Lubomir Hadjiyski

By |

Dr. Hadjiyski research interests include computer-aided diagnosis, artificial intelligence (AI), machine learning, predictive models, image processing and analysis, medical imaging, and control systems. His current research involves design of decision support systems for detection and diagnosis of cancer in different organs and quantitative analysis of integrated multimodality radiomics, histopathology and molecular biomarkers for treatment response monitoring using AI and machine learning techniques. He also studies the effect of the decision support systems on the physicians’ clinical performance.

Thomas L. Chenevert

By |

Multi-center clinical trials increasingly utilize quantitative diffusion imaging (DWI) to aid in patient management and treatment response assessment for translational oncology applications. A major source of systematic bias in diffusion was discovered originating from platform-dependent gradient hardware. Left uncorrected, these biases confound quantitative diffusion metrics used for characterization of tissue pathology and treatment response leading to inconclusive findings, and increasing the requisite subject numbers and trial cost. We have developed technology to mitigate systematic diffusion mapping bias that exists on MRI scanners and are in process of deploying this technology for multi-center clinical trials. Another major source of variance and bottleneck in high-throughput analysis of quantitative diffusion maps is segmentation of tumor/tissue volume of interest (VOI) based on intensities and patterns on multi-contrast MR image datasets, as well as reliable assessment of longitudinal change with disease progression or response to treatment. Our goal is development/trial/application AI algorithms for robust (semi-) automated VOI definition in analysis of multi-dimensional MR datasets for oncology trials.

Representative apparent diffusion coefficient (ADC) histograms and map overlays are shown for oncology trials to be supported by this Academic Industrial Partnership (AIP). ADC is used to characterize tumor malignancy of breast cancer, therapeutic effect in head and neck (H&N) and cellular proliferation in bone marrow of myelofibrosis (MF) patients. Relevant clinical outcome metrics are illustrated under histograms for detection sensitivity threshold (to reduce unnecessary breast biopsies (13)), Kaplan-Meier analysis of therapy response (stratified by median SD of H&N metastatic node (23)), and histopathologic proliferation stage (MF cellular infiltration classification).

Amie Gordon

By |

My research focuses on understanding the social cognitive, affective, and biological factors that shape our closest relationships. I am particularly interested in identifying factors that help romantic couples and families maintain high quality relationships. My work draws upon a variety of methods, including experimental, observational, naturalistic (e.g., daily experience), and physiological, to capture people at multiple levels in a variety of social situations. I frequently gather dyadic longitudinal data in order to understand how relationship partners influence each other in the moment and over time.

Elle O’Brien

By |

My research focuses on building infrastructure for public health and health science research organizations to take advantage of cloud computing, strong software engineering practices, and MLOps (machine learning operations). By equipping biomedical research groups with tools that facilitate automation, better documentation, and portable code, we can improve the reproducibility and rigor of science while scaling up the kind of data collection and analysis possible.

Research topics include:
1. Open source software and cloud infrastructure for research,
2. Software development practices and conventions that work for academic units, like labs or research centers, and
3. The organizational factors that encourage best practices in reproducibility, data management, and transparency

The practice of science is a tug of war between competing incentives: the drive to do a lot fast, and the need to generate reproducible work. As data grows in size, code increases in complexity and the number of collaborators and institutions involved goes up, it becomes harder to preserve all the “artifacts” needed to understand and recreate your own work. Technical AND cultural solutions will be needed to keep data-centric research rigorous, shareable, and transparent to the broader scientific community.

View MIDAS Faculty Research Pitch, Fall 2021


Felipe da Veiga Lerprevost

By |

My research concentrates on the area of bioinformatics, proteomics, and data integration. I am particularly interested in mass spectrometry-based proteomics, software development for proteomics, cancer proteogenomics, and transcriptomics. The computational methods and tools previously developed by my colleagues and me, such as PepExplorer, MSFragger, Philosopher, and PatternLab for Proteomics, are among the most referred proteome informatics tools and are used by hundreds of laboratories worldwide.

I am also a Proteogenomics Data Analysis Center (UM-PGDAC) member as part of the NCI’s Clinical Proteomic Tumor Analysis Consortium (CPTAC) initiative for processing and analyzing hundreds of cancer proteomics samples. UM-PGDAC develops advanced computational infrastructure for comprehensive and global characterization of genomics, transcriptomics, and proteomics data collected from several human tumor cohorts using NCI-provided biospecimens. Since 2019 I have been working as a bioinformatics data analyst with the University of Michigan Proteomics Resource Facility, which provides state-of-the-art capabilities in proteomics to the University of Michigan investigators, including Rogel Cancer Center investigators as Proteomics Shared Resource.

