Biomedical Informatics, Emory University

Department of Biomedical Informatics (BMI), Emory University School of Medicine

Technologies
python, java, tensorflow, deep learning, medical imaging
Topics
cloud, distributed systems, science and medicine, precision medicine, data integration
Department of Biomedical Informatics (BMI), Emory University School of Medicine

Biomedical Informatics (BMI) is a multidisciplinary field that is motivated by our desire to improve diagnosis, clinical care, and human health, through novel computational approaches to use (and learn from) biomedical and clinical data. 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 machine learning, healthcare middleware that leverages cloud computing, 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. All development work that is undertaken is free and open-source.

We have had a diverse set of successful GSoC projects in the past. In previous years, GSoC students have worked on diverse projects such as: geospatial systems for exploring microscopy environments that leveraged Hadoop; GPU accelerated pipelines for computational analysis of digitized biopsies; interactive visualization platforms for viewing massive images (>1GB); systems for data agnostic sharing of biomedical research datasets; Apache Drill based data integration platform; CNN based high throughput analysis of digitized biopsies; and information visualization of heterogeneous medical data. Many of these projects have been published in reputable journals and presented at major conferences. Some of the projects proved to be so successful that they were adopted in major national/international biomedical research initiatives.

2019 Program

Successful Projects

Contributor
Vikas Gola
Mentor
Monjoy Saha, Pooya Mobadersany
Organization
Biomedical Informatics, Emory University
Graphical User Interface for Tensorflow
The idea of this project is to make a software in which a user can make deep learning models in an easy way using a graphical user interface with...
Contributor
Insiyah Hajoori
Mentor
Ryan Birmingham, Nan Li
Organization
Biomedical Informatics, Emory University
Machine Learning Model Support for Digital Pathology
The following modules are to be integrated with caMicroscope: Creating a workflow to allow model developers to allow their model to be run on a...
Contributor
Vinay Pandramish
Mentor
Ganesh Iyer, Sapoon Dutta
Organization
Biomedical Informatics, Emory University
Deep Learning based Visual Recommendations
We come up with models that give the effective and efficient visualizations as recommendations to the given input. Current visualization tools...
Contributor
Tushar Aggarwal
Mentor
Pradeeban Kathiravelu
Organization
Biomedical Informatics, Emory University
Security Enhancements to Bindaas Data Integration Middleware
Bindaas acts as a unified interface to various data sources like Apache Drill, MySQL and MongoDB. The aim of this project is to add new modules that...