Ilwoo Lyu

(류일우)

3D Shape Analysis Lab (ShapeLab)
Computer Science and Engineering
Engineering Bldg. 106, 801-5
50 UNIST-gil, Ulsan 44919, Korea
E-mail: ilwoolyu at unist ac kr
Phone: +82-52-217-2298

Affiliations: @UNIST [CSE] [AIGS] [BME]
@Vanderbilt [CS] [VISE]
[Google Scholar] [GitHub]

orcid.org/0000-0001-5868-9603

Last Updated: December 2022

About Myself / Research Interests / Education / Employment / Publications / Teaching / Talks / Software

About Myself

I am an assistant professor of Computer Science and Engineering at Ulsan National Institute of Science and Technology (UNIST) and an adjoint assistant professor of Computer Science at Vanderbilt University. Prior to joining UNIST, I was a research assistant professor of Electrical Engineering and Computer Science at Vanderbilt University. I earned my PhD in Computer Science at The University of North Carolina at Chapel Hill. My main research area intersects computer vision, machine learning, and medical image analysis. I am interested particularly in developing novel algorithms for 3D shape analysis based on computer vision and machine learning techniques to explore highly convoluted shapes. My research topics span data processing on non-regular grids including shape matching, geometric feature extraction, unstructured neural nets design, statistical shape analysis, and 3D visualization with applications to medical image analysis. Please visit 3D Shape Analysis Lab (ShapeLab) for more information.

Research Interests

3D Shape Analysis
Image Processing
Computer Vision
Machine Learning
Medical Image Analysis

Education

The University of North Carolina at Chapel Hill Doctor of Philosophy in Computer Science	2011 - 2017
Korea Advanced Institute of Science and Technology (KAIST) Master of Science in Computer Science	2009 - 2011
KAIST Bachelor of Science in Computer Science	2002 - 2009

Employment

UNIST, Ulsan, Korea Assistant Professor	Mar 2021 - Present
Vanderbilt University, Nashville, TN, USA Adjoint Assistant Professor	Mar 2021 - Present
MASI Lab, Vanderbilt University, Nashville, TN, USA Research Assistant Professor Mentor: Dr. Bennett Landman	Mar 2017 - Feb 2021
Neuro Image Research and Analysis Lab, UNC, Chapel Hill, NC, USA Research Assistant Advisor: Dr. Martin Styner	Dec 2011 - Feb 2017
IBM Almaden Reserach Center, San Jose, California, USA Intern Mentor: Dr. Tanveer F. Syeda-Mahmood and Dr. Colin B. Compas	May 2015 - Jul 2015
Computer Graphics Laboratory, KAIST, Daejeon, Korea Research Assistant Advisor: Dr. Sung Yong Shin and Dr. Joon-Kyung Seong	Jun 2010 - May 2011
Cognitive Robotic Vision Laboratory, KIST, Seoul, Korea Intern Mentor: Dr. Sung-Kee Park	Mar 2009 - May 2009

Selected Publications

[Expand] [Collapse]

