Chengyu Wu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Chengyu Wu has a total of 50 co-authors. Here are the top co-authors by number of shared publications:
- Yaqi Wang
Innovation Center for Electronic Design Automation Technology, Hangzhou Dianzi University, Hangzhou, China
6 shared publications - Shuai Wang
Hangzhou Dianzi University
5 shared publications - Huiyu Zhou
University of Leicester, Leicester, United Kingdom
4 shared publications - Chengkai Wang
School of Management, Hangzhou Dianzi University, Hangzhou, China
3 shared publications - Qifeng Wang
Department of Radiation Oncology, Sichuan Clinical Research Center for Cancer, Sichuan Cancer Hospital & Institute, Sichuan Cancer Center, University of Electronic Science and Technology of China
3 shared publications - Yatao Zhang
Shandong University
3 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 11488-11497
Open-Linguistic Concept Unified Learning for Cross-Site Interpretable Dermatology Image Diagnosis
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 11488-11497
Open AccessOpen-Linguistic Concept Unified Learning for Cross-Site Interpretable Dermatology Image Diagnosis
- Open Access
- 20 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1275-1286
Medusa: Cross-Modal Transferable Adversarial Attacks on Multimodal Medical Retrieval-Augmented Generation
With the rapid advancement of retrieval-augmented vision-language models, multimodal medical retrieval-augmented generation (MMed-RAG) systems are increasingly adopted in clinical decision support. These systems enhance medical applications by performing cross-modal retrieval to integrate relevant visual and textual evidence for tasks, e.g., report generation and disease diagnosis. However, their complex architecture also introduces underexplored adversarial vulnerabilities, particularly via visual input perturbations. In this paper, we propose Medusa, a novel framework for crafting cross-modal transferable adversarial attacks on MMed-RAG systems under a black-box setting. Specifically, Medusa formulates the attack as a perturbation optimization problem, leveraging a multi-positive InfoNCE loss (MPIL) to align adversarial visual embeddings with medically plausible but malicious textual targets, thereby hijacking the retrieval process. To enhance transferability, we adopt a surrogate model ensemble and design a dual-loop optimization strategy augmented with invariant risk minimization (IRM). Extensive experiments on two real-world medical tasks, including medical report generation and disease diagnosis, demonstrate that Medusa achieves over 90% average attack success rate across various generation models and retrievers under appropriate parameter configuration, while remaining robust against four mainstream defenses, outperforming state-of-the-art baselines. Our results reveal critical vulnerabilities in the MMed-RAG systems and highlight the necessity of robustness benchmarking in safety-critical medical applications. The code and data are available at https://github.com/yiliucs/MMed-RAG-Attack.
- 20 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1275-1286
Open AccessMedusa: Cross-Modal Transferable Adversarial Attacks on Multimodal Medical Retrieval-Augmented Generation
With the rapid advancement of retrieval-augmented vision-language models, multimodal medical retrieval-augmented generation (MMed-RAG) systems are increasingly adopted in clinical decision support. These systems enhance medical applications by performing cross-modal retrieval to integrate relevant visual and textual evidence for tasks, e.g., report generation and disease diagnosis. However, their complex architecture also introduces underexplored adversarial vulnerabilities, particularly via visual input perturbations. In this paper, we propose Medusa, a novel framework for crafting cross-modal transferable adversarial attacks on MMed-RAG systems under a black-box setting. Specifically, Medusa formulates the attack as a perturbation optimization problem, leveraging a multi-positive InfoNCE loss (MPIL) to align adversarial visual embeddings with medically plausible but malicious textual targets, thereby hijacking the retrieval process. To enhance transferability, we adopt a surrogate model ensemble and design a dual-loop optimization strategy augmented with invariant risk minimization (IRM). Extensive experiments on two real-world medical tasks, including medical report generation and disease diagnosis, demonstrate that Medusa achieves over 90% average attack success rate across various generation models and retrievers under appropriate parameter configuration, while remaining robust against four mainstream defenses, outperforming state-of-the-art baselines. Our results reveal critical vulnerabilities in the MMed-RAG systems and highlight the necessity of robustness benchmarking in safety-critical medical applications. The code and data are available at https://github.com/yiliucs/MMed-RAG-Attack.
