About

Mark Anastasio is the Donald Biggar Willett Professor in Engineering and serves as the Head of the Department of Bioengineering at the University of Illinois Urbana-Champaign. His research interests encompass computational imaging science, image reconstruction, machine learning, and inverse problems. His work focuses on advancing imaging technologies and methodologies, particularly in the context of medical imaging, through the development of innovative computational techniques and algorithms. Anastasio has contributed to the fields of scientific computing and artificial intelligence, with a notable emphasis on improving imaging system performance and image analysis.

Research topics

• Computer Science
• Artificial Intelligence
• Biology
• Cell biology
• Machine Learning
• Biochemistry
• Optics
• Materials science
• Genetics
• Pathology
• Physics
• Medicine
• Computer vision
• Chemistry
• Mathematics
• Statistics

Selected publications

• Artificial confocal microscopy for deep label-free imaging

  Nature Photonics · 2023 · 62 citations

  • Artificial Intelligence
  • Computer Science
  • Optics
  PublisherOA PDFDOI

• Assessing the Ability of Generative Adversarial Networks to Learn Canonical Medical Image Statistics

  IEEE Transactions on Medical Imaging · 2023 · 35 citations

  Senior authorCorresponding
  • Computer Science
  • Artificial Intelligence
  • Computer Science

  In recent years, generative adversarial networks (GANs) have gained tremendous popularity for potential applications in medical imaging, such as medical image synthesis, restoration, reconstruction, translation, as well as objective image quality assessment. Despite the impressive progress in generating high-resolution, perceptually realistic images, it is not clear if modern GANs reliably learn the statistics that are meaningful to a downstream medical imaging application. In this work, the ability of a state-of-the-art GAN to learn the statistics of canonical stochastic image models (SIMs) that are relevant to objective assessment of image quality is investigated. It is shown that although the employed GAN successfully learned several basic first- and second-order statistics of the specific medical SIMs under consideration and generated images with high perceptual quality, it failed to correctly learn several per-image statistics pertinent to the these SIMs, highlighting the urgent need to assess medical image GANs in terms of objective measures of image quality.

  PublisherOA PDFDOI

• Live-dead assay on unlabeled cells using phase imaging with computational specificity

  Nature Communications · 2022 · 103 citations

  • Computer Science
  • Computer Science
  • Cell biology

  Existing approaches to evaluate cell viability involve cell staining with chemical reagents. However, the step of exogenous staining makes these methods undesirable for rapid, nondestructive, and long-term investigation. Here, we present an instantaneous viability assessment of unlabeled cells using phase imaging with computation specificity. This concept utilizes deep learning techniques to compute viability markers associated with the specimen measured by label-free quantitative phase imaging. Demonstrated on different live cell cultures, the proposed method reports approximately 95% accuracy in identifying live and dead cells. The evolution of the cell dry mass and nucleus area for the labeled and unlabeled populations reveal that the chemical reagents decrease viability. The nondestructive approach presented here may find a broad range of applications, from monitoring the production of biopharmaceuticals to assessing the effectiveness of cancer treatments.

  DOI

• High-resolution transcriptional and morphogenetic profiling of cells from micropatterned human ESC gastruloid cultures

  eLife · 2020 · 117 citations

  • Biology
  • Cell biology
  • Genetics

  During mammalian gastrulation, germ layers arise and are shaped into the body plan while extraembryonic layers sustain the embryo. Human embryonic stem cells, cultured with BMP4 on extracellular matrix micro-discs, reproducibly differentiate into gastruloids, expressing markers of germ layers and extraembryonic cells in radial arrangement. Using single-cell RNA sequencing and cross-species comparisons with mouse, cynomolgus monkey gastrulae, and post-implantation human embryos, we reveal that gastruloids contain cells transcriptionally similar to epiblast, ectoderm, mesoderm, endoderm, primordial germ cells, trophectoderm, and amnion. Upon gastruloid dissociation, single cells reseeded onto micro-discs were motile and aggregated with the same but segregated from distinct cell types. Ectodermal cells segregated from endodermal and extraembryonic but mixed with mesodermal cells. Our work demonstrates that the gastruloid system models primate-specific features of embryogenesis, and that gastruloid cells exhibit evolutionarily conserved sorting behaviors. This work generates a resource for transcriptomes of human extraembryonic and embryonic germ layers differentiated in a stereotyped arrangement.

  DOI

Recent grants

• Novel X-ray Imaging of Carotid Plaque Microstructure

  NSF · $302k · 2009–2011

• OP: Collaborative Research: Development of Advanced Image Reconstruction Methods for Pre-Clinical Applications of Photoacoustic Computed Tomography

  NSF · $108k · 2019–2020

• SPARSITY-DRIVEN IDEAL OBSERVERS FOR GUIDING IMAGING HARDWARE OPTIMIZATION

  NIH · $404k · 2015–2018

• Development of Thermoacoustic Tomography Brain Imaging

  NIH · $1.6M · 2010–2014

• Design Studies and Optimization of Phase-Contrast Mammography

  NIH · $1.6M · 2010–2015

Frequent coauthors

• H Li

  92 shared

• Sasa Mutic

  Varian Medical Systems (United States)

  82 shared

• S Dolly

  SSM Health Care

  81 shared

• Umberto Villa

  The University of Texas at Austin

  66 shared

• Su Ruan

  64 shared

• H Chen

  Washington University in St. Louis

  62 shared

• Hua Li

  Washington University in St. Louis

  59 shared

• Hiram A. Gay

  Washington University in St. Louis

  59 shared

Labs

• Anastasio LabPI

Education

• Ph.D., Computer Science

  University of Illinois at Urbana-Champaign

  2000

• M.S., Computer Science

  University of Illinois at Urbana-Champaign

  1996

• B.S., Computer Science

  University of Illinois at Urbana-Champaign

  1994

Awards & honors

• Donald Biggar Willett Professor in Engineering
• Celebration of Excellence 2026
• Celebration of Excellence 2025
• Celebration of Excellence 2024
• Celebration of Excellence 2023

Similar researchers at University of Illinois Urbana-Champaign

• Jiawei Hanh-146
• Maria T. Grosse Perdekamph-141
• Gan Zhangh-134
• Jeffrey S. Mooreh-130
• Shuming Nieh-128