	SPHARM-Net: Spherical Harmonics-based Convolution for Cortical Parcellation [DOI] [PMID:35436188] [Abstract] [Software] Seungbo Ha, Ilwoo Lyu IEEE Transactions on Medical Imaging, 41(10), 2739-2751, 2022
We present a spherical harmonics-based convolutional neural network (CNN) for cortical parcellation, which we call SPHARM-Net. Recent advances in CNNs offer cortical parcellation on a fine-grained triangle mesh of the cortex. Yet, most CNNs designed for cortical parcellation employ spatial convolution that depends on extensive data augmentation and allows only predefined neighborhoods of specific spherical tessellation. On the other hand, a rotation-equivariant convolutional filter avoids data augmentation, and rotational equivariance can be achieved in spectral convolution independent of a neighborhood definition. Nevertheless, the limited resources of a modern machine enable only a finite set of spectral components that might lose geometric details. In this paper, we propose (1) a constrained spherical convolutional filter that supports an infinite set of spectral components and (2) an end-to-end framework without data augmentation. The proposed filter encodes all the spectral components without the full expansion of spherical harmonics. We show that rotational equivariance drastically reduces the training time while achieving accurate cortical parcellation. Furthermore, the proposed convolution is fully composed of matrix transformations, which offers efficient and fast spectral processing. In the experiments, we validate SPHARM-Net on two public datasets with manual labels: Mindboggle-101 (N=101) and NAMIC (N=39). The experimental results show that the proposed method outperforms the state-of-the-art methods on both datasets even with fewer learnable parameters without rigid alignment and data augmentation. Our code is publicly available at https://github.com/Shape-Lab/SPHARM-Net. Hide
	Labeling Lateral Prefrontal Sulci using Spherical Data Augmentation and Context-aware Training [DOI] [PMID:33497773] [Abstract] [Software] Ilwoo Lyu, Shunxing Bao, Lingyan Hao, Jewelia Yao, Jacob Miller, Willa Voorhies, Warren Taylor, Silvia Bunge, Kevin Weiner, Bennett Landman NeuroImage, 229, 117758, 2021
The inference of cortical sulcal labels often focuses on deep (primary and secondary) sulcal regions, whereas shallow (tertiary) sulcal regions are largely overlooked in the literature due to the scarcity of manual/well-defined annotations and their large neuroanatomical variability. In this paper, we present an automated framework for regional labeling of both primary/secondary and tertiary sulci of the dorsal portion of lateral prefrontal cortex (LPFC) using spherical convolutional neural networks. We propose two core components that enhance the inference of sulcal labels to overcome such large neuroanatomical variability: (1) surface data augmentation and (2) context-aware training. (1) To take into account neuroanatomical variability, we synthesize training data from the proposed feature space that embeds intermediate deformation trajectories of spherical data in a rigid to non-rigid fashion, which bridges an augmentation gap in conventional rotation data augmentation. (2) Moreover, we design a two-stage training process to improve labeling accuracy of tertiary sulci by informing the biological associations in neuroanatomy: inference of primary/secondary sulci and then their spatial likelihood to guide the definition of tertiary sulci. In the experiments, we evaluate our method on 13 deep and shallow sulci of human LPFC in two independent data sets with different age ranges: pediatric (N=60) and adult (N=36) cohorts. We compare the proposed method with a conventional multi-atlas approach and spherical convolutional neural networks without/with rotation data augmentation. In both cohorts, the proposed data augmentation improves labeling accuracy of deep and shallow sulci over the baselines, and the proposed context-aware training offers further improvement in the labeling of shallow sulci over the proposed data augmentation. We share our tools with the field and discuss applications of our results for understanding neuroanatomical-functional organization of LPFC and the rest of cortex (https://github.com/ilwoolyu/SphericalLabeling). Hide
	Cortical Surface Parcellation using Spherical Convolutional Neural Networks [DOI] [PMID:31803864] [Abstract] [Software] Prasanna Parvathaneni, Shunxing Bao, Vishwesh Nath, Neil Woodward, Daniel Claassen, Carissa Cascio, David Zald, Yuankai Huo, Bennett Landman, Ilwoo Lyu Medical Image Computing and Computer Assisted Intervention (MICCAI) 2019, LNCS11766, 501-509, Shenzhen, China, 2019, early accept, travel award
We present cortical surface parcellation using spherical deep convolutional neural networks. Traditional multi-atlas cortical surface parcellation requires inter-subject surface registration using geometric features with slow processing speed on a single subject (2-3 h). Moreover, even optimal surface registration does not necessarily produce optimal cortical parcellation as parcel boundaries are not fully matched to the geometric features. In this context, a choice of training features is important for accurate cortical parcellation. To utilize the networks efficiently, we propose cortical parcellation-specific input data from an irregular and complicated structure of cortical surfaces. To this end, we align ground-truth cortical parcel boundaries and use their resulting deformation fields to generate new pairs of deformed geometric features and parcellation maps. To extend the capability of the networks, we then smoothly morph cortical geometric features and parcellation maps using the intermediate deformation fields. We validate our method on 427 adult brains for 49 labels. The experimental results show that our method outperforms traditional multi-atlas and naive spherical U-Net approaches, while achieving full cortical parcellation in less than a minute. Hide
	Hierarchical Spherical Deformation for Cortical Surface Registration [DOI] [PMID:31280090] [Abstract] [Software] Ilwoo Lyu, Hakmook Kang, Neil Woodward, Martin Styner, Bennett Landman Medical Image Analysis, 57, 72-88, 2019
We present hierarchical spherical deformation for a group-wise shape correspondence to address template selection bias and to minimize registration distortion. In this work, we aim at a continuous and smooth deformation field to guide accurate cortical surface registration. In conventional spherical registration methods, a global rigid alignment and local deformation are independently performed. Motivated by the composition of precession and intrinsic rotation, we simultaneously optimize global rigid rotation and non-rigid local deformation by utilizing spherical harmonics interpolation of local composite rotations in a single framework. To this end, we indirectly encode local displacements by such local composite rotations as functions of spherical locations. Furthermore, we introduce an additional regularization term to the spherical deformation, which maximizes its rigidity while reducing registration distortion. To improve surface registration performance, we employ the second order approximation of the energy function that enables fast convergence of the optimization. In the experiments, we validate our method on healthy normal subjects with manual cortical surface parcellation in registration accuracy and distortion. We show an improved shape correspondence with high accuracy in cortical surface parcellation and significantly low registration distortion in surface area and edge length. In addition to validation, we discuss parameter tuning, optimization, and implementation design with potential acceleration. Hide
	Hierarchical Spherical Deformation for Shape Correspondence [DOI] [PMID:31803863] [Abstract] [Software] Ilwoo Lyu, Martin Styner, Bennett Landman Medical Image Computing and Computer Assisted Intervention (MICCAI) 2018, LNCS11070, 853-861, Granada, Spain, 2018, early accept, oral presentation
We present novel spherical deformation for a landmark-free shape correspondence in a group-wise manner. In this work, we aim at both addressing template selection bias and minimizing registration distortion in a single framework. The proposed spherical deformation yields a non-rigid deformation field without referring to any particular spherical coordinate system. Specifically, we extend a rigid rotation represented by well-known Euler angles to general non-rigid local deformation via spatial-varying Euler angles. The proposed method employs spherical harmonics interpolation of the local displacements to simultaneously solve rigid and non-rigid local deformation during the optimization. This consequently leads to a continuous, smooth, and hierarchical representation of the deformation field that minimizes registration distortion. In addition, the proposed method is group-wise registration that requires no specific template to establish a shape correspondence. In the experiments, we show an improved shape correspondence with high accuracy in cortical surface parcellation as well as significantly low registration distortion in surface area and edge length compared to the existing registration methods while achieving fast registration in 3 m per subject. Hide
