PhD
Laboratory for Artificial Intelligence in Medical Imaging at TUM
Institut für Radiologie
Klinikum rechts der Isar
Ismaninger Str. 22
81675 Munich, Germany
Biosketch
Yitong is a PhD student in the Lab for AI in Medical Imaging at the Technical University of Munich (TUM) under the supervision of Prof. Christian Wachinger. Previously, she obtained her Master’s degree in Biomedical Computing at TUM and her Bachelor’s degree in Robot Engineering at Southeast University in China. Her research focuses on developing novel machine learning algorithms for medical image analysis, encompassing areas of generative AI, self-supervised learning, and multi-modal learning.
relAI Research
Trustworthy Multimodal Medical Image Analysis with Synthetic Image Generation
Our research focuses on developing reliable AI methods for clinical applications, with particular emphasis on controllable generative modeling with diffusion models and multi-modal learning.
Our preliminary advances include: 1) Conditional diffusion models for cross-modality translation on 3D medical imaging (MICCAI 2024, IPMI 2025, MedIA 2026); 2) Multi-modal learning in modality fusion and vision-language models (WACV 2025); 3) Pose-guided text-to-image generation with controllable diffusion models (NeurIPS 2024). We are dedicated to continually advancing this field through ongoing research.
Publications
[1] Diffusion Bridge Networks Simulate Clinical-grade PET from MRI for Dementia Diagnostics (doi.org/10.48550/arXiv.2510.15556)
[2] PASTA: Pathology-Aware MRI to PET Cross-modal Translation with Diffusion Models (doi.org/10.1007/978-3-031-72104-5_51)
[3] Translating MRI to PET through conditional diffusion models with enhanced pathology awareness (doi.org/10.1016/j.media.2026.104035)
[4] 3D Shape-to-Image Brownian Bridge Diffusion for Brain MRI Synthesis from Cortical Surfaces (doi.org/10.1007/978-3-031-96628-6_13)
[5] DiaMond: Dementia Diagnosis with Multi-Modal Vision Transformers Using MRI and PET (doi.org/10.48550/arXiv.2410.23219)
[6] Stable-Pose: Leveraging Transformers for Pose-Guided Text-to-Image Generation (doi.org/10.48550/arXiv.2406.02485)