Adaptive Multimodal Brain Network Model Improves Cross-Site Autism Classification Accuracy
Bioengineer.org
A deep learning model combining structural MRI and resting-state fMRI data, called CAS-GNN, significantly improves the accuracy of autism classification across different imaging centers. The model achieved an average accuracy of 78.75% in cross-validation and 79.25% on independent test data, demonstrating reliable separation of autistic individuals from controls. The approach addresses challenges of biological and hardware variability by integrating multimodal data and anchoring dynamic connectivity to stable anatomical structures.
All articles from 7 November 2026. Summaries are AI-generated and may contain errors; the linked article is the authority.
Get this news by email
Daily or as a weekly roundup in your inbox. You confirm your address first; every email has an unsubscribe link. For another topic or language, use the subscribe page.