ILIlwoo Lyu

Ilwoo Lyu

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Ilwoo Lyu has a total of 143 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Shape-Adaptive Guidance Signal for Interactive Cortical Sulcal Labeling

    by Jiwon Son, Ethan H. Willbrand, Benjamin J. Parker, Kevin S. Weiner, Ilwoo Lyu

  • SPHARM-Mamba: Rotation-Invariant Multiscale Modeling for Brain Age Prediction

    by Junho Choi, Mingyu Joo, Jiwon Son, Won Hwa Kim, Ilwoo Lyu

  • Sulcus-Aware Hippocampal Surface Modeling with Training-Time Sulcus-Guided Learning

    by Yuyeon Kim, Banseok Kim, Jiwon Son, Mingyu Joo, Kangmin Kim, Minji Ha, Minah Kim, Ilwoo Lyu

  • Isotropic spherical region enlargement and background contraction for sulcal labeling

    by Seunghwan Lee, Jiwon Son, Seungeun Lee, Ethan H. Willbrand, Benjamin J. Parker, Silvia A. Bunge, Kevin S. Weiner, Ilwoo Lyu

  • Open Access

    Long-term effects of preterm birth on cortical folding trajectories in early childhood

    by Yong Hun Jang, Jong Min Kim, Bong Gun Lee, Jeong-Kyu Hoh, Gang Yi Lee, Hyun Ho Kim, Ilwoo Lyu, Hyun Ju Lee

    Cortical folding emerges in the late prenatal period and undergoes rapid reorganization during early childhood. However, the long-term impact of folding alterations associated with preterm birth remains unclear. Herein, we analysed the structural MRI data of 56 preterm children and 206 full-term peers aged 1–7 years. We derived cortical metrics from the reconstructed cortical surfaces using a vertex-wise computation framework to characterize regional folding patterns. We then conducted a combined analysis of the local gyrification index and sulcal depth to explain folding patterns in the preterm brain. Compared with their full-term peers, preterm children exhibited a region-specific impairment pattern characterized by a significantly reduced local gyrification index and sulcal depth in the bilateral superior temporal gyrus and left superior frontal gyrus (P < 0.05). Notably, the sulcal depth in the superior temporal cortex showed significant differences between preterm and full-term children in its association with neurodevelopmental outcomes (P < 0.05), indicating an atypical structure–function relationship in preterm children. The local gyrification index was significantly reduced in the right isthmus cingulate and posterior cingulate gyri (P < 0.05), reflecting a simplified gyral configuration. The study findings suggest several folding patterns that capture diverse mechanisms of morphogenetic disruption, indicating that preterm birth induces persistent region-specific impairments in cortical folding that may affect neurodevelopmental domains. These folding-sensitive markers provide critical insights into the development of targeted interventions to optimize long-term neurodevelopmental outcomes.

  • Open Access

    Local gyrification index and sulcal depth as imaging markers of cognitive decline in Alzheimer’s disease

    by Yongsik Sim, Changmin Seo, Young-Gun Lee, Byoung Seok Ye, Ilwoo Lyu, Beomseok Sohn

