Automatic Evaluating of Multi-Phase Cranial CTA Collateral Circulation Based on Feature Fusion Attention Network...

Area of Science:

• Medical imaging analysis
• Artificial intelligence in medicine
• Neurology

Background:

• Stroke, particularly ischemic stroke, is a leading cause of death and disability.
• Computed tomography angiography (CTA) is crucial for assessing collateral circulation in stroke patients, guiding treatment and prognosis.
• Current deep learning models often lack temporal information from multi-phase CTA, limiting their ability to represent collateral circulation features effectively.

Purpose of the Study:

• To develop an advanced deep learning model for accurate collateral circulation evaluation in stroke patients.
• To address the limitations of single-phase data in existing AI models by incorporating temporal dimension information.
• To enhance the feature representation and performance of AI in analyzing multi-phase cranial CTA images.

Main Methods:

• Proposed a hybrid mechanism with a hybrid attention mechanism for feature encoding network.
• Incorporated temporal dimension information from multi-phase CTA data.
• Designed multi-branch networks with feature-level fusion modules, including single-stage and multi-stage fusion, to integrate deep/shallow and multi-phase vessel features.

Main Results:

• The proposed model achieved an accuracy rate exceeding 90.43% on a dataset of multi-phase cranial CTA images.
• The hybrid mechanism and feature fusion modules effectively explored collateral vessel features.
• Demonstrated improved feature expression capabilities and optimized deep learning network performance.

Conclusions:

• The integration of temporal information and advanced feature fusion techniques significantly enhances the accuracy and reliability of AI-based collateral circulation evaluation.
• The developed hybrid mechanism offers a promising approach for improving computer-aided diagnosis in stroke management.
• This study highlights the importance of multi-phase image data and sophisticated network architectures for robust medical image analysis.