Xueding Wang

By |

My research focuses on novel biomedical imaging and treatment technologies, especially those involving light and ultrasound. I have extensive experience in medical system development, laser-tissue interactions, ultrasound tissue characterization, and adaptation of novel technologies to preclinical and clinical settings. A major part of my research is the development and clinical applications of photoacoustic imaging technology. By working on small-animal models and human patients, I have been seeking for clinical applications of this exciting technology to inflammatory arthritis, cancer, inflammatory bowel disease, eye diseases, osteoporosis, and brain disorders. Besides photoacoustic imaging, I am also interested in development of other medical imaging and treatment technologies, such as ionizing radiation induced acoustic imaging (iRAI) and photo-mediated ultrasound therapy (PUT). As the PI or co-Investigator of several NIH, NSF and DoD-funded research, I have successfully administered the projects, collaborated with other researchers, and produced high-quality publications. My contribution to biomedical optics and ultrasound up to now including over 160 peer-reviewed journal papers is a solid evidence of my creativity and ability to surmount the challenges in this field. I received the Sontag Foundation Fellow of the Arthritis National Research Foundation in 2005, the Distinguished Investigator Award of the Academy of Radiology Research in 2013, and was elected as the fellow of AIMBE in 2020 and the fellow of SPIE in 2022.

What is your most interesting project?

Automated photoacoustic imaging of inflammatory arthritis: Our research has demonstrated the unique capability of photoacoustic imaging (PAI) in diagnosis and treatment monitoring of inflammatory arthritis. The new physiological and molecular biomarkers of synovitis presented by PAI can help in characterizing disease onset, progression, and response to therapy. Based on the endogenous optical contrast, PAI is extremely sensitive to the changes in hemodynamic properties in inflammatory joint tissues (e.g. enhanced flow and hypoxia). We are now conducting a preclinical research on patients affected by rheumatoid arthritis. The initial findings from this patient study are promising and suggest that the new optical contrast and physiological information introduced by PAI could greatly enhance the sensitivity and accuracy of diagnostic imaging and treatment monitoring of arthritis. Aiming at clinical translation, we are currently developing a point-of-care PAI and ultrasound dual-modality imaging system which is fully automated when powered by a robot and AI technologies.

Ionizing radiation acoustic imaging (iRAI) for personalized radiation therapy: iRAI, as a brand-new imaging technology relying on the detection of radiation-induced acoustic waves, allows online monitoring of radiation’s interactions with tissues during radiation therapy, providing real-time, adaptive feedback for cancer treatments. We are developing an iRAI volumetric imaging system that enables mapping of the three-dimensional (3D) radiation dose distribution in a complex clinical radiotherapy treatment. The feasibility of imaging temporal 3D dose accumulation was first validated in studies on phantoms and animal models. Then, real-time visualization of the 3D radiation dose delivered to a patient with liver metastases was accomplished with a clinical linear accelerator. These studies demonstrate the great potential of iRAI to monitor and quantify the 3D radiation dose deposition during treatment, potentially improving radiotherapy treatment efficacy using real-time adaptive treatment.

Describe your research journey.

2005 – 2007 Research Investigator, Department of Radiology, University of Michigan
2007 – 2008 Research Assistant Professor, Department of Radiology, University of Michigan
2008 – 2012 Assistant Professor, Department of Radiology, University of Michigan Medical School
2012 – 2014 Associate Professor, Department of Radiology, University of Michigan
2015 – 2018 Associate Professor, Department of Biomedical Engineering, University of Michigan
2018 – 2022 Professor, Department of Biomedical Engineering, University of Michigan
2022 – Now Jonathan Rubin Collegiate Professor of Biomedical Engineering, University of Michigan

What is the most significant scientific contribution you would like to make?

Develop and translate state-of-the-art medical imaging and treatment technologies.

What makes you excited about your data science and AI research?

Date science and AI is super important in developing state-of-the-art medical imaging and treatment technologies, especially for achieving personalized diagnosis and treatment ensuring largely improved patient outcome. As mentioned in the above, the automated imaging system for rheumatology/radiology clinic for arthritis imaging would be strongly powered by AI, which is crucial to achieve our goal of a “smart” ultrasound imaging platform.

Automated dual-modality ultrasound and photoacoustic imaging system

Automated dual-modality ultrasound and photoacoustic imaging system

Maggie Makar

By |

My research focuses on developing reliable and efficient machine learning methods for causal inference as well as predictive models that leverage causal reasoning. My work typically involves applications to healthcare.

Alexander RodrĂ­guez

By |

Alex’s research interests include machine learning, time series, multi-agent systems, uncertainty quantification, and scientific modeling. His recent focus is on developing trustworthy AI systems that can offer insightful guidance for critical decisions, especially in applications involving complex spatiotemporal dynamics. His work is primarily motivated by real-world problems in public health, environmental health and community resilience.

