About the Lab
The Garyfallidis Research Group (GRG) was established on September 1,
2016, by Dr. Eleftherios Garyfallidis. GRG specializes in cutting-edge
research across multiple domains, including medical imaging, machine
learning, signal processing, scientific visualization, and software
engineering. The group’s primary focus is the development of innovative
methods in these areas, particularly for the analysis of MRI data. This
research has broad applications, such as mapping the brain's structural
connectivity, as well as targeted uses in fields like Alzheimer's
disease research and brain tumor tracking.
GRG also serves as the headquarters for DIPY, a renowned international software project dedicated to computational neuroanatomy. DIPY is widely recognized for its contributions to the field, offering advanced tools for understanding brain structure and function through imaging technologies.
GRG also serves as the headquarters for DIPY, a renowned international software project dedicated to computational neuroanatomy. DIPY is widely recognized for its contributions to the field, offering advanced tools for understanding brain structure and function through imaging technologies.
About the Founder
Dr. Eleftherios Garyfallidis holds the position of
Associate Professor of Intelligent Systems Engineering (ISE) at
Indiana University (IU) Luddy School of Informatics, Computing, and
Engineering.
Prof. Garyfallidis works on the interface between machine learning, medical imaging and engineering visualization.
Prof. Garyfallidis is a pioneer in the world of scientific open source software as he is a core member of the Neuroimaging in Python development team that revolutionized and democratized the way research is performed in Neuroscience. Other members of the team include Matthew Brett (nibabel), Gael Varoquaux (scikit-learn), Fernando Perez (jupyter), Stefan van der Walt (scikit-image), Satrajit Gosh (nipype) and Ariel Rokem (nitime). Dr. Garyfallidis was the youngest member of the team but he was instrumental to the success of Neuroimaging in Python by leading the Diffusion Imaging in Python (DIPY) project. One of the most challenging and research heavy projects in scientific software in the world. Prof. Garyfallidis is the inventor of multiple ground breaking algorithms including QuickBundles. QuickBundles was the first fast and unsupervised algorithm in neuroimaging for grouping tractographies using streamlines. Prof. Garyfallidis is the inventor of SLR. SLR is the most accurate method for affinely registering bundles or tractograms. Prof. Garyfallidis research has been foundational in understanding the challenges of brain tractography. Due to a method called RecoBundles, in 2015 Garyfallidis enabled the evaluation of tractographies in data with distortions. Until that day, no other method was able to solve this problem. This led to a publication in Nature Communications that evaluated the state-of-the-art in tractography research across many labs in the world.
Prof. Garyfallidis is a pioneer in the world of scientific open source software as he is a core member of the Neuroimaging in Python development team that revolutionized and democratized the way research is performed in Neuroscience. Other members of the team include Matthew Brett (nibabel), Gael Varoquaux (scikit-learn), Fernando Perez (jupyter), Stefan van der Walt (scikit-image), Satrajit Gosh (nipype) and Ariel Rokem (nitime). Dr. Garyfallidis was the youngest member of the team but he was instrumental to the success of Neuroimaging in Python by leading the Diffusion Imaging in Python (DIPY) project. One of the most challenging and research heavy projects in scientific software in the world. Prof. Garyfallidis is the inventor of multiple ground breaking algorithms including QuickBundles. QuickBundles was the first fast and unsupervised algorithm in neuroimaging for grouping tractographies using streamlines. Prof. Garyfallidis is the inventor of SLR. SLR is the most accurate method for affinely registering bundles or tractograms. Prof. Garyfallidis research has been foundational in understanding the challenges of brain tractography. Due to a method called RecoBundles, in 2015 Garyfallidis enabled the evaluation of tractographies in data with distortions. Until that day, no other method was able to solve this problem. This led to a publication in Nature Communications that evaluated the state-of-the-art in tractography research across many labs in the world.
The pioneering work that Dr. Garyfallidis started and is today championed by his graduate students. See for example his labs work on Patch2Self denoising and Bundle Analytics. Prof. Garyfallidis is organizing yearly workshops (see DIPY workshops) to train faculty and students to use the latest methods in neuroimaging.