- Top Cited PapersOpen Access
- 9 February 2026
- Published by Elsevier in Medical Image Analysis
- Vol. 110, 103986
MICCAI STS 2024 challenge: Semi-supervised instance-level tooth segmentation in panoramic X-ray and CBCT images
- 9 February 2026
- Published by Elsevier in Medical Image Analysis
- Vol. 110, 103986
Top Cited PapersOpen AccessMICCAI STS 2024 challenge: Semi-supervised instance-level tooth segmentation in panoramic X-ray and CBCT images
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 7376-7385
SAMVSR: Leveraging Semantic Priors to Zone-Focused Mamba for Video Snow Removal
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 7376-7385
Open AccessSAMVSR: Leveraging Semantic Priors to Zone-Focused Mamba for Video Snow Removal
- 4 October 2024
- Published by Springer Nature
- p. 469-479
MMFusion: Multi-modality Diffusion Model for Lymph Node Metastasis Diagnosis in Esophageal Cancer
- 4 October 2024
- Published by Springer Nature
- p. 469-479
MMFusion: Multi-modality Diffusion Model for Lymph Node Metastasis Diagnosis in Esophageal Cancer
- 6 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 29 (5) , 3206-3219
A Novel Multi-Modal Population-Graph Based Framework for Patients of Esophageal Squamous Cell Cancer Prognostic Risk Prediction
Prognostic risk prediction is pivotal for clinicians to appraise the patient's esophageal squamous cell cancer (ESCC) progression status precisely and tailor individualized therapy treatment plans. Currently, CT-based multi-modal prognostic risk prediction methods have gradually attracted the attention of researchers for their universality, which is also able to be applied in scenarios of preoperative prognostic risk assessment in the early stages of cancer. However, much of the current work focuses only on CT images of the primary tumor, ignoring the important role that CT images of lymph nodes play in prognostic risk prediction. Additionally, it is important to consider and explore the inter-patient feature similarity in prognosis when developing models. To solve these problems, we proposed a novel multi-modal population-graph based framework leveraging CT images including primary tumor and lymph nodes combined with clinical, hematology, and radiomics data for ESCC prognostic risk prediction. A patient population graph was constructed to excavate the homogeneity and heterogeneity of inter-patient feature embedding. Moreover, a novel node-level multi-task joint loss was proposed for graph model optimization through a supervised-based task and an unsupervised-based task. Sufficient experimental results show that our model achieved state-of-the-art performance compared with other baseline models as well as the gold standard on discriminative ability, risk stratification, and clinical utility. The core code is available at https://github.com/wuchengyu123/MPGSurv .
- 6 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 29 (5) , 3206-3219
A Novel Multi-Modal Population-Graph Based Framework for Patients of Esophageal Squamous Cell Cancer Prognostic Risk Prediction
Prognostic risk prediction is pivotal for clinicians to appraise the patient's esophageal squamous cell cancer (ESCC) progression status precisely and tailor individualized therapy treatment plans. Currently, CT-based multi-modal prognostic risk prediction methods have gradually attracted the attention of researchers for their universality, which is also able to be applied in scenarios of preoperative prognostic risk assessment in the early stages of cancer. However, much of the current work focuses only on CT images of the primary tumor, ignoring the important role that CT images of lymph nodes play in prognostic risk prediction. Additionally, it is important to consider and explore the inter-patient feature similarity in prognosis when developing models. To solve these problems, we proposed a novel multi-modal population-graph based framework leveraging CT images including primary tumor and lymph nodes combined with clinical, hematology, and radiomics data for ESCC prognostic risk prediction. A patient population graph was constructed to excavate the homogeneity and heterogeneity of inter-patient feature embedding. Moreover, a novel node-level multi-task joint loss was proposed for graph model optimization through a supervised-based task and an unsupervised-based task. Sufficient experimental results show that our model achieved state-of-the-art performance compared with other baseline models as well as the gold standard on discriminative ability, risk stratification, and clinical utility. The core code is available at https://github.com/wuchengyu123/MPGSurv .
