@inproceedings{a89efec522a24faca6d6c18f8ba21b86,
title = "NDAS: Noise-Decomposed Abnormal Segmentation for Robust Medical Image Retrieval",
abstract = "This paper presents NDAS (Noise-Decomposed Abnormal Segmentation), an innovative framework for robust medical image retrieval and segmentation. By explicitly decomposing noise and abnormal features, NDAS enhances retrieval accuracy and segmentation precision. Experimental results on the BraTS 2019 dataset validate NDAS{\textquoteright}s superiority over CBMIR and SBMIR methods, achieving the highest Top-5 accuracy and Dice coefficient. This demonstrates its effectiveness in handling noise, isolating pathological regions, and retrieving diagnostically relevant medical images. NDAS offers a significant advancement in medical imaging analysis, emphasizing its potential for clinical applications requiring precision and reliability.",
keywords = "Abnormal Segmentation, Medical Image Retrieval, Noise Decomposition",
author = "Kim, \{Ju Chan\} and \{Van Nguyen\}, Pham and Le, \{Duc Tai\} and Hyunseung Choo",
note = "Publisher Copyright: {\textcopyright} 2025 IEEE.; 19th International Conference on Ubiquitous Information Management and Communication, IMCOM 2025 ; Conference date: 03-01-2025 Through 05-01-2025",
year = "2025",
doi = "10.1109/IMCOM64595.2025.10857580",
language = "English",
series = "Proceedings of the 2025 19th International Conference on Ubiquitous Information Management and Communication, IMCOM 2025",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
editor = "Sukhan Lee and Hyunseung Choo and Roslan Ismail",
booktitle = "Proceedings of the 2025 19th International Conference on Ubiquitous Information Management and Communication, IMCOM 2025",
}