	A Cortical Shape-Adaptive Approach to Local Gyrification Index [DOI] [PMID:29990689] [Abstract] [Software] Ilwoo Lyu, Sun Hyung Kim, Jessica Girault, John Gilmore, Martin Styner Medical Image Analysis, 48, 244-258, 2018
The amount of cortical folding, or gyrification, is typically measured within local cortical regions covered by an equidistant geodesic or nearest neighborhood-ring kernel. However, without careful design, such a kernel can easily cover multiple sulcal and gyral regions that may not be functionally related. Furthermore, this can result in smoothing out details of cortical folding, which consequently blurs local gyrification measurements. In this paper, we propose a novel kernel shape to locally quantify cortical gyrification within sulcal and gyral regions. We adapt wavefront propagation to generate a spatially varying kernel shape that encodes cortical folding patterns: neighboring gyral crowns, sulcal fundi, and sulcal banks. For this purpose, we perform anisotropic wavefront propagation that runs fast along gyral crowns and sulcal fundi by solving a static Hamilton-Jacobi partial differential equation. The resulting kernel adaptively elongates along gyral crowns and sulcal fundi, while keeping a uniform shape over flat regions like sulcal banks. We then measure local gyrification within the proposed spatially varying kernel. The experimental results show that the proposed kernel-based gyrification measure achieves a higher reproducibility than the conventional method in a multi-scan dataset. We further apply the proposed kernel to a brain development study in the early postnatal phase from neonate to 2 years of age. In this study we find that our kernel yields both positive and negative associations of gyrification with age, whereas the conventional method only captures positive associations. In general, our method yields sharper and more detailed statistical maps that associate cortical folding with sex and gestational age. Hide
	TRACE: A Topological Graph Representation for Automatic Sulcal Curve Extraction [DOI] [PMID:29969416] [Abstract] [Software] Ilwoo Lyu, Sun Hyung Kim, Neil Woodward, Martin Styner, Bennett Landman IEEE Transactions on Medical Imaging, 37(7), 1653-1663, 2018
A proper geometric representation of the cortical regions is a fundamental task for cortical shape analysis and landmark extraction. However, a significant challenge has arisen due to the highly variable, convoluted cortical folding patterns. In this paper, we propose a novel topological graph representation for automatic sulcal curve extraction (TRACE). In practice, the reconstructed surface suffers from noise influences introduced during image acquisition/surface reconstruction. In the presence of noise on the surface, TRACE determines stable sulcal fundic regions by employing the line simplification method that prevents the sulcal folding pattern from being significantly smoothed out. The sulcal curves are then traced over the connected graph in the determined regions by the Dijkstra's shortest path algorithm. For validation, we used state-of-the-art surface reconstruction pipelines on a reproducibility dataset. The experimental results showed a higher reproducibility and robustness to noise in TRACE than the existing method (Li et al. 2010) with over 20% relative improvement in error for both surface reconstruction pipelines. In addition, the extracted sulcal curves by TRACE were well-aligned with manually delineated primary sulcal curves. We also provided a choice of parameters to control a quality of the extracted sulcal curves and showed the influences of the parameter selection on the resulting curves. Hide
	Novel Local Shape-Adaptive Gyrification Index with Application to Brain Development [DOI] [Abstract] [Software] Ilwoo Lyu, Sun Hyung Kim, Jessica Bullins, John Gilmore, Martin Styner Medical Image Computing and Computer Assisted Intervention (MICCAI) 2017, LNCS10433, 31-39, Quebec City, Quebec, Canada, 2017
Conventional approaches to quantification of the cortical folding employ a simple circular kernel. Such a kernel commonly covers multiple cortical gyral/sulcal regions that may be functionally unrelated and also often blurs local gyrification measurements. We propose a novel adaptive kernel for quantification of the local cortical folding, which incorporates neighboring gyral crowns and sulcal fundi. The proposed kernel is adaptively elongated to cover regions along the cortical folding patterns. The experimental results showed that the proposed kernel-based gyrification measure achieved a higher reproducibility in a multi-scan human phantom dataset and captured the cortical folding in a more shape-adaptive way than the conventional method. In early human brain development, we found positive correlations with age over most cortical regions as previously found as well as novel, refined regions of both positive and negative correlations undetectable by the conventional method. Hide
	Group-Wise Cortical Correspondence via Sulcal Curve-Constrained Entropy Minimization [DOI] [PMID:24683983] [Abstract] [Tutorial] Ilwoo Lyu, Sun Hyung Kim, Joon-Kyung Seong, Sang Wook Yoo, Alan Evans, Yundi Shi, Mar Sanchez, Marc Niethammer, Martin Styner Information Processing in Medical Imaging (IPMI) 2013, LNCS7917, 364-375, Asilomar, California, USA, 2013, oral presentation with open-ended discussion
We present a novel cortical correspondence method employing group-wise registration in a spherical parametrization space for the use in local cortical thickness analysis in human and non-human primate neuroimaging studies. The proposed method is unbiased registration that estimates a continuous smooth deformation field into an unbiased average space via sulcal curve-constrained entropy minimization using spherical harmonic decomposition of the spherical deformation field. We initialize a correspondence by our pair-wise method that establishes a surface correspondence with a prior template. Since this pair-wise correspondence is biased to the choice of a template, we further improve the correspondence by employing unbiased ensemble entropy minimization across all surfaces, which yields a deformation field onto the iteratively updated unbiased average. The specific entropy metric incorporates two terms: the first focused on optimizing the correspondence of automatically extracted sulcal landmarks and the second on that of sulcal depth maps. We also propose an encoding scheme for spherical deformation via spherical harmonics as well as a novel method to choose an optimal spherical polar coordinate system for the most efficient deformation field estimation. The experimental results show evidence that the proposed method improves the correspondence quality in non-human primate and human subjects as compared to the pair-wise method. Hide
	Spectral-based Automatic Labeling and Refining of Human Cortical Sulcal Curves using Expert-Provided Examples [DOI] [PMID:20363334] [Abstract] Ilwoo Lyu, Joon-Kyung Seong, Sung Yong Shin, Kiho Im, Jee Hoon Roh, Min-Jeong Kim, Geon Ha Kim, Jong Hun Kim, Alan Evans, Duk L. Na, Jong-Min Lee NeuroImage, 52(1), 142-157, 2010
We present a spectral-based method for automatically labeling and refining major sulcal curves of a human cerebral cortex. Given a set of input (unlabeled) sulcal curves automatically extracted from a cortical surface and a collection of expert-provided examples (labeled sulcal curves), our objective is to identify the input major sulcal curves and assign their neuroanatomical labels, and then refines these curves based on the expert-provided example data, without employing any atlas-based registration scheme as preprocessing. In order to construct the example data, neuroanatomists manually labeled a set of 24 major sulcal curves (12 each for the left and right hemispheres) for each individual subject according to a precise protocol. We collected 30 sets of such curves from 30 subjects. Given the raw input sulcal curve set of a subject, we choose the most similar example curve to each input curve in the set to label and refine the latter according to the former. We adapt a spectral matching algorithm to choose the example curve by exploiting the sulcal curve features and their relationship. The high dimensionality of sulcal curve data in spectral matching is addressed by using their multi-resolution representations, which greatly reduces time and space complexities. Our method provides consistent labeling and refining results even under high variability of cortical sulci across the subjects. Through experiments we show that the results are comparable in accuracy to those done manually. Most output curves exhibited accuracy values higher than 80%, and the mean accuracy values of the curves in the left and the right hemispheres were 84.69% and 84.58%, respectively. Hide

