Xian Lin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Xian Lin has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Zengqiang Yan
Huazhong University of Science and Technology
12 shared publications - Li Yu
Huazhong University of Science and Technology
10 shared publications - Kwang-Ting Cheng
Department of Electronic and Computer Engineering, the Hong Kong University of Science and Technology, Hong Kong, China
5 shared publications Li Yu
3 shared publications- Chuansheng Zheng
Department of Radiology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
2 shared publications - Xianbo Deng
Department of Radiology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
2 shared publications
Latest Publications
- 13 December 2025
- Published by Elsevier in Pattern Recognition
- Vol. 174
Selective intra- and inter-slice interaction for efficient anisotropic medical image segmentation
- 13 December 2025
- Published by Elsevier in Pattern Recognition
- Vol. 174
Selective intra- and inter-slice interaction for efficient anisotropic medical image segmentation
- 20 September 2025
- Published by Springer Nature
- p. 636-646
Towards Robust Medical Image Referring Segmentation with Incomplete Textual Prompts
- 20 September 2025
- Published by Springer Nature
- p. 636-646
Towards Robust Medical Image Referring Segmentation with Incomplete Textual Prompts
- 9 July 2025
- Published by Springer Nature
- p. 54-64
Segment Any Cancer in CT Scans Through Equipping SAM with Cross-Slice Interaction and Indicator Prompt
- 9 July 2025
- Published by Springer Nature
- p. 54-64
Segment Any Cancer in CT Scans Through Equipping SAM with Cross-Slice Interaction and Indicator Prompt
- 7 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 44 (3) , 1386-1399
SAMCT: Segment Any CT Allowing Labor-Free Task-Indicator Prompts
Segment anything model (SAM), a foundation model with superior versatility and generalization across diverse segmentation tasks, has attracted widespread attention in medical imaging. However, it has been proved that SAM would encounter severe performance degradation due to the lack of medical knowledge in training and local feature encoding. Though several SAM-based models have been proposed for tuning SAM in medical imaging, they still suffer from insufficient feature extraction and highly rely on high-quality prompts. In this paper, we propose a powerful foundation model SAMCT allowing labor-free prompts and train it on a collected large CT dataset consisting of 1.1M CT images and 5M masks from public datasets. Specifically, based on SAM, SAMCT is further equipped with a U-shaped CNN image encoder, a cross-branch interaction module, and a task-indicator prompt encoder. The U-shaped CNN image encoder works in parallel with the ViT image encoder in SAM to supplement local features. Cross-branch interaction enhances the feature expression capability of the CNN image encoder and the ViT image encoder by exchanging global perception and local features from one to the other. The task-indicator prompt encoder is a plug-and-play component to effortlessly encode task-related indicators into prompt embeddings. In this way, SAMCT can work in an automatic manner in addition to the semi-automatic interactive strategy in SAM. Extensive experiments demonstrate the superiority of SAMCT against the state-of-the-art task-specific and SAM-based medical foundation models on various tasks. The code, data, and model checkpoints are available at https://github.com/xianlin7/SAMCT.
- 7 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 44 (3) , 1386-1399
SAMCT: Segment Any CT Allowing Labor-Free Task-Indicator Prompts
Segment anything model (SAM), a foundation model with superior versatility and generalization across diverse segmentation tasks, has attracted widespread attention in medical imaging. However, it has been proved that SAM would encounter severe performance degradation due to the lack of medical knowledge in training and local feature encoding. Though several SAM-based models have been proposed for tuning SAM in medical imaging, they still suffer from insufficient feature extraction and highly rely on high-quality prompts. In this paper, we propose a powerful foundation model SAMCT allowing labor-free prompts and train it on a collected large CT dataset consisting of 1.1M CT images and 5M masks from public datasets. Specifically, based on SAM, SAMCT is further equipped with a U-shaped CNN image encoder, a cross-branch interaction module, and a task-indicator prompt encoder. The U-shaped CNN image encoder works in parallel with the ViT image encoder in SAM to supplement local features. Cross-branch interaction enhances the feature expression capability of the CNN image encoder and the ViT image encoder by exchanging global perception and local features from one to the other. The task-indicator prompt encoder is a plug-and-play component to effortlessly encode task-related indicators into prompt embeddings. In this way, SAMCT can work in an automatic manner in addition to the semi-automatic interactive strategy in SAM. Extensive experiments demonstrate the superiority of SAMCT against the state-of-the-art task-specific and SAM-based medical foundation models on various tasks. The code, data, and model checkpoints are available at https://github.com/xianlin7/SAMCT.
