representations using unlabeled training data, followed by model fine‐tuning to perform downstream disease identification tasks. Specifically, in the pretext model, we first design a bi‐level fMRI augmentation strategy to increase the sample size by augmenting blood‐oxygen‐level‐dependent (BOLD) signals, and then employ two parallel graph convolutional networks for fMRI feature extraction in an unsupervised contrastive learning manner. This pretext model can be optimized on large‐scale fMRI datasets, without requiring labeled training data. This model is further fine‐tuned on to‐be‐analyzed fMRI data for downstream disease detection in a task‐oriented learning manner. We evaluate the proposed method on three rs‐fMRI datasets for cross‐site and cross‐dataset learning tasks. Experimental results suggest that the UCGL outperforms several state‐of‐the‐art approaches in automated diagnosis of three brain diseases (i.e., major depressive disorder, autism spectrum disorder, and Alzheimer's disease) with rs‐fMRI data.

show abstract

Improving the Diagnosis of Psychiatric Disorders with Self-Supervised Graph State Space Models

Cited by 2 publications

References 38 publications

Benchmarking Graph Neural Networks for FMRI analysis

Benchmarking Graph Neural Networks for FMRI analysis

Unsupervised contrastive graph learning for resting‐state functional MRI analysis and brain disorder detection

Contact Info

Product

Resources

About