- Full List -

Book Chapters
Multiatlas Segmentation [ISBN:9780128161760] Bennett Landman, Ilwoo Lyu, Yuankai Huo, Andrew Asman. Handbook of Medical Image Computing and Computer Assisted Intervention, 137-164, 2019
Journal Articles
Comprehensive shape analysis of the cortex in Huntington's disease [DOI] Zachary Stoebner, Kilian Hett, Ilwoo Lyu, Hans Johnson, Jane Paulsen, Jeffrey Long, Ipek Oguz. Human Brain Mapping, in press
Hierarchical particle optimization for cortical shape correspondence in temporal lobe resection [DOI] Yue Liu, Shunxing Bao, Dario Englot, Victoria Morgan, Warren Taylor, Ying Wei, Ipek Oguz, Bennett Landman, Ilwoo Lyu. Computers in Biology and Medicine, 152, 106414, 2023
Integrating the BIDS Neuroimaging Data Format and Workflow Optimization for Large-Scale Medical Image Analysis [DOI] [PMID:35922700] Shunxing Bao, Brian Boyd, Praitayini Kanakaraj, Karthik Ramadass, Francisco Meyer, Yuqian Liu, William Duett, Yuankai Huo, Ilwoo Lyu, David Zald, Seth Smith, Baxter Rogers, Bennett Landman. Journal of Digital Imaging, 35(6), 1576-1589, 2022
*Automated volumetric determination of high R₂^ regions in substantia nigra: a feasibility study of quantifying substantia nigra atrophy in progressive supranuclear palsy** [DOI] [PMID:35775868] Abel Worku Tessema, Hansol Lee, Yelim Gong, HwaPyeong Cho, Hamdia Murad Adem, Ilwoo Lyu, Jae-Hyeok Lee, HyungJoon Cho. NMR in Biomedicine, 35(11), e4795, 2022
SPHARM-Net: Spherical Harmonics-based Convolution for Cortical Parcellation [DOI] [PMID:35436188] Seungbo Ha, Ilwoo Lyu. IEEE Transactions on Medical Imaging, 41(10), 2739-2751, 2022
Uncovering a tripartite landmark in posterior cingulate cortex [DOI] [PMID:36070384] Ethan Willbrand, Benjamin Parker, Willa Voorhies, Jacob Miller, Ilwoo Lyu, Tyler Hallock, Lyndsey Aponik-Gremillion, Seth Koslov, Alzheimer's Disease Neuroimaging Initiative, Silvia Bunge, Brett Foster, Kevin Weiner. Science Advances, 8(36), eabn9516, 2022
Incomplete hippocampal inversion determines hippocampal shape deformations in schizophrenia [DOI] [Cover] Maxwell Roeske, Ilwoo Lyu, Maureen McHugo, Jeniffer Blackford, Neil Woodward, Stephan Heckers. Biological Psychiatry, 92(4), 314-322, 2022
Generalizing deep learning brain segmentation for skull removal and intracranial measurements [DOI] [PMID:34999162] Yue Liu, Yuankai Huo, Blake Dewey, Ying Wei, Ilwoo Lyu, Bennett Landman. Magnetic Resonance Imaging, 88, 44-52, 2022
Cortical morphology in ASD: findings from a cortical shape-adaptive approach to gyrification indexing [DOI] [PMID:34195789] Alisa Zoltowski, Ilwoo Lyu, Michelle Failla, Lisa Mash, Kacie Dunham, Jacob Feldman, Tiffany Woynaroski, Mark Wallace, Laura Barquero, Tin Nguyen, Laurie Cutting, Hakmook Kang, Bennett Landman, Carissa Cascio. Cerebral Cortex, 31(11), 5188-5205, 2021
Body Part Regression with Self-supervision [DOI] [PMID:33560981] Yucheng Tang, Riqiang Gao, Shizhong Han, Yunqiang Chen, Dashan Gao, Vishwesh Nath, Camilo Bermudez, Michael R Savona, Shunxing Bao, Ilwoo Lyu, Yuankai Huo, Bennett A Landman. IEEE Transactions on Medical Imaging, 40(5), 1499-1507, 2021
Anatomical texture patterns identify cerebellar distinctions between essential tremor and Parkinson's disease [DOI] [PMID:33755270] Killian Hett, Ilwoo Lyu, Paula Trujillo Diaz, Alexander Lopez, Megan Aumann, Kathleen Larson, Peter Hedera, Benoit Dawant, Bennett Landman, Daniel Claassen, Ipek Oguz. Human Brain Mapping, 42(8), 2322-2331, 2021
Labeling Lateral Prefrontal Sulci using Spherical Data Augmentation and Context-aware Training [DOI] [PMID:33497773] Ilwoo Lyu, Shunxing Bao, Lingyan Hao, Jewelia Yao, Jacob Miller, Willa Voorhies, Warren Taylor, Silvia Bunge, Kevin Weiner, Bennett Landman. NeuroImage, 229, 117758, 2021
High-resolution 3D Abdominal Segmentation with Random Patch Network Fusion [DOI] Yucheng Tang, Riqiang Gao, Ho Hin Lee, Shizhong Han, Yunqiang Chen, Dashan Gao, Vishwesh Nath, Camilo Bermudez, Michael Savona, Richard Abramson, Shunxing Bao, Ilwoo Lyu, Yuankai Huo, Bennett Landman. Medical Image Analysis, 69, 101894, 2021
Pandora: 4-D white matter bundle population-based atlases derived from diffusion MRI fiber tractography [DOI] [PMID:33196967] Colin Hansen, Qi Yang, Ilwoo Lyu, Francois Rheault, Cailey Kerley, Bramsh Qamar Chandio, Shreyas Fadnavis, Owen Williams, Andrea Shafer, Susan Resnick, David Zald, Laurie Cutting, Warren Taylor, Brian Boyd, Eleftherios Garyfallidis, Adam Anderson, Maxime Descoteaux, Bennett Landman, Kurt Schilling. Neuroinformatics, 2020
Fast Polynomial Approximation of Heat Kernel Convolution on Manifolds and Its Application to Brain Sulcal and Gyral Graph Pattern Analysis [DOI] [PMID:31976883] Shih-Gu Huang, Ilwoo Lyu, Anqi Qiu, Moo Chung. IEEE Transactions on Medical Imaging, 39(6), 2201-2212, 2020
