Dr. 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.
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 2023. 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.
Prospective students are required to have a professional work ethic, passion for research and coding, solid knowledge of applied mathematics or engineering mathematics and fluent written and verbal skills. In addition, knowledge of data science, statistical science and network science is a bonus. Currently, GRG is also interested in students with a strong focus in game development and shader programming.
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.
For more information see https://grg.luddy.indiana.edu
Garyfallidis, Eleftherios, Matthew Brett, Bagrat Amirbekian, Ariel Rokem, Stefan Van Der Walt, Maxime Descoteaux, and Ian Nimmo-Smith. "Dipy, a library for the analysis of diffusion MRI data." Frontiers in Neuroinformatics 8 (2014): 8.
KH Maier-Hein, PF Neher, JC Houde, MA Cote, E Garyfallidis et al. "The challenge of mapping the human connectome based on diffusion tractography." Nature communications 8 (1), 1349, 2017.
Garyfallidis, Eleftherios, Serge Koudoro, Javier Guaje, Marc-Alex Cote, Soham Biswas, David Reagan, Nasim Anousheh, Filipi Silva, Geoffrey Fox, and Fury Contributors. "FURY: advanced scientific visualization." Journal of Open Source Software 6, no. 64 (2021): 3384.
Chandio, Bramsh Qamar, Shannon Leigh Risacher, Franco Pestilli, Daniel Bullock, Fang-Cheng Yeh, Serge Koudoro, Ariel Rokem, Jaroslaw Harezlak, and Eleftherios Garyfallidis. "Bundle analytics, a computational framework for investigating the shapes and profiles of brain pathways across populations." Scientific Reports 10, no. 1 (2020): 1-18.
Garyfallidis, Eleftherios, Marc-Alexandre Cote, Francois Rheault, Jasmeen Sidhu, Janice Hau, Laurent Petit, David Fortin, Stephen Cunanne, and Maxime Descoteaux. "Recognition of white matter bundles using local and global streamline-based registration and clustering." NeuroImage 170 (2018): 283-295.
Garyfallidis, Eleftherios, Omar Ocegueda, Demian Wassermann, and Maxime Descoteaux. "Robust and efficient linear registration of white-matter fascicles in the space of streamlines." NeuroImage 117 (2015): 124-140.
Garyfallidis, Eleftherios, Matthew Brett, Marta Morgado Correia, Guy B. Williams, and Ian Nimmo-Smith. "Quickbundles, a method for tractography simplification." Frontiers in neuroscience 6 (2012): 175.