Prof. Garyfallidis is the creator and lead of FURY. FURY was created to address this necessity of high-performance 3D scientific visualization in an easy-to-use API fully compatible with the Pythonic ecosystem and for heavy duty use (large and dynamic data). FURY uses OpenGL/Vulkan and enhances them using customized shaders. FURY provides access to the latest technologies such as raytracing, signed distance functionality, physically based rendering, and collision detection for direct use in research. More importantly, FURY enables students and researchers to script their own 3D animations in Python and simulate dynamic environments. Students and industrial partners can use FURY to showcase: optimization problems, machine learning algorithms, investigate different representations of the data and even create interactive games with skinning and morphing and physical simulations. FURY is driving scientific innovation. For example, it gave rise to Furious Atoms and Horizon projects.
Prof. Garyfallidis is the director of the GRG research group at ISE specializing in the development of new methods and intelligent algorithms for medical imaging and brain mapping. In addition, the GRG creates general purpose machine learning algorithms that solve hard problems for a great range of domains. One of the most exciting projects is Thetan. Thetan is a new machine learning framework that outperforms the current state of the art in machine learning. The Thetan software is aimed to be released in Fall 2026. In addition, the GRG team is working on many areas in ML from improving optimization using topology to creating new neural networks and reinforcement learning methods to solve eminent signal processing problems.
Prof. Garyfallidis has won multiple scientific challenges (IEEE) and his research is supported by multiple NIH and NSF grants. His target conferences include NeurIPS, ICML, ICLR, ISMRM, OHBM, IEEEVis and RSNA.
Prof. Garyfallidis teaches intro to neuroengineering (ENGR-E 506) and image processing (ENGR-E 435/535, CSCI-B 456) (an advanced signal processing class). Prof. Garyfallidis is a core member of IUNI (IU Network Science Institute) and directs a new project for visualizing and interacting with large dynamic networks.
Dr. Garyfallidis has a background in robotics, computer vision and neuroscience. He holds a PhD from the University of Cambridge, UK, advised by Royal Statistician and Prof. Ian Nimmo-Smith. He was also a Postdoctoral researcher with Prof. Maxime Descoteaux, inventor of analytical QBall, at the Sherbrooke Connectivity Imaging Lab (SCIL) of the University of Sherbrooke, CA.
Prof. Garyfallidis has 20 years of experience in collaborating and supporting the research and day to day practice of psychiatrists, psychologists, neuroanatomists, neurosurgeons and ophthalmologists (dMRI, EEG, MEG, fMRI, OCT). Finally, Prof. Garyfallidis innovations and software are used by leading engineering companies such as IBM Watson and NVIDIA.
Prof. Garyfallidis works on the interface between machine learning, medical imaging and engineering visualization.
Prof. Garyfallidis is a pioneer in the world of scientific open source software as he is a core member of the Neuroimaging in Python development team that revolutionized and democratized the way research is performed in Neuroscience. Other members of the team include Matthew Brett (nibabel), Gael Varoquaux (scikit-learn), Fernando Perez (jupyter), Stefan van der Walt (scikit-image), Satrajit Gosh (nipype) and Ariel Rokem (nitime). Dr. Garyfallidis was the youngest member of the team but he was instrumental to the success of Neuroimaging in Python by leading the Diffusion Imaging in Python (DIPY) project. One of the most challenging and research heavy projects in scientific software in the world. Prof. Garyfallidis is the inventor of multiple ground breaking algorithms including QuickBundles. QuickBundles was the first fast and unsupervised algorithm in neuroimaging for grouping tractographies using streamlines. Prof. Garyfallidis is the inventor of SLR. SLR is the most accurate method for affinely registering bundles or tractograms. Prof. Garyfallidis research has been foundational in understanding the challenges of brain tractography. Due to a method called RecoBundles, in 2015 Garyfallidis enabled the evaluation of tractographies in data with distortions. Until that day, no other method was able to solve this problem. This led to a publication in Nature Communications that evaluated the state-of-the-art in tractography research across many labs in the world.