- 6 October 2024
- Published by Springer Nature
- p. 24-34
Beyond Adapting SAM: Towards End-to-End Ultrasound Image Segmentation via Auto Prompting
- 6 October 2024
- Published by Springer Nature
- p. 24-34
Beyond Adapting SAM: Towards End-to-End Ultrasound Image Segmentation via Auto Prompting
- 3 October 2024
- Published by Springer Nature
- p. 555-566
Revisiting Self-attention in Medical Transformers via Dependency Sparsification
- 3 October 2024
- Published by Springer Nature
- p. 555-566
Revisiting Self-attention in Medical Transformers via Dependency Sparsification
- Top Cited Papers
- 10 April 2024
- Published by Elsevier in Pattern Recognition
- Vol. 152
UCTNet: Uncertainty-guided CNN-Transformer hybrid networks for medical image segmentation
- 10 April 2024
- Published by Elsevier in Pattern Recognition
- Vol. 152
Top Cited PapersUCTNet: Uncertainty-guided CNN-Transformer hybrid networks for medical image segmentation
- Open Access
- 24 March 2024
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 38 (6) , 5814-5822
DTMFormer: Dynamic Token Merging for Boosting Transformer-Based Medical Image Segmentation
Despite the great potential in capturing long-range dependency, one rarely-explored underlying issue of transformer in medical image segmentation is attention collapse, making it often degenerate into a bypass module in CNN-Transformer hybrid architectures. This is due to the high computational complexity of vision transformers requiring extensive training data while well-annotated medical image data is relatively limited, resulting in poor convergence. In this paper, we propose a plug-n-play transformer block with dynamic token merging, named DTMFormer, to avoid building long-range dependency on redundant and duplicated tokens and thus pursue better convergence. Specifically, DTMFormer consists of an attention-guided token merging (ATM) module to adaptively cluster tokens into fewer semantic tokens based on feature and dependency similarity and a light token reconstruction module to fuse ordinary and semantic tokens. In this way, as self-attention in ATM is calculated based on fewer tokens, DTMFormer is of lower complexity and more friendly to converge. Extensive experiments on publicly-available datasets demonstrate the effectiveness of DTMFormer working as a plug-n-play module for simultaneous complexity reduction and performance improvement. We believe it will inspire future work on rethinking transformers in medical image segmentation. Code: https://github.com/iam-nacl/DTMFormer.
- 24 March 2024
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 38 (6) , 5814-5822
Open AccessDTMFormer: Dynamic Token Merging for Boosting Transformer-Based Medical Image Segmentation
Despite the great potential in capturing long-range dependency, one rarely-explored underlying issue of transformer in medical image segmentation is attention collapse, making it often degenerate into a bypass module in CNN-Transformer hybrid architectures. This is due to the high computational complexity of vision transformers requiring extensive training data while well-annotated medical image data is relatively limited, resulting in poor convergence. In this paper, we propose a plug-n-play transformer block with dynamic token merging, named DTMFormer, to avoid building long-range dependency on redundant and duplicated tokens and thus pursue better convergence. Specifically, DTMFormer consists of an attention-guided token merging (ATM) module to adaptively cluster tokens into fewer semantic tokens based on feature and dependency similarity and a light token reconstruction module to fuse ordinary and semantic tokens. In this way, as self-attention in ATM is calculated based on fewer tokens, DTMFormer is of lower complexity and more friendly to converge. Extensive experiments on publicly-available datasets demonstrate the effectiveness of DTMFormer working as a plug-n-play module for simultaneous complexity reduction and performance improvement. We believe it will inspire future work on rethinking transformers in medical image segmentation. Code: https://github.com/iam-nacl/DTMFormer.
- 1 October 2023
- Published by Springer Nature
- p. 642-651
ConvFormer: Plug-and-Play CNN-Style Transformers for Improving Medical Image Segmentation
- 1 October 2023
- Published by Springer Nature
- p. 642-651
ConvFormer: Plug-and-Play CNN-Style Transformers for Improving Medical Image Segmentation