Diagnosis of autism disorder from rs-fMRI brain images through hierarchical YOLO and mechanism of attention (HYMA)

Key Points

• Improved detection accuracy for autism using an attention mechanism, enhancing traditional neural methods.
• Achieved 92% accuracy with hierarchical YOLO in analyzing 200 rs-fMRI brain images.
• Assessment using computer vision techniques, applying a deep learning framework for image classification.
• Highlights the potential of AI in diagnosing autism, requiring further validation across diverse populations.