Deep Learning-based Classification of Resting-state fMRI Independent-component Analysis

GINNA, a 33 resting-state networks atlas with meta-analytic decoding-based cognitive characterization

Since resting-state networks were first observed using magnetic resonance imaging (MRI), their cognitive relevance has been widely suggested. However, to date, the empirical cognitive characterization of these networks has been limited. The present study introduces the Groupe d'Imagerie Neurofonctionnelle Network Atlas, a comprehensive brain atlas featuring 33 resting-state networks. Based on the resting-state data of 1812 participants, the atlas was developed by classifying independent components extracted individually, ensuring consistent between-subject detection. We further explored the cognitive relevance of each GINNA network using Neurosynth-based meta-analytic decoding and generative null hypothesis testing. Significant cognitive terms for each network were then synthesized into appropriate cognitive processes through the consensus of six authors. The GINNA atlas showcases a diverse range of topological profiles, reflecting a broad spectrum of the known human cognitive repertoire. The processes associated with each network are named according to the standard Cognitive Atlas ontology, thus providing opportunities for empirical validation.

The expert's knowledge combined with AI outperforms AI alone in seizure onset zone localization using resting state fMRI

We evaluated whether integration of expert guidance on seizure onset zone (SOZ) identification from resting state functional MRI (rs-fMRI) connectomics combined with deep learning (DL) techniques enhances the SOZ delineation in patients with refractory epilepsy (RE), compared to utilizing DL alone. Rs-fMRI was collected from 52 children with RE who had subsequently undergone ic-EEG and then, if indicated, surgery for seizure control (n = 25). The resting state functional connectomics data were previously independently classified by two expert epileptologists, as indicative of measurement noise, typical resting state network connectivity, or SOZ. An expert knowledge integrated deep network was trained on functional connectomics data to identify SOZ. Expert knowledge integrated with DL showed a SOZ localization accuracy of 84.8 ± 4.5% and F1 score, harmonic mean of positive predictive value and sensitivity, of 91.7 ± 2.6%. Conversely, a DL only model yielded an accuracy of <50% (F1 score 63%). Activations that initiate in gray matter, extend through white matter, and end in vascular regions are seen as the most discriminative expert-identified SOZ characteristics. Integration of expert knowledge of functional connectomics can not only enhance the performance of DL in localizing SOZ in RE but also lead toward potentially useful explanations of prevalent co-activation patterns in SOZ. RE with surgical outcomes and preoperative rs-fMRI studies can yield expert knowledge most salient for SOZ identification.

Multi feature fusion network for schizophrenia classification and abnormal brain network recognition

Schizophrenia classification and abnormal brain network recognition have an important research significance. Researchers have proposed many classification methods based on machine learning and deep learning. However, fewer studies utilized the advantages of complementary information from multi feature to learn the best representation of schizophrenia. In this study, we proposed a multi-feature fusion network (MFFN) using functional network connectivity (FNC) and time courses (TC) to distinguish schizophrenia patients from healthy controls. DNN backbone was adopted to learn the feature map of functional network connectivity, C-RNNAM backbone was designed to learn the feature map of time courses, and Deep SHAP was applied to obtain the most discriminative brain networks. We proved the effectiveness of this proposed model using the combining two public datasets and evaluated this model quantitatively using the evaluation indexes. The results showed that the functional network connectivity generated by independent component analysis has advantage in schizophrenia classification by comparing static and dynamic functional connections. This method obtained the best classification accuracy (ACC=87.30%, SPE=89.28%, SEN=85.71%, F1 =88.23%, and AUC=0.9081), and it demonstrated the superiority of this proposed model by comparing state-of-the-art methods. Ablation experiment also demonstrated that multi feature fusion and attention module can improve classification accuracy. The most discriminative brain networks showed that default mode network and visual network of schizophrenia patients have aberrant connections in brain networks. In conclusion, this method can identify schizophrenia effectively and visualize the abnormal brain network, and it has important clinical application value.

Atlasing white matter and grey matter joint contributions to resting-state networks in the human brain

Over the past two decades, the study of resting-state functional magnetic resonance imaging has revealed that functional connectivity within and between networks is linked to cognitive states and pathologies. However, the white matter connections supporting this connectivity remain only partially described. We developed a method to jointly map the white and grey matter contributing to each resting-state network (RSN). Using the Human Connectome Project, we generated an atlas of 30 RSNs. The method also highlighted the overlap between networks, which revealed that most of the brain's white matter (89%) is shared between multiple RSNs, with 16% shared by at least 7 RSNs. These overlaps, especially the existence of regions shared by numerous networks, suggest that white matter lesions in these areas might strongly impact the communication within networks. We provide an atlas and an open-source software to explore the joint contribution of white and grey matter to RSNs and facilitate the study of the impact of white matter damage to these networks. In a first application of the software with clinical data, we were able to link stroke patients and impacted RSNs, showing that their symptoms aligned well with the estimated functions of the networks.

Automated seizure onset zone locator from resting-state functional MRI in drug-resistant epilepsy

OBJECTIVE

Accurate localization of a seizure onset zone (SOZ) from independent components (IC) of resting-state functional magnetic resonance imaging (rs-fMRI) improves surgical outcomes in children with drug-resistant epilepsy (DRE). Automated IC sorting has limited success in identifying SOZ localizing ICs in adult normal rs-fMRI or uncategorized epilepsy. Children face unique challenges due to the developing brain and its associated surgical risks. This study proposes a novel SOZ localization algorithm (EPIK) for children with DRE.

