GSoC/GCI Archive
Google Summer of Code 2014

Biomedical Informatics, Emory University

License: Apache License, 2.0

Web Page:

Mailing List:

Biomedical Informatics (BMI) is a multidisciplinary field that studies and pursues the effective use of biomedical and clinical data, through novel computational approaches, driven by efforts to improve diagnosis, clinical care, and human health. The BMI department is working in the area of Big Data Analytics for Healthcare. We use our expertise in computer science and informatics by developing various enabling tools, technologies, and algorithms to solve specific biomedical and clinical applications. And in doing so help advance our understanding of disease and treatment, and also develop useful software and applications. Members of the department work in a variety of areas that range from healthcare middleware such as security, cloud computing, high end computing and metadata management, to clinical information systems, clinically oriented image analysis and biomedical knowledge modeling. The driving applications for the various ongoing projects include cancer research, organ transplant, HIV, medical imaging, radiation therapy, and clinical data analytics. This year we are partnering with our collaborators from the Electronic Research Lab (ERL) at Washington University, St. Louis. ERL has a long history of conducting pioneering research and development in medical imaging informatics. In recent years they have developed open source application hosting platforms such as OpenXIP and Algorithm Validation Toolkit. Mentors from ERL have some exciting projects involving the Cancer Imaging Archive (TCIA). TCIA is one of the largest a public repositories of cancer images and related clinical data with the express purpose of enabling open science research. Currently over 26 million radiologic images and several thousand pathology images of cancer are contained in this repository. All development work that is undertaken by both departments is free and open-source.


  • Data Replication / Synchronization Tools Consumers download the data by searching the image repository using the browser. The information that the consumer is interested in, gets updated whenever the data producers update or add patient information. The current download tool lacks the ability to track the relevant updates to the consumer. A pub-sub solution based on Apache CXF, utilizing the JAX-RS REST API of CXF will assist automated downloads to the consumers.
  • Medical Vocabulary Generating Tool Create a tool that can improve the usage for standardized medical vocabulary such as ICD-10 and HL7. Since there are various medical standards and vocabularies in use, it would be very valuable to design a system and corresponding protocol that can parse and reformat them to a more formal representation, like XML. The goal of the tool is to enable and ease the process of customizing a domain specific vocabulary and help medical professionals with their specific usage of the domain knowledge.
  • TCIA Data Exploration and Information Visualization We propose an environment for visualizing and exploring TCIA data . We leverage TCIA's REST API to programmatically query and download data. We propose methods to create a new search interface to the data as an alternate way to explore the contents of TCIA, create dynamic dashboards that can be extended to support the exploration of TCIA data using Javascript libraries like crossfilter and dc.js. This method is extendible to support data from other remote archives.
  • Web-based Source To Target Mappings UX design is more than making a nice visual design, it'a a process of understanding customers, business requirements and comming up with the right solution. I plan to work with my mentor, the comunity and users in finding the best UX and UI design for the source to target mappings project and also implement the solution in the production code.