AI for Medical Imaging · Medical Visual Question Answering · Radiology Report Generation · Trustworthy Multimodal Medical Intelligence
I am Lijun Liu (@cloneiq), working on medical artificial intelligence, with a focus on medical imaging, multimodal learning, medical visual question answering, radiology report generation, and trustworthy clinical reasoning. My GitHub is organized as a research-oriented project hub for reproducible medical AI, including model implementations, academic resource repositories, and medical image analysis projects.
|
Medical Visual Question Answering Med-VQA, knowledge-enhanced reasoning, causal debiasing, evidence grounding, and active inquiry. |
Radiology Report Generation Chest X-ray report generation, causal evidence coupling, semantic consistency, and clinical evaluation. |
Medical Image Analysis Polyp segmentation, lesion-aware modeling, boundary enhancement, and diagnosis-oriented image understanding. |
| Project | Focus |
|---|---|
| ARISE-MedVQA | A curated academic resource hub for Medical Visual Question Answering, covering surveys, datasets, metrics, methods, MLLMs, medical agents, and code resources. |
| CIMB-MVQA | Causal intervention on modality-specific biases for Medical Visual Question Answering. |
| CKRA-MedVQA | Dynamic context-aware cross-modal contrastive learning for Medical Visual Question Answering. |
| DE-CaGI | Causal gradient intervention for debiased and evidence-grounded Medical Visual Question Answering. |
| C3E-RRG | Confounder-aware causal evidence coupling and evolution for chest X-ray report generation. |
The following pinned repositories highlight representative work by our team in medical VQA, radiology report generation, and medical image analysis.