DYNAFormer: Enhancing transformer segmentation with dynamic anchor mask for medical imaging
Tan-Cong Nguyen, Kim Anh Phung, Thao Thi Phuong Dao, Trong-Hieu Nguyen-Mau, Thuc Nguyen-Quang, Cong Nhan Pham, Trung-Nghia Le, Ju Shen, Tam Nguyen, Minh–Triet Tran · Computers in Biology and Medicine · 2025
Polyp shape is critical for diagnosing colorectal polyps and assessing cancer risk, yet there is limited data on segmenting pedunculated and sessile polyps. This paper introduces PolypDB_INS, a dataset of 4403 images containing 4918 annotated polyps, specifically for sessile and pedunculated polyps. In addition, we propose DYNAFormer, a novel transformer-based model utilizing an anchor mask-guided mechanism that incorporates cross-attention, dynamic query updates, and query denoising for improved object segmentation. Treating each positional query as an anchor mask dynamically updated through decoder layers enhances perceptual information regarding the object's position, allowing for more precise segmentation of complex structures like polyps. Extensive experiments on the PolypDB_INS dataset using standard evaluation metrics for both instance and semantic segmentation show that DYNAFormer significantly outperforms state-of-the-art methods. Ablation studies confirm the effectiveness of the proposed techniques, highlighting the model's robustness for diagnosing colorectal cancer. The source code and dataset are available at https://github.com/ntcongvn/DYNAFormer https://github.com/ntcongvn/DYNAFormer.