A Bayesian Approach to Examining Default Mode Network Functional Connectivity and Cognitive Performance in Major Depressive Disorder [DOI] [PMID:32447185] Rui Wang, Kimberly Albert, Warren Taylor, Brian Boyd, Justin Blaber, Ilwoo Lyu, Bennett Landman, Jennifer Vega, Sepideh Shokouhi, Hakmook Kang. Psychiatry Research: Neuroimaging, 301, 111102, 2020
Network localization of clinical, cognitive, and neuropsychiatric symptoms in Alzheimer's disease [DOI] [PMID:32176777] Aaron Tetreault, Tony Phan, Dana Orlando, Ilwoo Lyu, Hakmook Kang, Bennett Landman, Ryan Darby. Brain, 143(4), 1249-1260, 2020
Deep Learning Reveals Untapped Information for Local White-matter Fiber Reconstruction in Diffusion-weighted MRI [DOI] [PMID:31323317] Vishwesh Nath, Kurt Schilling, Prasanna Parvathaneni, Colin Hansen, Allison Hainline, Yuankai Huo, Justin Blaber, Ilwoo Lyu, Vaibhav Janve, Yurui Gao, Iwona Stepniewska, Adam Anderson, Bennett Landman. Magnetic Resonance Imaging, 62, 220-227, 2019
Hierarchical Spherical Deformation for Cortical Surface Registration [DOI] [PMID:31280090] Ilwoo Lyu, Hakmook Kang, Neil Woodward, Martin Styner, Bennett Landman. Medical Image Analysis, 57, 72-88, 2019
Improving Human Cortical Sulcal Curve Labeling in Large Scale Cross-Sectional MRI using Deep Neural Networks [DOI] [PMID:31201823] Prasanna Parvathaneni, Vishwesh Nath, Maureen McHugo, Yuankai Huo, Susan Resnick, Neil Woodward, Bennett Landman, Ilwoo Lyu. Journal of Neuroscience Methods, 324, 108311, 2019
Improved Gray Matter Surface based Spatial Statistics in Neuroimaging Studies [DOI] [PMID:31128227] Prasanna Parvathaneni, Ilwoo Lyu, Yuankai Huo, Baxter Rogers, Kurt Schilling, Vishwish Nath, Justin Blaber, Allison Hainline, Adam Anderson, Neil Woodward, Bennett Landman. Magnetic Resonance Imaging, 61, 285-295, 2019
Registration-based Image Enhancement Improves Multi-Atlas Segmentation of the Thalamic Nuclei and Hippocampal Subfields [DOI] [PMID:30880111] Shunxing Bao, Camilo Bermudez, Yuankai Huo, Prasanna Parvathaneni, William Rodriguez, Susan Resnick, Pierre-Francois D'Haese, Maureen McHugo, Stephan Heckers, Benoit Dawant, Ilwoo Lyu, Bennett Landman. Magnetic Resonance Imaging, 59, 143-152, 2019
A Cortical Shape-Adaptive Approach to Local Gyrification Index [DOI] [PMID:29990689] Ilwoo Lyu, Sun Hyung Kim, Jessica Girault, John Gilmore, Martin Styner. Medical Image Analysis, 48, 244-258, 2018
TRACE: A Topological Graph Representation for Automatic Sulcal Curve Extraction [DOI] [PMID:29969416] Ilwoo Lyu, Sun Hyung Kim, Neil Woodward, Martin Styner, Bennett Landman. IEEE Transactions on Medical Imaging, 37(7), 1653-1663, 2018
Towards Portable Large-Scale Image Processing with High-Performance Computing [DOI] [PMID:29725960] Yuankai Huo, Justin Blaber, Stephen Damon, Brian Boyd, Shunxing Bao, Prasanna Parvathaneni, Camilo Bermudez Noguera, Shikha Chaganti, Vishwesh Nath, Jasmine Greer, Ilwoo Lyu, William French, Allen Newton, Baxter Rogers, Bennett Landman. Journal of Digital Imaging, 31(3), 304-314, 2018
Development of Cortical Shape in the Human Brain from 6 to 24 Months of Age via a Novel Measure of Shape Complexity [DOI] [PMID:27150231] Sun Hyung Kim, Ilwoo Lyu, Vladimir Fonov, Clement Vachet, Heather Hazlett, Rachel Smith, Joseph Piven, Stephen Dager, Robert McKinstry, John Pruett Jr, Alan Evans, Louis Collins, Kelly Botteron, Robert Schultz, Guido Gerig, Martin Styner, The IBIS Network. NeuroImage, 135, 163-176, 2016
Robust Estimation of Group-wise Cortical Correspondence with an Application to Macaque and Human Neuroimaging Studies [DOI] [PMID:26113807] Ilwoo Lyu, Sun Hyung Kim, Joon-Kyung Seong, Sang Wook Yoo, Alan Evans, Yundi Shi, Mar Sanchez, Marc Niethammer, Martin Styner. Frontiers in Neuroscience, 9, 210, 2015
Spectral-based Automatic Labeling and Refining of Human Cortical Sulcal Curves using Expert-Provided Examples [DOI] [PMID:20363334] Ilwoo Lyu, Joon-Kyung Seong, Sung Yong Shin, Kiho Im, Jee Hoon Roh, Min-Jeong Kim, Geon Ha Kim, Jong Hun Kim, Alan Evans, Duk L. Na, Jong-Min Lee. NeuroImage, 52(1), 142-157, 2010
Top Computer Science Conferences
From Brain to Body: Learning Low-Frequency Respiration and Cardiac Signals from fMRI Dynamics [DOI] Roza Bayrak, Colin Hansen, Jorge Salas, Nafis Ahmed, Ilwoo Lyu, Yuankai Huo, Catie Chang. Medical Image Computing and Computer Assisted Intervention (MICCAI) 2021, LNCS12907, 553-563, Strasbourg, France, 2021
Cortical Surface Parcellation using Spherical Convolutional Neural Networks [DOI] [PMID:31803864] Prasanna Parvathaneni, Shunxing Bao, Vishwesh Nath, Neil Woodward, Daniel Claassen, Carissa Cascio, David Zald, Yuankai Huo, Bennett Landman, Ilwoo Lyu. Medical Image Computing and Computer Assisted Intervention (MICCAI) 2019, LNCS11766, 501-509, Shenzhen, China, 2019, early accept, travel award