Omar Jamil Ahmed

By |

The Ahmed lab studies behavioral neural circuits and attempts to repair them when they go awry in neurological disorders. Working with patients and with transgenic rodent models, we focus on how space, time and speed are encoded by the spatial navigation and memory circuits of the brain. We also focus on how these same circuits go wrong in Alzheimer’s disease, Parkinson’s disease and epilepsy. Our research involves the collection of massive volumes of neural data. Within these terabytes of data, we work to identify and understand irregular activity patterns at the sub-millisecond level. This requires us to leverage high performance computing environments, and to design custom algorithmic and analytical signal processing solutions. As part of our research, we also discover new ways for the brain to encode information (how neurons encode sequences of space and time, for example) – and the algorithms utilized by these natural neural networks can have important implications for the design of more effective artificial neural networks.

Mark Steven Cohen

By |

In his various roles, he has helped develop several educational programs in Innovation and Entrepreneurial Development (the only one of their kind in the world) for medical students, residents, and faculty as well as co-founding 4 start-up companies (including a consulting group, a pharmaceutical company, a device company, and a digital health startup) to improve the care of surgical patients and patients with cancer. He has given over 80 invited talks both nationally and internationally, written and published over 110 original scientific articles, 12 book chapters, as well as a textbook on “Success in Academic Surgery: Innovation and Entrepreneurship” published in 2019 by Springer-NATURE. His research is focused on drug development and nanoparticle drug delivery for cancer therapeutic development as well as evaluation of circulating tumor cells, tissue engineering for development of thyroid organoids, and evaluating the role of mixed reality technologies, AI and ML in surgical simulation, education and clinical care delivery as well as directing the Center for Surgical Innovation at Michigan. He has been externally funded for 13 consecutive years by donors and grants from Susan G. Komen Foundation, the American Cancer Society, and he currently has funding from three National Institute of Health R-01 grants through the National Cancer Institute. He has served on several grant study sections for the National Science Foundation, the National Institute of Health, the Department of Defense, and the Susan G. Komen Foundation. He also serves of several scientific journal editorial boards and has serves on committees and leadership roles in the Association for Academic Surgery, the Society of University Surgeons and the American Association of Endocrine Surgeons where he was the National Program Chair in 2013. For his innovation efforts, he was awarded a Distinguished Faculty Recognition Award by the University of Michigan in 2019. His clinical interests and national expertise are in the areas of Endocrine Surgery: specifically thyroid surgery for benign and malignant disease, minimally invasive thyroid and parathyroid surgery, and adrenal surgery, as well as advanced Melanoma Surgery including developing and running the hyperthermic isolated limb perfusion program for in transit metastatic melanoma (the only one in the state of Michigan) which is now one of the largest in the nation.

Kevin Bakker

By |

Kevin’s research is focused on to identifying and interpreting the mechanisms responsible for the complex dynamics we observe in ecological and epidemiological systems using data science and modeling approaches. He is primarily interested in emerging and endemic pathogens, such as SARS-CoV-2, influenza, vampire bat rabies, and a host of childhood infectious diseases such as chickenpox. He uses statistical and mechanistic models to fit, forecast, and occasionally back-cast expected disease dynamics under a host of conditions, such as vaccination or other control mechanisms.

Andrew Brouwer

By |

Andrew uses mathematical and statistical modeling to address public health problems. As a mathematical epidemiologist, he works on a wide range of topics (mostly related to infectious diseases and cancer prevention and survival) using an array of computational and statistical tools, including mechanistic differential equations and multistate stochastic processes. Rigorous consideration of parameter identifiability, parameter estimation, and uncertainty quantification are underlying themes in Andrew’s work.

Rajiv Saran

By |

Dr. Saran is an internationally recognized expert in kidney disease research – specifically, in the area of kidney disease surveillance and epidemiology. From 2014 – 2019, he served as Director of the United States Renal Data System (USRDS;, a ‘gold standard’ for kidney disease data systems, worldwide. Since 2006 he has been Co-Principal Investigator for the Centers for the Disease Control and Prevention’s (CDC’s) National CKD Surveillance System for the US, a one of a kind project that complements the USRDS, while focusing on upstream surveillance of CKD and its risk factors ( Both projects have influenced policy related to kidney disease in the US and were cited extensively in the July 2019 Advancing American Kidney Health Federal policy document. Dr. Saran led the development of the first National Kidney Disease Information System (VA-REINS), for the Department of Veterans Affairs (VA), funded by the VA’s Center for Innovation, and one that led to the VA recognizing the importance of kidney disease as a health priority for US veterans. Dr. Saran has recently (2018-2021) been funded on a spin off project from VA REINS for investigation of ‘hot-spot’ of kidney disease among US Veterans involving both risk-prediction and geospatial analyses – a modern approach to health system big data being used for prevention and population health improvement, using kidney disease as an example. This approach has broad application for prevention and optimizing management of major chronic diseases.