Related Experiment Video
Updated: May 21, 2025
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
Published on: November 30, 2022
Multi-modal pre-post treatment consistency learning for automatic segmentation and evaluation of the Circle of Willis
Zehang Lin1, Yusheng Liu2, Jiahua Wu1
1School of Computer and Information Engineering, Xiamen University of Technology, Xiamen, China.
Insights
This study introduces a new framework for analyzing brain vascular changes using CT and MR angiography. It improves segmentation accuracy and reliably evaluates treatment effectiveness, overcoming previous limitations.
Area of Science:
- Neuroimaging
- Medical Image Analysis
- Vascular Biology
Background:
- The Circle of Willis (CoW) is critical for brain vascular health diagnosis.
- CT angiography (CTA) and MR angiography (MRA) are used for pre- and post-treatment assessment.
- Previous single-modality segmentation methods cause cumulative errors, hindering accurate treatment evaluation.
Purpose of the Study:
- To develop a comprehensive framework for accurate CoW segmentation and treatment efficacy evaluation across different imaging modalities.
- To address challenges in differentiating segmentation errors from actual therapeutic effects in CoW analysis.
- To improve clinical assessment of treatment outcomes for vascular diseases.
Main Methods:
- Proposed a Cross-Modal Semantic Consistency Network (CMSC-Net) for segmentation, featuring a Modality Pair Alignment Module (MPAM) and Cross-Modal Attention Module (CMAM).
- Integrated a novel loss function for semantic consistency across CTA and MRA modalities.
- Developed a Semantic Consistency Evaluation Network (SC-ENet) for automated treatment efficacy assessment by tracking morphological changes.
Main Results:
- CMSC-Net achieved consistent Circle of Willis segmentation across CTA and MRA modalities.
- SC-ENet demonstrated high-precision automated evaluation of treatment efficacy.
- The integrated framework effectively mitigates cumulative errors from single-modality segmentation.
Conclusions:
- The proposed framework provides accurate and consistent Circle of Willis segmentation across imaging modalities.
- The framework enables reliable automated evaluation of treatment efficacy, distinguishing therapeutic effects from segmentation artifacts.
- This approach enhances clinical decision-making for vascular disease treatment by improving pre- and post-treatment assessments.
Abstract:
The Circle of Willis (CoW) is a crucial vascular structure in the brain, vital for diagnosing vascular diseases. During the acute phase of diseases, CT angiography (CTA) is commonly used to locate occlusions within the CoW quickly. After treatment, MR angiography (MRA) is preferred to visualize postoperative vascular structures, reducing radiation exposure. Clinically, the pre- and post-treatment (P&P-T) changes in the CoW are critical for assessing treatment efficacy. However, previous studies focused on single-modality segmentation, leading to cumulative errors when segmenting CoW in CTA and MRA modalities separately. Thus, it is challenging to differentiate whether changes in the CoW are due to segmentation errors or actual therapeutic effects when evaluating treatment efficacy. To address these challenges, we propose a comprehensive framework integrating the Cross-Modal Semantic Consistency Network (CMSC-Net) for segmentation and the Semantic Consistency Evaluation Network (SC-ENet) for treatment evaluation. Specifically, CMSC-Net includes two key components: the Modality Pair Alignment Module (MPAM), which generates spatially aligned modality pairs (CTA-MRA, MRA-CTA) to mitigate imaging discrepancies, and the Cross-Modal Attention Module (CMAM), which enhances CTA segmentation by leveraging high-resolution MRA features. Additionally, a novel loss function ensures semantic consistency across modalities, supporting stable network convergence. Meanwhile, SC-ENet automates treatment efficacy evaluation by extracting static vascular features and dynamically tracking morphological changes over time. Experimental results show that CTMSC-Net achieves consistent CoW segmentation across modalities, with SC-ENet delivering high-precision treatment evaluation.
