3D Swin Transformer With Multi‐Scale Dilated Convolution for White Blood Cell Hyperspectral Image Classification
Journal of Biophotonics · 2026-05 · 19 (5)
DOI: 10.1002/jbio.70280 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Biophotonics, online erschienen am 19.05.2026. Verfasst von Yushi Yang und 5 weiteren Autor:innen. Beteiligte Einrichtung: College of Optoelectronic Engineering, Changchun University of Science and Technology, Changchun, China. Hauptthemen laut MEDLINE: Leukocytes, Hyperspectral Imaging, Imaging, Three-Dimensional. Die Arbeit nennt 31 Literaturangaben. Gefördert von: Foundation for Innovative Research Groups of the National Natural Science Foundation of China, National Natural Science Foundation of China.
Abstract (Originalsprache)
White blood cell (WBC) classification plays a crucial role in clinical diagnosis. However, traditional microscopic examination and existing deep learning methods primarily focus on spatial structures, resulting in the insufficient utilization of spectral information. In this study, we apply hyperspectral imaging technology and propose a 3D Swin Transformer network (SwinMDC) based on multi‐scale dilated convolutions for WBC hyperspectral image classification. The network employs a 3D multi‐scale dilated convolution feature extractor as its initial embedding layer, thereby enhancing low‐level representations and alleviating receptive field limitations. By integrating a 3D window‐based attention mechanism, the network constructs a hierarchical Transformer encoder to capture long‐range dependencies. On a three‐class white blood cell microscopic hyperspectral dataset, SwinMDC achieved an overall classification accuracy of 99.07%, demonstrating its potential value for clinical white blood cell analysis.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- College of Optoelectronic Engineering, Changchun University of Science and Technology, Changchun, China.
- Zhongshan Institute, Changchun University of Science and Technology, Zhongshan, China.
- Chaonan Hospital, Zhujiang Hospital of Southern Medical University, Shantou, China.
ORCID-Profile: Yushi Yang, Danfei Huang
Förderung
- Foundation for Innovative Research Groups of the National Natural Science Foundation of China
- National Natural Science Foundation of China
Zitieren
APA
Yang, Y., Huang, D., Xie, Y., Qiu, L., Yan, J., & Liu, Z. (2026). 3D Swin Transformer With Multi‐Scale Dilated Convolution for White Blood Cell Hyperspectral Image Classification. Journal of Biophotonics, 19(5). https://doi.org/10.1002/jbio.70280
Vancouver
Yang Y, Huang D, Xie Y, Qiu L, Yan J, Liu Z. 3D Swin Transformer With Multi‐Scale Dilated Convolution for White Blood Cell Hyperspectral Image Classification. Journal of Biophotonics. 2026;19(5). doi:10.1002/jbio.70280
BibTeX
@article{Yang2026,
author = {Yang, Yushi and Huang, Danfei and Xie, Yi and Qiu, Lijia and Yan, Jiaxuan and Liu, Ziyang},
title = {3D Swin Transformer With Multi‐Scale Dilated Convolution for White Blood Cell Hyperspectral Image Classification},
journal = {Journal of Biophotonics},
year = {2026},
volume = {19},
number = {5},
doi = {10.1002/jbio.70280}
}
EUVIMED