Research in Visual Informatics and Data Analytics (VIDA)

Synopsis of the Research Area

The Visual Informatics and Data Analytics (VIDA) Group at DePaul University focuses on creating machine learning and computer vision algorithms as well as developing systems for data processing, analysis, modeling, and visualization. Two laboratories, the Medical Informatics (MedIX) lab and the Intelligent Multimedia Processing (IMP) lab, house state-of-the-art research that combines theory and experimental methodologies to provide novel solutions to challenging data problems. The research conducted in the labs is applied to various domains including medical imaging, neuroscience, cellular biology, psychology, security and urban studies.

Current Research Projects

Identification of Gene Function Using Image Analytics

  • Funding Agency: DePaul – RFUMS Collaborative Pilot Research Grant
  • Type of Project: Collaborative Project with Rosalind Franklin University Medical School
  • Project Description: A challenge in neuroscience is understanding the genetic bases of behavior; traditionally, the nematode Caenorhabditis elegans is used as a model organism for neural studies due to its simple neural structure and well known connectome. Our study aims to identify genes that modulate food related behaviors in nematodes by quantifying behavioral differences in mutant strains. In order to empirically quantify nematode behavior, we have developed methods for recording and tracking nematodes over long periods of time, as well as algorithms for extracting and analyzing information from the observational data.

Computational Methods for Chronic Fatigue Syndrome

  • Type of Project: Collaborative Project with College of Science and Health, DePaul University
  • Project Description: The goal of the Chronic Fatigue Syndrome (CFS) project is to analyze existing data to come up with an empirical definition for Chronic Fatigue Syndrome that could be used to develop a homogenous research group from which to explore biological causes. Because 1) current definitions of CFS are based on medical consensus, and 2) CFS shares symptoms with many other disorders, it is difficult to accurately explore biological causes. Recently, a new definition came out for Systemic Exertion Intolerance Disease (SEID), which is supposed to replace CFS and is causing some interesting movement in the research.

Computer-aided Diagnosis for Lung Cancer

  • Funding Agency: DePaul URC Grant
  • Type of Project: Collaborative Project with University of Chicago
  • Project Description: The Lung Nodule Database Consortium (LIDC) is a joint initiative among five institutions providing a dataset for researchers to conduct analysis and develop techniques to advance the state-of-art computer-aided diagnosis (CADx) and detection (CADe) of lung nodules using Computed Tomography (CT) scans. The dataset contains 1,018 patient CT series in which 2,669 nodules are identified, outlined and rated by up to four radiologists. Radiologists provide 5-point scale ratings for 8 intermediate semantic characteristics and a malignancy rating. The complex structure of this dataset provides opportunities to conduct compelling research in Image Processing and Analysis, Machine Learning, and Data Mining, solving problems relevant beyond the medical domain.

MedIX: Research Experience for Undergraduates (REU) Program

  • Funding Agency: National Science Foundation
  • Type of Project: REU site jointly with University of Chicago
  • Project Description: The Medical Informatics (MedIX) program is a National Science Foundation REU site hosted by two interdisciplinary laboratories: the Medical Informatics Laboratory at DePaul University and the Imaging Research Institute at the University of Chicago. The main objectives of the MedIX REU program are to encourage talented undergraduates to pursue graduate education and to expose students to interdisciplinary research, especially at the border of information technology and medicine. For more information, please visit the MedIX REU site at

21st Century Technologies Learning Analytics

  • Funding Agency: College of Computing and Digital Media (CDM) Collaborative Grant
  • Type of Project: Collaborative Project with CDM School of Design
  • Project Description: Online social learning networks have offered students new opportunities to create, learn from exemplars, receive and offer feedback, and showcase their work in ways that are not limited by the constraints of classroom time and space. While the growing presence of computers in schools and prominence of social networks in the everyday lives of students have motivated educators to adopt online social learning networks, there remains a lack of tools to help teachers understand if and how the process of learning occurs. Educators would benefit from meaningful insights into how their students are interacting online, and how actions from teachers and mentors are supporting learning. At the same time, the rich data generated by these systems presents unique opportunities to understand teaching and learning online. This project develops data mining algorithms and social learning networks with the goals of offering educators the means to evaluate the health of the social network over time and tools that can be used to encourage desired learning outcomes.

Current Students

NameDegree Program
Valerie SimonisPhD student
Evan Story MS in Computer Science student
Miguel Carrazza BS in Computer Science student
Sriram Yarlagadda MS in Predictive Analytics student
Ian Wang MS in Computer Science student
Carleton Smith MS in Predictive Analytics student
Mingfei Shao MS in Game Development student
Taha Hamid MS in Predictive Analytics
Taihua Li MS in Predictive Analytics

Sample Publications

  • Miguel Carrazza, Brendan Kennedy, Jacob Furst, Alex Rasin, Daniela S. Raicu, "Investigating the effects of majority voting on CAD systems: an LIDC case study", SPIE Medical Imaging. San Diego, California, February 27 - March 3, 2016.
  • Brendan Kennedy, Miguel Carrazza, Jacob Furst, Alex Rasin, “Applying Association Rule Mining to Semantic Data in the Lung Image Database Consortium”, IEEE International Conference in Data Mining, Atlantic City, New Jersey, November 14 - 17, 2015
  • Furst J.D., Raicu D.S., and Jason L.A. “Data Mining”, In L.A. Jason & D.S. Glenwick (Eds). Handbook of Methodological Approaches to Community-Based Research: Qualitative, Quantitative, and Mixed Methods, 2015.
  • Moy K., Simonis V., Li W., Story E., Brandon C., Furst J., Raicu D., Kim H., “Computational Methods for Tracking, Quantitative Assessment, and Visualization of C. elegans Locomotory Behavior”, PLOS ONE Journal, 2015.
  • Zamacona J., Niehaus R, Rasin A., Furst JD., Raicu DS. “Assessing Diagnostic Complexity: an image feature-based strategy to reduce annotation costs”. Journal of Computers in Medicine and Biology, 2015, Feb 4. pii: S0010-4825(15)00030-X. doi: 10.1016/j.compbiomed.2015.01.013. (impact factor•=1.475)
  • Kelly H. Oh, Linu S. Abraham, Chandler Gegg, Christian Silvestri, Yung-Chi Huang, Mark J. Alkema, Jacob Furst, Daniela Raicu, Hongkyun Kim, “Presynaptic BK channel localization is dependent on the hierarchical organization of alpha-catulin and dystrobrevin and fine-tuned by CaV2 calcium channels”, BMC Neuroscience 2015, 16:26 doi:10.1186/s12868-015-0166-2. (impact factor•=2.85)
  • Niehaus R, Furst JD., S. Armato, Raicu DS, “The Importance of Shape Features for Computer-Aided Diagnosis of Lung Nodules”, Journal of Digital Imaging, February 2015. (impact factor•=1.1)