Hong-Yu Zhou, Ph.D. 周洪宇 博士

1. Foundation Models for Medical Imaging 1. 医学影像基础模型

We are developing large-scale foundation models that can understand diverse medical imaging modalities and clinical contexts. Our recent work on Swin-UMamba demonstrates state-of-the-art performance in medical image segmentation tasks. 我们正在开发能够理解多种医学成像模态和临床场景的大规模基础模型。 我们最近的Swin-UMamba工作在医学图像分割任务中展现了最先进的性能。

2. Multimodal Clinical Intelligence 2. 多模态临床智能

Building unified transformer architectures that can process and reason over multiple types of clinical data simultaneously, including radiographs, lab results, and clinical notes. Our IRENE model published in Nature Biomedical Engineering represents a breakthrough in this direction. 构建统一的transformer架构，能够同时处理和推理多种类型的临床数据， 包括X光片、实验室结果和临床记录。我们在Nature Biomedical Engineering发表的IRENE模型代表了这个方向的突破。

3. Self-Supervised Medical Representation Learning 3. 自监督医学表示学习

Developing novel self-supervised and cross-supervised learning methods that can leverage the vast amounts of unlabeled medical data to improve model performance and generalization. 开发新型自监督和交叉监督学习方法，能够利用大量无标签医学数据来提高模型性能和泛化能力。

BME 501: Deep Learning for Medical Image Analysis BME 501：医学图像分析的深度学习

Fall 2024 - Graduate level course covering fundamental and advanced topics in medical image analysis using deep learning. 2024秋季 - 研究生课程，涵盖使用深度学习进行医学图像分析的基础和高级主题。

• Convolutional Neural Networks for Medical Imaging 医学影像的卷积神经网络
• Transformer Architectures in Healthcare 医疗保健中的Transformer架构
• Self-supervised Learning Methods 自监督学习方法
• Clinical Applications and Case Studies 临床应用与案例研究

BME 302: Introduction to Medical AI BME 302：医学人工智能导论

Spring 2025 - Undergraduate course introducing AI applications in medicine and healthcare. 2025春季 - 本科生课程，介绍人工智能在医学和医疗保健中的应用。

Requirements: 要求：

• Strong background in computer science, electrical engineering, biomedical engineering, or related fields 计算机科学、电子工程、生物医学工程或相关领域的扎实背景
• Experience with machine learning and deep learning frameworks 机器学习和深度学习框架的使用经验
• Programming proficiency in Python, PyTorch/TensorFlow 熟练掌握Python、PyTorch/TensorFlow编程
• Excellent communication skills in English 优秀的英语沟通能力
• Passion for medical AI research 对医学AI研究充满热情

Application: Please send your CV, transcripts, and a brief research statement to hongyu_zhou@tsinghua.edu.cn 申请：请将您的简历、成绩单和简短的研究陈述发送至 hongyu_zhou@tsinghua.edu.cn

Opportunities: 机会：

• Thesis projects on medical image analysis 医学图像分析的论文项目
• Clinical AI system development 临床AI系统开发
• Collaboration with leading hospitals 与顶级医院合作

Note: Priority given to Tsinghua students, but exceptional external candidates are welcome to apply. 注意：优先考虑清华学生，但欢迎优秀的外部候选人申请。

Research Assistant Positions: 研究助理职位：

• Summer research internships 暑期研究实习
• Senior thesis projects 毕业论文项目
• Part-time research during academic year 学年期间的兼职研究

We welcome motivated undergraduates who want to gain research experience in medical AI. 我们欢迎希望获得医学AI研究经验的积极主动的本科生。

We seek postdocs with: 我们寻找具备以下条件的博士后：

• Ph.D. in relevant fields 相关领域的博士学位
• Strong publication record 优秀的发表记录
• Independent research capabilities 独立研究能力
• Interest in medical AI applications 对医学AI应用感兴趣

Benefits: Competitive salary, research funding support, and opportunities for career development. 待遇：有竞争力的薪资、研究资金支持和职业发展机会。