Mark Draelos

Mark Draelos

By |

My work focuses on image-guided medical robots with an emphasis on clinical translation. My interests include medical robotics, biomedical imaging, data visualization, medical device development, and real-time algorithms.

A major ongoing project is the development of robotic system for automated eye examination. This system relies on machine learning models for tracking and eventually for interpretation of collected data. Other projects concern the live creation of virtual reality scenes from volumetric imaging modalities like optical coherence tomography and efficient acquisition strategies for such purposes.

Venkat Viswanathan

Venkat Viswanathan

By |

Research on computational modeling of energy materials design and optimization

1) I led this large research project on developing machine-learning guided materials discovery demonstrating speed-up of over 80% over traditional methods.

2) My research group runs a popular Scientific Machine Learning webinar series: https://micde.umich.edu/news-events/sciml-webinar-series/

Rebecca Lindsey

By |

Research in the Lindsey Lab focuses on using simulation to enable on-demand design, discovery, and synthesis of bespoke materials.

These efforts are made possible by Dr. Lindsey’s ChIMES framework, which comprises a unique physics-informed machine-learned (ML) interatomic potential (IAP) and artificial intelligence-automated development tool that enables “quantum accurate” simulation of complex systems on scales overlapping with experiment, with atomistic resolution. Using this tool, her group elucidates fundamental materials behavior and properties that can be manipulated through advanced material synthesis and modification techniques. At the same time, her group develops new approaches to overcome grand challenges in machine learning for physical sciences and engineering, including: training set generation, model uncertainty quantification, reproducibility and automation, robustness, and accessibility to the broader scientific community. Her also group seeks to understand what the models themselves can teach us about fundamental physics and chemistry.

Artists interpretation of a new laser-driven shockwave approach for nanocarbon synthesis predicted by ChIMES simulations and later validated experimentally.

Qiong Yang

Qiong Yang

By |

My research program at the University of Michigan (UM) integrates the fields of biophysics, quantitative systems biology, and bottom-up synthetic biology to understand complex stochastic cellular and developmental processes in early embryos.
We have developed innovative computational and experimental techniques in microfluidics and imaging to allow high-throughput quantitative manipulation and single-cell lineage tracking of cellular spatiotemporal dynamical processes in various powerful in vitro and in vivo systems we established in my lab. These systems range from cell-free extracts, synthetic cells reconstituted in microemulsion droplets, presomitic mesoderm (PSM) and progenitor zone (PZ) cells dissociated from the zebrafish tail buds, their re-aggregated 2D and 3D cell-cell communications, ex vivo live tissue explants, and live embryos.
Our current research questions center around the understanding of the design-function relation of robust biological timing, growth, and patterning, how individual molecules and cells communicate to generate collective patterns, and how biochemical, biophysical, and biomechanical signals work together to shape morphogenesis during early embryo development.

Saif Benjaafar

Saif Benjaafar

By |

I used the tools of operations research (optimization, stochastic modeling, and game theory), machine learning, and statistics to study problems in operations management broadly defined, including supply chains, service systems, transportation and mobility, and markets. My current research focus is on sustainable operations and innovative business models, including sharing economy, on-demand services, and online marketplaces.

Changxiao Cai

Changxiao Cai

By |

Changxiao Cai’s research interests lie broadly in the intersection of statistics, optimization, and machine learning. He is interested in developing provably scalable methods for information extraction from high-dimensional data, with an aim to achieve the optimal interplay between statistical accuracy and computational efficiency.

jjpark

Jeong Joon Park

By |

3D reconstruction and generative models. I use neural and physical 3D representations to generate realistic 3D objects and scenes. The current focus is large-scale, dynamic, and interactable 3D scene generations. These generative models will be greatly useful for content creators, like games or movies, or for autonomous agent training in virtual environments. For my research, I frequently use and adopt generative modeling techniques such as auto-decoders, GANs, or Diffusion Models.

In my project “DeepSDF,” I suggested a new representation for a 3D generative model that made a breakthrough in the field. The question I answered is: “what should the 3D model be generating? Points, meshes, or voxels?” In DeepSDF paper, I proposed that we should generate a “function,” that takes input as a 3D coordinate and outputs a field value corresponding to that coordinate, where the “function” is represented as a neural network. This neural coordinate-based representation is memory-efficient, differentiable, and expressive, and is at the core of huge progress our community has made for 3D generative modeling and reconstruction.

3D faces with apperance and geometry generated by our AI model

Two contributions I would like to make. First, I would like to enable AI generation of large-scale, dynamic, and interactable 3D world, which will benefit entertainment, autonomous agent training (robotics and self-driving) and various other scientific fields such as 3D medical imaging. Second, I would like to devise a new and more efficient neural network architecture that mimics our brains better. The current AI models are highly inefficient in terms of how they learn from data (requires a huge number of labels), difficult to train continuously and with verbal/visual instructions. I would like to develop a new architecture and learning methods that address these current limitations.