Enabling Multi-Shell b-Value Generalizability of Data-Driven Diffusion Models with Deep SHORE [DOI] Vishwesh Nath, Ilwoo Lyu, Kurt Schilling, Prasanna Parvathaneni, Colin Hansen, Yuankai Huo, Vaibhav Janve, Yurui Gao, Iwona Stepniewska, Adam Anderson, Bennett Landman. Medical Image Computing and Computer Assisted Intervention (MICCAI) 2019, LNCS11766, 573-581, Shenzhen, China, 2019
Fast Polynomial Approximation to Heat Diffusion in Manifolds [DOI] Shih-Gu Huang, Ilwoo Lyu, Anqi Qiu, Moo Chung. Medical Image Computing and Computer Assisted Intervention (MICCAI) 2019, LNCS11767, 48-56, Shenzhen, China, 2019
Technology Enablers for Cloud-based Multi-level Analysis Applications in Medical Image Processing [DOI] Shunxing Bao, Prasanna Parvathaneni, Yuankai Huo, Yogesh Barve, Andrew Plassard, Yuang Yao, Hongyang Sun, Ilwoo Lyu, David Zald, Bennett Landman, Aniruddha Gokhale. IEEE International Conference on BigData 2018, 1337-1346, Seattle, Washington, USA, 2018
Hierarchical Spherical Deformation for Shape Correspondence [DOI] [PMID:31803863] Ilwoo Lyu, Martin Styner, Bennett Landman. Medical Image Computing and Computer Assisted Intervention (MICCAI) 2018, LNCS11070, 853-861, Granada, Spain, 2018, early accept, oral presentation
Novel Local Shape-Adaptive Gyrification Index with Application to Brain Development [DOI] Ilwoo Lyu, Sun Hyung Kim, Jessica Bullins, John Gilmore, Martin Styner. Medical Image Computing and Computer Assisted Intervention (MICCAI) 2017, LNCS10433, 31-39, Quebec City, Quebec, Canada, 2017
Geodesic Distances to Landmarks for Dense Correspondence on Ensembles of Complex Shapes [DOI] [PMID:24579119] Manasi Datar, Ilwoo Lyu, Sun Hyung Kim, Joshua Cates, Martin Styner, Ross Whitaker. Medical Image Computing and Computer Assisted Intervention (MICCAI) 2013, LNCS8150, 19-26, Nagoya, Japan, 2013, oral presentation
Particle-Guided Image Registration [DOI] [PMID:24505762] Joohwi Lee, Ilwoo Lyu, Ipek Oguz, Martin Styner. Medical Image Computing and Computer Assisted Intervention (MICCAI) 2013, LNCS8151, 203-210, Nagoya, Japan, 2013
Group-Wise Cortical Correspondence via Sulcal Curve-Constrained Entropy Minimization [DOI] [PMID:24683983] Ilwoo Lyu, Sun Hyung Kim, Joon-Kyung Seong, Sang Wook Yoo, Alan Evans, Yundi Shi, Mar Sanchez, Marc Niethammer, Martin Styner. Information Processing in Medical Imaging (IPMI) 2013, LNCS7917, 364-375, Asilomar, California, USA, 2013, oral presentation with open-ended discussion
Refereed Conferences
Learning Subject-Specific Functional Parcellations from Cortical Surface Measures [DOI] Roza Bayrak, Ilwoo Lyu, Catie Chang. MICCAI Workshop on PRedictive Intelligence In MEdicine (PRIME) 2022, LNCS13564, 172-180, Singapore, 2022
Ultra-high-resolution Mapping of Cortical Layers 3T-Guided 7T MRI [DOI] Karthik Ramadass, Francois Rheault, Leon Cai, Lucas Remedios, Micah DArchangel, Ilwoo Lyu, Laura Barquero, Allen Newton, Laurie Cutting, Yuankai Huo, Bennett Landman. SPIE Medical Imaging 2022, SPIE12032, 120321G, San Diego, California, USA, 2022, oral presentation
Random Multi-Channel Image Synthesis for Multiplexed Immunofluorescence Imaging [DOI] [PMID:34993490] Shunxing Bao, Yucheng Tang, Ho Hin Lee, Riqiang Gao, Sophie Chiron, Ilwoo Lyu, Lori Coburn, Keith Wilson, Joseph Roland, Bennett Landman, Yuankai Huo. MICCAI Workshop on Computational Pathology (COMPAY) 2021, PMLR156, 1-11, Strasbourg, France, 2021
Establishing Surface Correspondence for Post-surgical Cortical Thickness Changes in Temporal Lobe Epilepsy [DOI] [PMID:34531630] Yue Liu, Dario Englot, Victoria Morgan, Warren Taylor, Ying Wei, Ipek Oguz, Bennett Landman, Ilwoo Lyu. SPIE Medical Imaging 2021, SPIE11596, 115960Y, Houston, Texas, USA, 2021, oral presentation
Validation of group-wise registration for surface-based functional MRI analysis [DOI] [PMID:34531631] Chang Yu, Yue Liu, Leon Cai, Cailey Kerley, Kaiwen Xu, Katherine Aboud, Warren Taylor, Hakmook Kang, Andrea Shafer, Lori Beason-Held, Susan Resnick, Bennett Landman, Ilwoo Lyu. SPIE Medical Imaging 2021, SPIE11596, 115960X, Houston, Texas, USA, 2021
Joint cortical surface and structural connectivity analysis of Alzheimer's Disease [DOI] [PMID:34354323] Leon Cai, Cailey Kerley, Chang Yu, Katherine Aboud, Lori Beason-Held, Andrea Shafer, Susan Resnick, Lori Jordan, Adam Anderson, Kurt Schilling, Ilwoo Lyu, Bennett Landman. SPIE Medical Imaging 2021, SPIE11596, 1159630, Houston, Texas, USA, 2021, oral presentation
Automatic Labeling of Cortical Sulci using Convolutional Neural Networks in a Developmental Cohort [DOI] [PMID:32547677] Lingyan Hao, Shunxing Bao, Yucheng Tang, Riqiang Gao, Prasanna Parvathaneni, Jacob Miller, Willa Voorhies, Jewelia Yao, Silvia Bunge, Kevin Weiner, Bennett Landman, Ilwoo Lyu. IEEE International Symposium on Biomedical Imaging (ISBI) 2020, IEEE, 412-415, Iowa City, Iowa, USA, 2020