    Purpose: To investigate the correlation between cortical thickness (CT), sulcal depth (SD), local gyrification index (LGI), and cognitive scores in patients with Alzheimer’s disease (AD).Methods: A total of 200 patients with AD from 2014 to 2021 were included, confirmed by 18F-florbetaben-positron emission tomography, and having a Clinical Dementia Rating score of 0.5 or 1. Demographic and clinical data were collected, and cognitive function was assessed through the Mini-Mental State Examination (MMSE) and Seoul Neuropsychological Screening Battery (SNSB)-II, with specific z-scores used for multiple divisional cognitive functions. CT, SD, and LGI were extracted from the 3D T1-weighted images acquired with 3-T MRI scanners. General linear models were used to examine associations between cortical features and cognitive scores, controlling for age, sex, and years of education. Cluster-level significance was determined using a family-wise error (FWE)–corrected threshold of p < 0.05, with a cluster-forming height threshold of uncorrected p < 0.01.Results: The analysis included patients with a mean age of 73.7 years and an average MMSE score of 23.8. The cortical shape features of multiple brain regions showed significant correlations with the MMSE score after adjusting for age, sex, and years of education. Among those, SD and LGI in the parahippocampal and fusiform gyri had positive correlations with MMSE. For executive function, SD showed correlations in the left inferior frontal and orbitofrontal gyrus. Regarding language function, CT was associated with regions such as the superior temporal gyrus, while SD demonstrated correlations with the left supramarginal gyrus.Conclusion: The results indicate that certain changes in cortical shape features are associated with particular cognitive function scores. Surface-based morphometric features of SD and LGI provided complementary results to CT analyses. Region-specific changes in SD and LGI could be useful imaging markers to predict cognitive decline in AD patients.


  • SPHARM-Reg: Unsupervised Cortical Surface Registration Using Spherical Harmonics

    by Seungeun Lee, Seunghwan Lee, Sunghwa Ryu, Ilwoo Lyu

    We present a novel learning-based spherical registration method, called SPHARM-Reg, tailored for establishing cortical shape correspondence. SPHARM-Reg aims to reduce warp distortion that can introduce biases in downstream shape analyses. To achieve this, we tackle two critical challenges: (1) joint rigid and non-rigid alignments and (2) rotation-preserving smoothing. Conventional approaches perform rigid alignment only once before a non-rigid alignment. The resulting rotation is potentially sub-optimal, and the subsequent non-rigid alignment may introduce unnecessary distortion. In addition, common velocity encoding schemes on the unit sphere often fail to preserve the rotation component after spatial smoothing of velocity. To address these issues, we propose a diffeomorphic framework that integrates spherical harmonic decomposition of the velocity field with a novel velocity encoding scheme. SPHARM-Reg optimizes harmonic components of the velocity field, enabling joint adjustments for both rigid and non-rigid alignments. Furthermore, the proposed encoding scheme using spherical functions encourages consistent smoothing that preserves the rotation component. In the experiments, we validate SPHARM-Reg on healthy adult datasets. SPHARM-Reg achieves a substantial reduction in warp distortion while maintaining a high level of registration accuracy compared to existing methods. In the clinical analysis, we show that the extent of warp distortion significantly impacts statistical significance.


  • Leveraging Input-Level Feature Deformation With Guided-Attention for Sulcal Labeling

    by Seungeun Lee, Seunghwan Lee, Ethan H. Willbrand, Benjamin J. Parker, Silvia A. Bunge, Kevin S. Weiner, Ilwoo Lyu

    The identification of cortical sulci is key for understanding functional and structural development of the cortex. While large, consistent sulci (or primary/secondary sulci) receive significant attention in most studies, the exploration of smaller and more variable sulci (or putative tertiary sulci) remains relatively under-investigated. Despite its importance, automatic labeling of cortical sulci is challenging due to (1) the presence of substantial anatomical variability, (2) the relatively small size of the regions of interest (ROIs) compared to unlabeled regions, and (3) the scarcity of annotated labels. In this paper, we propose a novel end-to-end learning framework using a spherical convolutional neural network (CNN). Specifically, the proposed method learns to effectively warp geometric features in a direction that facilitates the labeling of sulci while mitigating the impact of anatomical variability. Moreover, we introduce a guided-attention mechanism that takes into account the extent of deformation induced by the learned warping. This extracts discriminative features that emphasize sulcal ROIs, while suppressing irrelevant information of unlabeled regions. In the experiments, we evaluate the proposed method on 8 sulci of the posterior medial cortex. Our method outperforms existing methods particularly in the putative tertiary sulci. The code is publicly available at https://github.com/Shape-Lab/DSPHARM-Net.