Researchers from Central China Normal University have developed CoReFuse-Med, a novel method for multi-modal medical image segmentation. This approach addresses the issue of low-quality modalities negatively impacting the fusion process, particularly when dealing with MRI scans where different sequences (T1, T2, FLAIR) have varying sampling qualities. CoReFuse-Med first purifies these modalities before rebalancing and fusing them, aiming to improve the accuracy of segmentation by preventing artifacts from low-quality data from compromising high-quality data. AI
IMPACT This research could lead to more accurate medical diagnoses by improving the quality of fused multi-modal image data.
RANK_REASON The cluster describes a new method for medical image segmentation presented at a conference, which falls under research. [lever_c_demoted from research: ic=1 ai=1.0]
- ACM MM 2026
- Central China Normal University
- CoReFuse
- CoReFuse-Med
- Dingwen Hu
- Gang Li
- Huazhong University of Science and Technology
- Leiphone
- Shijun Qiu
- The First Affiliated Hospital of Guangzhou University of Chinese Medicine
- University of North Carolina at Chapel Hill
- Xiaoyu Hu
- Xu Chu
- Yixiong Zou
- Yuchen Pei
- Yutao Ma
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