Harmonizing 1.5T/3T Diffusion Weighted MRI through Development of Deep Learning Stabilized Microarchitecture Estimators [DOI] [PMID:32089583] Vishwesh Nath, Samuel Remedios, Prasanna Parvathaneni, Colin Hansen, Roza Bayrak, Camilo Bermudez, Justin Blaber, Karthik Ramadass, Kurt Schilling, Vaibhav Janve, Yurui Gao, Yuankai Huo, Ilwoo Lyu, Owen Williams, Susan Resnick, Lori Beason-Held, Baxter Rogers, Iwona Stepniewska, Adam Anderson, Bennett Landman. SPIE Medical Imaging 2019, SPIE10949, 109490O-1-109490O-12, San Diego, California, USA, 2019, oral presentation
Inter-Scanner Harmonization of High Angular Resolution DW-MRI using Null Space Deep Learning [DOI] Vishwesh Nath, Kurt Schilling, Prasanna Parvathaneni, Colin Hansen, Allison Hainline, Camilo Bermudez, Samuel Remedios, Justin Blaber, Ilwoo Lyu, Vaibhav Janve, Yurui Gao, Iwona Stepniewska, Baxter Rogers, Allen Newton, Taylor Davis, Jeff Luci, Adam Anderson, Bennett Landman. MICCAI Workshop on Computational Diffusion MRI (CDMRI) 2018, MATHVISUAL46, 193-201, Granada, Spain, 2018
Harmonization of White and Gray Matter Features in Diffusion Microarchitecture for Cross Sectional Studies [DOI] Prasanna Parvathaneni, Shunxing Bao, Allison Hainline, Yuankai Huo, Kurt Schilling, Hakmook Kang, Owen Williams, Neil Woodward, Susan Resnick, David Zald, Ilwoo Lyu, Bennett Landman. International Conference on Clinical and Medical Image Analysis (ICCMIA) 2018, LNCVB31, 21-29, Coimbatore, Tamilnadu, India, 2018
Fully Convolutional Neural Networks Improve Abdominal Organ Segmentation [DOI] [PMID:29887665] Meg Bobo, Shunxing Bao, Yuankai Huo, Yuang Yao, Jack Virostko, Andrew Plassard, Ilwoo Lyu, Albert Assad, Richard Abramson, Bennett Landman. SPIE Medical Imaging 2018, SPIE10574, 105742V-1-105742V-8, Houston, Texas, USA, 2018, best poster award
SHARD: Spherical Harmonic based Robust Outlier Detection for HARDI Methods [DOI] [PMID:29887661] Vishwesh Nath, Kurt Schilling, Allison Hainline, Prasanna Parvathaneni, Justin Blaber, Ilwoo Lyu, Adam Anderson, Hakmook Kang, Allen Newton, Baxter Rogers, Bennett Landman. SPIE Medical Imaging 2018, SPIE10574, 105740X-1-105740X-11, Houston, Texas, USA, 2018, oral presentation
A Data Colocation Grid Framework for Big Data Medical Image Processing – Backend Design [DOI] [PMID:29887668] Shunxing Bao, Yuankai Huo, Prasanna Parvathaneni, Andrew Plassard, Camilo Bermudez, Yuang Yao, Ilwoo Lyu, Aniruddha Gokhale, Bennett Landman. SPIE Medical Imaging 2018, SPIE10579, 105790A-1-105790A-10, Houston, Texas, USA, 2018, oral presentation
Constructing Statistically Unbiased Cortical Surface Templates Using Feature-Space Covariance [DOI] [PMID:29887664] Prasanna Parvathaneni, Ilwoo Lyu, Yuankai Huo, Justin Blaber, Allison Hainline, Hakmook Kang, Neil Woodward, Bennett Landman. SPIE Medical Imaging 2018, SPIE10574, 1057406-1-1057406-9, Houston, Texas, USA, 2018, oral presentation
Sulcal Depth-based Cortical Shape Analysis in Normal Healthy Control and Schizophrenia Groups [DOI] [PMID:29887663] Ilwoo Lyu, Hakmook Kang, Neil Woodward, Bennett Landman. SPIE Medical Imaging 2018, SPIE10574, 1057402-1-1057402-8, Houston, Texas, USA, 2018, oral presentation
Group-wise Shape Correspondence of Variable and Complex Objects [DOI] Ilwoo Lyu, Jonathan Perdomo, Gabriel Yapuncich, Beatriz Paniagua, Doug Boyer, Martin Styner. SPIE Medical Imaging 2018, SPIE10574, 105742T-1-105742T-7, Houston, Texas, USA, 2018
Cortical Surface Shape Assessment via Sulcal/Gyral Curve-based Gyrification Index [DOI] Ilwoo Lyu, Sun Hyung Kim, Martin Styner. IEEE International Symposium on Biomedical Imaging (ISBI) 2016, IEEE, 221-224, Prague, Czech Republic, 2016, oral presentation, finalist for best student award
Automatic Sulcal Curve Extraction on the Human Cortical Surface [DOI] [PMID:26028801] Ilwoo Lyu, Sun Hyung Kim, Martin Styner. SPIE Medical Imaging 2015, SPIE9413, 94130P-1-94130P-7, Orlando, Florida, USA, 2015, oral presentation
Multi-atlas Segmentation with Particle-based Group-wise Image Registration [DOI] [PMID:25075158] Joohwi Lee, Ilwoo Lyu, Martin Styner. SPIE Medical Imaging 2014, SPIE9034, 903447-1-903447-8, San Diego, California, USA, 2014
Cortical Correspondence via Sulcal Curve-Constrained Spherical Registration with Application to Macaque Studies [DOI] [PMID:24357916] Ilwoo Lyu, Sun Hyung Kim, Joon-Kyung Seong, Sang Wook Yoo, Alan Evans, Yundi Shi, Mar Sanchez, Marc Niethammer, Martin Styner. SPIE Medical Imaging 2013, SPIE8669, 86692X-1-86692X-7, Orlando, Florida, USA, 2013
Multiple Atlases-based Joint Labeling of Human Cortical Sulcal Curves [DOI] Ilwoo Lyu, Gang Li, Min-Jeong Kim, Dinggang Shen. MICCAI Workshop on Medical Computer Vision (MCV) 2012, LNCS7766, 124-132, Nice, France, 2012

