publications

2025

1. Test-Time Modality Generalization for Medical Image Segmentation

   Ju-Hyeon Nam, and Sang-Chul Lee

   arXiv preprint arXiv:2502.19671, 2025
2. Transgunet: Transformer meets graph-based skip connection for medical image segmentation

   Ju-Hyeon Nam, Nur Suriza Syazwany, and Sang-Chul Lee

   arXiv preprint arXiv:2502.09931, 2025

2024

1. Integrating multimodal contrastive learning with prototypical domain alignment for unsupervised domain adaptation of time series

   Seo-Hyeong Park, Nur Suriza Syazwany, Ju-Hyeon Nam, and Sang-Chul Lee

   Engineering Applications of Artificial Intelligence, 2024
2. Vizecgnet: Visual ECG Image Network for Cardiovascular Diseases Classification With Multi-Modal Training and Knowledge Distillation

   Ju-Hyeon Nam, Seo-Hyung Park, Su Jung Kim, and Sang-Chul Lee

   In 2024 IEEE International Conference on Image Processing (ICIP), 2024
3. FSDA: Frequency re-scaling in data augmentation for corruption-robust image classification

   Ju-Hyeon Nam, and Sang-Chul Lee

   Pattern Recognition, 2024
4. Modality-agnostic domain generalizable medical image segmentation by multi-frequency in multi-scale attention

   Ju-Hyeon Nam, Nur Suriza Syazwany, Su Jung Kim, and Sang-Chul Lee

   In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2024

   Abs DOI Bib HTML Video

   Generalizability in deep neural networks plays a pivotal role in medical image segmentation. However deep learning-based medical image analyses tend to overlook the importance of frequency variance which is critical element for achieving a model that is both modality-agnostic and domain-generalizable. Additionally various models fail to account for the potential information loss that can arise from multi-task learning under deep supervision a factor that can impair the model’s representation ability. To address these challenges we propose a Modality-agnostic Domain Generalizable Network (MADGNet) for medical image segmentation which comprises two key components: a Multi-Frequency in Multi-Scale Attention (MFMSA) block and Ensemble Sub-Decoding Module (E-SDM). The MFMSA block refines the process of spatial feature extraction particularly in capturing boundary features by incorporating multi-frequency and multi-scale features thereby offering informative cues for tissue outline and anatomical structures. Moreover we propose E-SDM to mitigate information loss in multi-task learning with deep supervision especially during substantial upsampling from low resolution. We evaluate the segmentation performance of MADGNet across six modalities and fifteen datasets. Through extensive experiments we demonstrate that MADGNet consistently outperforms state-of-the-art models across various modalities showcasing superior segmentation performance. This affirms MADGNet as a robust solution for medical image segmentation that excels in diverse imaging scenarios. Our MADGNet code is available in GitHub Link.

   @inproceedings{nam2024modality,
     title = {Modality-agnostic domain generalizable medical image segmentation by multi-frequency in multi-scale attention},
     author = {Nam, Ju-Hyeon and Syazwany, Nur Suriza and Kim, Su Jung and Lee, Sang-Chul},
     booktitle = {Proceedings of the IEEE/CVF conference on computer vision and pattern recognition},
     pages = {11480--11491},
     year = {2024},
     doi = {10.1109/CVPR52733.2024.01091},
   }

2023

1. M3fpolypsegnet: Segmentation network with multi-frequency feature fusion for polyp localization in colonoscopy images

   Ju-Hyeon Nam, Seo-Hyeong Park, Nur Suriza Syazwany, Yerim Jung, Yu-Han Im, and Sang-Chul Lee

   In 2023 IEEE International Conference on Image Processing (ICIP), 2023
2. Random image frequency aggregation dropout in image classification for deep convolutional neural networks

   Ju-Hyeon Nam, and Sang-Chul Lee

   Computer Vision and Image Understanding, 2023

2022

1. FBI-Net: Frequency-based image forgery localization via multitask learning with self-attention

   A-Rom Gu, Ju-Hyeon Nam, and Sang-Chul Lee

   IEEE Access, 2022

2021

1. MM-BiFPN: multi-modality fusion network with Bi-FPN for MRI brain tumor segmentation

   Nur Suriza Syazwany, Ju-Hyeon Nam, and Sang-Chul Lee

   IEEE Access, 2021
2. Frequency filtering for data augmentation in X-ray image classification

   Ju-Hyeon Nam, and Sang-Chul Lee

   In 2021 IEEE International Conference on Image Processing (ICIP), 2021