Prof. Garyfallidis is a pioneer in the world of scientific open source software as he is a core member of the Neuroimaging in Python development team that revolutionized and democratized the way research is performed in Neuroscience. Other members of the team include Matthew Brett (nibabel), Gael Varoquaux (scikit-learn), Fernando Perez (jupyter), Stefan van der Walt (scikit-image), Satrajit Gosh (nipype) and Ariel Rokem (nitime). Dr. Garyfallidis was the youngest member of the team but he was instrumental to the success of Neuroimaging in Python by leading the Diffusion Imaging in Python (DIPY) project. One of the most challenging and research heavy projects in scientific software in the world. Prof. Garyfallidis is the inventor of multiple ground breaking algorithms including QuickBundles. QuickBundles was the first fast and unsupervised algorithm in neuroimaging for grouping tractographies using streamlines. Prof. Garyfallidis is the inventor of SLR. SLR is the most accurate method for affinely registering bundles or tractograms. Prof. Garyfallidis research has been foundational in understanding the challenges of brain tractography. Due to a method called RecoBundles, in 2015 Garyfallidis enabled the evaluation of tractographies in data with distortions. Until that day, no other method was able to solve this problem. This led to a publication in Nature Communications that evaluated the state-of-the-art in tractography research across many labs in the world.
The pioneering work that Dr. Garyfallidis started and is today championed by his graduate students. See for example his labs work on Patch2Self denoising and Bundle Analytics. Prof. Garyfallidis is organizing yearly workshops (see DIPY workshops) to train faculty and students to use the latest methods in neuroimaging.
Prof. Garyfallidis is the creator and lead of FURY. FURY was created to address this necessity of high-performance 3D scientific visualization in an easy-to-use API fully compatible with the Pythonic ecosystem and for heavy duty use (large and dynamic data). FURY uses OpenGL/Vulkan and enhances them using customized shaders. FURY provides access to the latest technologies such as raytracing, signed distance functionality, physically based rendering, and collision detection for direct use in research. More importantly, FURY enables students and researchers to script their own 3D animations in Python and simulate dynamic environments. Students and industrial partners can use FURY to showcase: optimization problems, machine learning algorithms, investigate different representations of the data and even create interactive games with skinning and morphing and physical simulations. FURY is driving scientific innovation. For example, it gave rise to Furious Atoms and Horizon projects.
Prof. Garyfallidis is the director of the GRG research group at ISE specializing in the development of new methods and intelligent algorithms for medical imaging and brain mapping. In addition, the GRG creates general purpose machine learning algorithms that solve hard problems for a great range of domains. One of the most exciting projects is Thetan. Thetan is a new machine learning framework that outperforms the current state of the art in machine learning. The Thetan software is aimed to be released in Fall 2026. In addition, the GRG team is working on many areas in ML from improving optimization using topology to creating new neural networks and reinforcement learning methods to solve eminent signal processing problems.
Prof. Garyfallidis has won multiple scientific challenges (IEEE) and his research is supported by multiple NIH and NSF grants. His target conferences include NeurIPS, ICML, ICLR, ISMRM, OHBM, IEEEVis and RSNA.
Prof. Garyfallidis teaches intro to neuroengineering (ENGR-E 506) and image processing (ENGR-E 435/535, CSCI-B 456) (an advanced signal processing class). Prof. Garyfallidis is a core member of IUNI (IU Network Science Institute) and directs a new project for visualizing and interacting with large dynamic networks.
Dr. Garyfallidis has a background in robotics, computer vision and neuroscience. He holds a PhD from the University of Cambridge, UK, advised by Royal Statistician and Prof. Ian Nimmo-Smith. He was also a Postdoctoral researcher with Prof. Maxime Descoteaux, inventor of analytical QBall, at the Sherbrooke Connectivity Imaging Lab (SCIL) of the University of Sherbrooke, CA.
Prof. Garyfallidis has 20 years of experience in collaborating and supporting the research and day to day practice of psychiatrists, psychologists, neuroanatomists, neurosurgeons and ophthalmologists (dMRI, EEG, MEG, fMRI, OCT). Finally, Prof. Garyfallidis innovations and software are used by leading engineering companies such as IBM Watson and NVIDIA.