METHODS

EPIK is developed in a phased approach, where fMRI noise-related biomarkers are used through high-fidelity image processing techniques to eliminate noise ICs. Then, the SOZ markers are used through a maximum likelihood-based classifier to determine SOZ localizing ICs. The performance of EPIK was evaluated on a unique pediatric DRE dataset (n = 52). A total of 24 children underwent surgical resection or ablation of an rs-fMRI identified SOZ, concurrently evaluated with an EEG and anatomical MRI. Two state-of-art techniques were used for comparison: (a) least squares support-vector machine and (b) convolutional neural networks. The performance was benchmarked against expert IC sorting and Engel outcomes for surgical SOZ resection or ablation. The analysis was stratified across age and sex.

RESULTS

EPIK outperformed state-of-art techniques for SOZ localizing IC identification with a mean accuracy of 84.7% (4% higher), a precision of 74.1% (22% higher), a specificity of 81.9% (3.2% higher), and a sensitivity of 88.6% (16.5% higher). EPIK showed consistent performance across age and sex with the best performance in those < 5 years of age. It helped achieve a ~5-fold reduction in the number of ICs to be potentially analyzed during pre-surgical screening.

SIGNIFICANCE

Automated SOZ localization from rs-fMRI, validated against surgical outcomes, indicates the potential for clinical feasibility. It eliminates the need for expert sorting, outperforms prior automated methods, and is consistent across age and sex.

Sparse Hierarchical Representation Learning on Functional Brain Networks for Prediction of Autism Severity Levels

Machine learning algorithms have been widely applied in diagnostic tools for autism spectrum disorder (ASD), revealing an altered brain connectivity. However, little is known about whether an magnetic resonance imaging (MRI)-based brain network is related to the severity of ASD symptoms in a large-scale cohort. We propose a graph convolution neural network-based framework that can generate sparse hierarchical graph representations for functional brain connectivity. Instead of assigning initial features for each node, we utilized a feature extractor to derive node features and the extracted representations can be fed to a hierarchical graph self-attention framework to effectively represent the entire graph. By incorporating connectivity embeddings in the feature extractor, we propose adjacency embedding networks to characterize the heterogeneous representations of the brain connectivity. Our proposed model variants outperform the benchmarking model with different configurations of adjacency embedding networks and types of functional connectivity matrices. Using this approach with the best configuration (SHEN atlas for node definition, Tikhonov correlation for connectivity estimation, and identity-adjacency embedding), we were able to predict individual ASD severity levels with a meaningful accuracy: the mean absolute error (MAE) and correlation between predicted and observed ASD severity scores resulted in 0.96, and r = 0.61 (P < 0.0001), respectively. To obtain a better understanding on how to generate better representations, we investigate the relationships between the extracted feature embeddings and the graph theory-based nodal measurements using canonical correlation analysis. Finally, we visualized the model to identify the most contributive functional connections for predicting ASD severity scores.

Automated Classification of Resting-State fMRI ICA Components Using a Deep Siamese Network

Manual classification of functional resting state networks (RSNs) derived from Independent Component Analysis (ICA) decomposition can be labor intensive and requires expertise, particularly in large multi-subject analyses. Hence, a fully automatic algorithm that can reliably classify these RSNs is desirable. In this paper, we present a deep learning approach based on a Siamese Network to learn a discriminative feature representation for single-subject ICA component classification. Advantages of this supervised framework are that it requires relatively few training data examples and it does not require the number of ICA components to be specified. In addition, our approach permits one-shot learning, which allows generalization to new classes not seen in the training set with only one example of each new class. The proposed method is shown to out-perform traditional convolutional neural network (CNN) and template matching methods in identifying eleven subject-specific RSNs, achieving 100% accuracy on a holdout data set and over 99% accuracy on an outside data set. We also demonstrate that the method is robust to scan-rescan variation. Finally, we show that the functional connectivity of default mode and salience networks identified by the proposed technique is altered in a group analysis of mild traumatic brain injury (TBI), severe TBI, and healthy subjects.

Understanding complex functional wiring patterns in major depressive disorder through brain functional connectome

Brain function relies on efficient communications between distinct brain systems. The pathology of major depressive disorder (MDD) damages functional brain networks, resulting in cognitive impairment. Here, we reviewed the associations between brain functional connectome changes and MDD pathogenesis. We also highlighted the utility of brain functional connectome for differentiating MDD from other similar psychiatric disorders, predicting recurrence and suicide attempts in MDD, and evaluating treatment responses. Converging evidence has now linked aberrant brain functional network organization in MDD to the dysregulation of neurotransmitter signaling and neuroplasticity, providing insights into the neurobiological mechanisms of the disease and antidepressant efficacy. Widespread connectome dysfunctions in MDD patients include multiple, large-scale brain networks as well as local disturbances in brain circuits associated with negative and positive valence systems and cognitive functions. Although the clinical utility of the brain functional connectome remains to be realized, recent findings provide further promise that research in this area may lead to improved diagnosis, treatments, and clinical outcomes of MDD.