Make Your Summers Count
The Summer Undergraduate Research in Engineering (SURE) program provides summer research opportunities for U-M undergraduates; the Rackham Summer Research Opportunity Program (SROP) serves undergraduates from outside U-M.
Apply for a Summer Research Program
You are welcome to contact faculty if you have additional, specific questions regarding these projects. After your application is received (in late January), you will be contacted and asked to list your top three projects, in order of preference. You are also welcome to list these preferences on your application.
BME Guidelines:
Successful applicants will be selected by the projects’ listed faculty mentors. There is no requirement to contact the faculty mentor of your desired project(s) prior to being selected, but you may reach out to them with specific questions regarding the project if you desire. The number of positions awarded is dependent on SURE/SROP program allocations to the BME department (typically 6-8 each year).
Upcoming BME projects will be listed starting in November; the application period runs through late January.
Projects are added as they become available. Please check back for updated listings.
2026 BME Projects:
BME Project #1: In situ microbiome editing
Faculty Mentor: Jiahe Li, [email protected]
Prerequisites: extensive experience in microbiology, aseptic techniques, mammalian cell culture, flow cytometry, CRISPR genome editing and animal work
Project Description: We are engineering bacteria conjugation systems to deliver CRISPR cas9 into the microbiota in the mouse gut
Research Mode: 80% in-person wet lab and 20% paper writing
BME Project #2: Computational microscopy with machine learning
Faculty Mentor: Kevin C. Zhou, [email protected]
Prerequisites: proficiency with python; experience with pytorch/jax/tensorflow is plus
Project Description: A computational optical imaging system or microscope is one in which computation plays a significant role in the image formation process. Although computational imaging predates the recent explosion of interest in machine learning/AI, there are many opportunities for the application of such machine learning tools and techniques to enhance image reconstruction, where traditional techniques fall short. In particular, our lab is interested in developing high-throughput 4D computational imaging systems that can generate up to several terabytes of data in under a minute; however, traditional reconstruction algorithms are unable to scale to such high throughputs. To this end, in this project, you will help augment one of our image reconstruction algorithms with machine learning models to both enhance the image quality and reconstruction speed.
Research Mode: In-Person is encouraged
BME Project #3: Multimodal Foundation Model and AI Agent for Disease Diagnosis and Progression Prediction
Faculty Mentor: Dr. Yan-Ran (Joyce) Wang, [email protected]
Prerequisites: trong programming skills in Python; familiarity with machine learning and deep learning frameworks (e.g., PyTorch, TensorFlow); experience with biomedical data (imaging, clinical, or molecular) is a plus; prior exposure to large language models or generative AI is beneficial but not required.
Project Description: This project focuses on developing a multimodal foundation model and intelligent AI agent for disease diagnosis and progression prediction.
The foundation model will integrate diverse biomedical data modalities—such as imaging, clinical text, and molecular profiles—into a unified representation space using self-supervised and contrastive learning. Building on this, the AI agent will be designed to interact with clinical data and reasoning tasks, enabling automated interpretation, question answering, and disease trajectory prediction.
Students will:
- Work with large-scale multimodal biomedical datasets;
- Implement deep learning and multimodal fusion architectures;
- Develop an AI agent layer capable of clinical reasoning and retrieval-augmented responses;
- Evaluate performance on real-world diagnostic and prognostic tasks.
This project provides an excellent opportunity to gain experience in foundation model training, medical AI agent development, and translational biomedical applications.
Research Mode: Hybrid
BME Project #4: Synthetic Biomaterials to Direct Therapeutic Angiogenesis
Faculty Mentor: Brendon M. Baker, Ph.D., [email protected]
Prerequisites: general lab experience, lab notebooking, cell and tissue culture, familiarity with MATLAB
Project Description: Angiogenesis is a complex morphogenetic process that involves intimate interactions between migrating multicellular endothelial structures and their extracellular milieu. To investigate how microenvironmental cues regulate angiogenesis, we develop in vitro organotypic models that reduce the complexity of the native microenvironment and enable mechanistic insight into how soluble and physical extracellular matrix cues regulate this dynamic process. The focus of this project is to build a synthetic material that promotes angiogenesis without the need for exogenous soluble cues or growth factor gradients. This implantable biomaterial in the longer term will be applied to disease or injury settings to restore vascular function or for the creation of vascularized tissue grafts. Students involved in this project will gain expertise in biomaterials, microphysiologic modeling, and biological image analysis.
Research Mode: In-person, wet lab research.