Publications
论文成果
按发表状态展示 MARS 相关论文、作者列表、会议期刊信息和神经网络架构图。
Publications
学术成果
19篇
已整理的代表性论文与在研稿件
Published
覆盖医学影像分析、病理图像、眼底影像与多模态建模
Preprint
持续更新预印本、开源代码、数据集与引用信息
Figures
每篇论文配套展示核心网络结构图
Published
Published Papers
LASAGNA-U-NET: Revisiting U-Shape Architecture for Histopathology Image Segmentation
MUSCLE: A New Perspective to Multi-scale Fusion for Medical Image Classification based on the Theory of Evidence
GAD: Domain generalized diabetic retinopathy grading by grade-aware de-stylization
Cross-Modal Vertical Federated Learning for MRI Reconstruction
Multi-Constraint Transferable Generative Adversarial Networks for Cross-Modal Brain Image Synthesis
Triplet-branch network with contrastive prior-knowledge embedding for disease grading
Unsupervised Domain Adaptation for Medical Image Segmentation by Disentanglement Learning and Self-Training
Anomaly detection via gating highway connection for retinal fundus images
Dynamically Masked Discriminator for Generative Adversarial Networks
Improving vision transformer for medical image classification via token-wise perturbation
MIL-ViT: A multiple instance vision transformer for fundus image classification
Preprints & Under Review 8 Papers
Towards cross-center head and neck cancer detection: a multi-level domain alignment exploration
Adaptive Wavelet Enhancement and Stratified Feature Fusion for Robust Medical Image Segmentation
Dual-Domain Wavelet State-Space Network for Medical Image Segmentation
SG-CMTA: Self-Guided Pathology Enhancement for Multimodal Cancer Survival Prediction
Det-Y: A Multi-center Dataset and Benchmark for Efficient Detection of Mycobacterium Tuberculosis in Sputum Smears
HEDS-Net: A Hybrid State-Space Architecture with Axial Bridge and Progressive Weighting for Medical Image Segmentation
A Hybrid Framework Bridging CNN and ViT based on Theory of Evidence for Diabetic Retinopathy Grading
Radiotherapy Planning of Nasopharyngeal Carcinoma using Deep-Learning-Based Across-Feature-Map-Attention Mechanism
* Corresponding author. Citation counts use exact Crossref matches where available; under-review papers are shown without speculative counts.