Multi-view site independent adaptation via prototypical contrastive learning for ASD
Poster No:
1132
Submission Type:
Abstract Submission
Authors:
Junhai Xu1, Jinghan Ouyang1
Institutions:
1Tianjin University, Tianjin, Tianjin
First Author:
Co-Author:
Introduction:
The resting-state functional magnetic resonance imaging (rs-fMRI) technique has been extensively needed to identify the underlying neurodegenerative conditions such as Autism Spectrum Disorders. However, most of the current work relies on the low-order brain network features, which only reflect the pairwise relationships between regions, overlooking the complex interactions present in the high-order connectivity. Moreover, the heterogeneity of data collected from multiple sites also remains great challenges for downstream tasks.
Methods:
To tackle these challenges, we propose a novel Multi-view Site Independent Adaptation via Prototypical Contrastive Learning (MSIA-PCL) for autism spectrum disorder diagnosis. Specifically, MSIA-PCL performs the domain adaptation of both low-order and high-order brain network features to maximize the site independence to reduce data heterogeneity. Then, a multi-modal representation fusion module aggregates overall features by capturing the underlying relationships between different modalities. Furthermore, we propose a multi-view prototypical contrastive learning approach to enhance the learning capability of the model, maximize the consistency of the representation learned across different views, and collaboratively capture different relationships while encoding the semantic information discovered by clusters into the learned embedding space.
·Detailed construction of the proposed method
Results:
We select five metrics to evaluate the performance of the models in identifying ASD on the ABIDE dataset. It can be seen that the method we proposed achieves a better performance across various evaluation metrics. With SVM and LR as the baseline methods for comparison, we can see that our proposed model has achieved an accuracy improvement of nearly 10%. Specifically, it obtains Accuracy, AUC, Recall, Precision and F1 of 75.54%, 75.04%, 82.07%, 75.62% and 78.27% respectively.
·Visualization of different representation on the ABIDE dataset
Conclusions:
Extensive experiments on ABIDE database demonstrate the significant superiority across different data acquisition sites and protocols of MSIA-PCL.
Modeling and Analysis Methods:
Classification and Predictive Modeling 1
Connectivity (eg. functional, effective, structural) 2
Keywords:
Autism
Data analysis
DISORDERS
Modeling
1|2Indicates the priority used for review
Abstract Information
By submitting your proposal, you grant permission for the Organization for Human Brain Mapping (OHBM) to distribute your work in any format, including video, audio print and electronic text through OHBM OnDemand, social media channels, the OHBM website, or other electronic publications and media.
The Open Science Special Interest Group (OSSIG) is introducing a reproducibility challenge for OHBM 2025. This new initiative aims to enhance the reproducibility of scientific results and foster collaborations between labs. Teams will consist of a “source” party and a “reproducing” party, and will be evaluated on the success of their replication, the openness of the source work, and additional deliverables. Click here for more information. Propose your OHBM abstract(s) as source work for future OHBM meetings by selecting one of the following options:
Please indicate below if your study was a "resting state" or "task-activation” study.
Healthy subjects only or patients (note that patient studies may also involve healthy subjects):
Was this research conducted in the United States?
Were any human subjects research approved by the relevant Institutional Review Board or ethics panel? NOTE: Any human subjects studies without IRB approval will be automatically rejected.
Were any animal research approved by the relevant IACUC or other animal research panel? NOTE: Any animal studies without IACUC approval will be automatically rejected.
Please indicate which methods were used in your research:
For human MRI, what field strength scanner do you use?
Which processing packages did you use for your study?
Provide references using APA citation style.
Huang, Z.A., Zhu, Z., Yau, C.H., Tan, K.C. (2021). Identifying Autism Spectrum Disorder From Resting-State fMRI Using Deep Belief Network. IEEE Transactions on Neural Networks and Learning Systems 32, 2847–2861.
Kim, S., Lee, N., Lee, J., Hyun, D., Park, C. (2023). Heterogeneous Graph Learning for Multi-Modal Medical Data Analysis. Proceedings of the AAAI Conference on Artificial Intelligence 37, 5141–5150.
Zhang, Z., Bu, J., Ester, M., Zhang, J., Li, Z., Yao, C., Huifen, D., Yu, Z., Wang, C. (2021). Hierarchical Multi-View Graph Pooling with Structure Learning. IEEE Transactions on Knowledge and Data Engineering , 1