- Hide -

Teaching

Fall 2022: CSE471 Introduction to Computer Graphics, UNIST, Korea Instructor
Fall 2021: CSE472 Introduction to Computer Vision, UNIST, Korea Instructor
Fall 2021: CSE421 Introduction to Database Systems, UNIST, Korea Instructor
Spring 2021, Fall 2022: CSE613 3D Shape Analysis in Neuroimaging, UNIST, Korea Instructor
Fall 2020: CS8395 Open Source Programming for Medical Image Analysis - Surface-based Cortical Shape Analysis, Vanderbilt University, USA Guest Lecturer	Oct 2020
Fall 2019: CS8395 Open Source Programming for Medical Image Analysis - Cortical Surface Reconstruction and Shape Analysis, Vanderbilt University, USA Guest Lecturer	Oct 2019
Fall 2019: CS4262 Foundations of Machine Learning - Machine Learning for Brain Image Analysis, Vanderbilt University, USA Guest Lecturer	Sep 2019
Fall 2017, Fall 2019: SC3250 Scientific Computing - Introduction to Copmuter Vision with Applications, Vanderbilt University, USA Guest Lecturer	Sep 2017, Sep 2019
Summer 2019: Vanderbilt Data Science Institute Summer Research Program (DSI-SRP) , Vanderbilt University, USA Mentor	May 2019 - Jul 2019
Spring 2014: COMP915 Technical Communication in Computer Science, UNC, USA Trainee	Jan 2014 - May 2014
Fall 2010: CS300 Introduction to Algorithms, KAIST, Korea Teaching Assistant	Sep 2010 - Dec 2010
Fall 2009: CS202 Problem Solving, KAIST, Korea Teaching Assistant	Sep 2009 - Dec 2009
Tutoring Program for Freshman: JAVA language, KAIST, Korea Private Tutor	Feb 2008 - Dec 2008

Podium Talks

Hierarchical Spherical Deformation for Shape Correspondence, MICCAI 2018, Granada, Spain	Sep 2018
Sulcal Depth-based Cortical Shape Analysis in Normal Healthy Control and Schizophrenia Groups, SPIE Medical Imaging 2018, Houston, Texas, USA	Feb 2018
Cortical Surface Registration and Shape Analysis, VISE Summer Seminar 2017, Vanderbilt University, Nashville, Tennessee, USA	Jul 2017
Cortical Surface Shape Assessment via Sulcal/Gyral Curve-based Gyrification Index, ISBI 2016, Prague, Czech Republic	Apr 2016
Group-wise Cortical Correspondence via Sulcal Curve-Constrained Entropy Minimization, IPMI 2013, Asilomar, California, USA	Jun 2013

Software

The source codes in my publications are publicly available to the community for reproducible research. Many of them are also distributed as a software package imaged by Docker through my Docker repository or as Singularity images. In the Docker (or Singularity) environment, no package build/installation is required; everything is fully containerized in the Docker (Singularity) images. These tools can be run with a single command line after pulling the images from the Docker repository or Singularity distributions below. See more details about implementation, installation, usage, etc. at my GitHub profile or ShapeLab repo.

Containerized images (standalone applications)

BISCUIT: Brain Shape Computing Toolbox [Singularity]
SphericalLabeling: Automatic Labeling of Cortical Surface and Sulci [Singularity]
CMorph: Shape Analysis Tools for Cortical Morphometry [Docker] [Singularity]

Github repositories

Ilwoo Lyu

(류일우)

Book Chapters

Journal Articles

Top Computer Science Conferences

Refereed Conferences