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 Multi-modal Differential Diagnosis of Dementia with Synthetic Medical Image Generation
We aim for a trustworthy computer-aided diagnostic system for differential diagnosis of dementia, providing clinicians with reliable decision-making support. Given the challenges posed by limited availability of medical data, particularly for critical but invasive modalities like PET, we pursue generating such commonly missing modalities to support diagnosis.
Our preliminary advances include: 1) A self-supervised learning framework for dementia diagnosis using limited data (MIDL 2024) [1]; 2) A pathology-aware MRI-to-PET translation framework with diffusion models (MICCAI 2024) [2]; 3) Multi-modal vision transformers to integrate MRI and PET for dementia diagnosis (WACV 2025) [3]; 4) A pose-guided text-to-image generation framework (NeurIPS 2024) [4]. We are dedicated to continually advancing this field through ongoing research.
[1] doi.org/10.48550/arXiv.2404.06253
[2] doi.org/10.1007/978-3-031-72104-5_51
[3] doi.org/10.48550/arXiv.2410.23219
[4] doi.org/10.48550/arXiv.2406.02485