- Open Access
MMFusion: Multi-modality Diffusion Model for Lymph Node Metastasis Diagnosis in Esophageal Cancer
Esophageal cancer is one of the most common types of cancer worldwide and ranks sixth in cancer-related mortality. Accurate computer-assisted diagnosis of cancer progression can help physicians effectively customize personalized treatment plans. Currently, CT-based cancer diagnosis methods have received much attention for their comprehensive ability to examine patients' conditions. However, multi-modal based methods may likely introduce information redundancy, leading to underperformance. In addition, efficient and effective interactions between multi-modal representations need to be further explored, lacking insightful exploration of prognostic correlation in multi-modality features. In this work, we introduce a multi-modal heterogeneous graph-based conditional feature-guided diffusion model for lymph node metastasis diagnosis based on CT images as well as clinical measurements and radiomics data. To explore the intricate relationships between multi-modal features, we construct a heterogeneous graph. Following this, a conditional feature-guided diffusion approach is applied to eliminate information redundancy. Moreover, we propose a masked relational representation learning strategy, aiming to uncover the latent prognostic correlations and priorities of primary tumor and lymph node image representations. Various experimental results validate the effectiveness of our proposed method. The code is available at https://github.com/wuchengyu123/MMFusion.
Open AccessMMFusion: Multi-modality Diffusion Model for Lymph Node Metastasis Diagnosis in Esophageal Cancer
Esophageal cancer is one of the most common types of cancer worldwide and ranks sixth in cancer-related mortality. Accurate computer-assisted diagnosis of cancer progression can help physicians effectively customize personalized treatment plans. Currently, CT-based cancer diagnosis methods have received much attention for their comprehensive ability to examine patients' conditions. However, multi-modal based methods may likely introduce information redundancy, leading to underperformance. In addition, efficient and effective interactions between multi-modal representations need to be further explored, lacking insightful exploration of prognostic correlation in multi-modality features. In this work, we introduce a multi-modal heterogeneous graph-based conditional feature-guided diffusion model for lymph node metastasis diagnosis based on CT images as well as clinical measurements and radiomics data. To explore the intricate relationships between multi-modal features, we construct a heterogeneous graph. Following this, a conditional feature-guided diffusion approach is applied to eliminate information redundancy. Moreover, we propose a masked relational representation learning strategy, aiming to uncover the latent prognostic correlations and priorities of primary tumor and lymph node image representations. Various experimental results validate the effectiveness of our proposed method. The code is available at https://github.com/wuchengyu123/MMFusion.
- Open Access
- 11 March 2024
- Published by Elsevier in Artificial Intelligence in Medicine
- Vol. 150, 102837
PGKD-Net: Prior-guided and Knowledge Diffusive Network for Choroid Segmentation
- 11 March 2024
- Published by Elsevier in Artificial Intelligence in Medicine
- Vol. 150, 102837
Open AccessPGKD-Net: Prior-guided and Knowledge Diffusive Network for Choroid Segmentation
- Open Access
- 6 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 125346-125358
Multi-Task Dual Boundary Aware Network for Retinal Layer Segmentation
Layer segmentation of Optical Coherence Tomography (OCT) images is an important step in diagnosing retinal diseases. However, the presence of some artifacts and noise in OCT images often leads to unsatisfactory layer segmentation results. Especially when the number of layers to be segmented is particularly large, the boundaries between layers are indistinguishable, which poses a great challenge to automatic and accurate segmentation. To solve these problems, we propose a novel multi-task dual boundary-aware network to improve the retinal layer segmentation performance in OCT images. Specifically, based on the hierarchical relationship between retinal layers, we design a dual boundary representation method to encode the bidirectional boundary information between layers. Then we design a multi-task architecture and a novel consistency loss to utilize the boundary representation to make the segmentation more accurate. For evaluation, we have built a large-scale OCT layer segmentation dataset with 1,200 images. The comprehensive experimental results show that our method achieves superior performance over other state-of-the-art algorithms.
- 6 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 125346-125358
Open AccessMulti-Task Dual Boundary Aware Network for Retinal Layer Segmentation
Layer segmentation of Optical Coherence Tomography (OCT) images is an important step in diagnosing retinal diseases. However, the presence of some artifacts and noise in OCT images often leads to unsatisfactory layer segmentation results. Especially when the number of layers to be segmented is particularly large, the boundaries between layers are indistinguishable, which poses a great challenge to automatic and accurate segmentation. To solve these problems, we propose a novel multi-task dual boundary-aware network to improve the retinal layer segmentation performance in OCT images. Specifically, based on the hierarchical relationship between retinal layers, we design a dual boundary representation method to encode the bidirectional boundary information between layers. Then we design a multi-task architecture and a novel consistency loss to utilize the boundary representation to make the segmentation more accurate. For evaluation, we have built a large-scale OCT layer segmentation dataset with 1,200 images. The comprehensive experimental results show that our method achieves superior performance over other state-of-the-art algorithms.