Machine learning–enhanced digital microscopy for personalized assessment of red blood cell storage lesions
Vox Sanguinis · 2025
DOI: 10.1111/vox.70103 ↗Kurz gefasst
Fachartikel in der Zeitschrift Vox Sanguinis, 2025. Verfasst von Jiang Deng und 9 weiteren Autor:innen. Beteiligte Einrichtung: Academy of Military Medical Science, Beijing, People's Republic of China. Hauptthemen laut MEDLINE: Erythrocytes, Machine Learning, Microscopy, Blood Preservation. Die Arbeit nennt 41 Literaturangaben.
Abstract (Originalsprache)
Background and Objectives This study aims to develop a novel platform combining machine learning and microscope images for personalized assessment of red blood cell (RBC) storage lesions. RBCs undergo storage lesions, which adversely affect transfusion outcomes. Currently, there is no individualized assessment method for RBC aging applicable in clinical practice. Materials and Methods Blood smears and cytospin preparations from stored donor RBCs were digitized using whole‐slide scanning. Predictive models were developed and validated using classical machine learning, deep learning and ensemble learning techniques. These models were tested against various datasets and validated with flow cytometry. The training dataset comprised 550,870 images, the internal testing set included 192,562 images and the external testing set contained 350,793 images. Models such as k‐nearest neighbour, support vector machine, extra trees, DenseNet‐121, InceptionV3 and ResNet101 were employed, with ensemble learning leveraging InceptionV3 for enhanced performance.
Results
Classical machine learning models showed modest performance, whereas deep learning models (DenseNet‐121, InceptionV3, ResNet101) significantly outperformed them, achieving accuracy rates up to 0.86 on the internal testing set and 0.83 on the external testing set. The RBC morphology ensemble learning model (RBC‐MELM) further enhanced predictive capabilities, particularly in the blood smear and cytospin datasets. Comparative analyses with flow cytometry indicated that while flow cytometry detected accelerated aging under certain conditions, our machine learning approaches more effectively identified RBCs exhibiting accelerated aging.
Conclusion
The proposed method utilizing machine learning techniques and microscopic blood smear analysis provides a rapid, accurate and stable approach for the personalized assessment of RBC storage lesions.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Academy of Military Medical Science, Beijing, People's Republic of China.
- Department of Transfusion, The Fifth Medical Center of PLA General Hospital, Beijing, People's Republic of China.
- College of Biotechnology, Tianjin University of Science & Technology, Tianjin, People's Republic of China.
- Department of Transfusion, The Seventh Medical Center of PLA General Hospital, Beijing, People's Republic of China.
ORCID-Profile: Jiang Deng, Yanyu Zhang
Zitieren
APA
Deng, J., Zhuo, H., Wang, C., Zhao, N., Lv, L., Ma, P., Wu, T., Luo, Q., Zhang, K., & Zhang, Y. (2025). Machine learning–enhanced digital microscopy for personalized assessment of red blood cell storage lesions. Vox Sanguinis. https://doi.org/10.1111/vox.70103
Vancouver
Deng J, Zhuo H, Wang C, Zhao N, Lv L, Ma P, et al. Machine learning–enhanced digital microscopy for personalized assessment of red blood cell storage lesions. Vox Sanguinis. 2025. doi:10.1111/vox.70103
BibTeX
@article{Deng2025,
author = {Deng, Jiang and Zhuo, Hailong and Wang, Chaojie and Zhao, Ning and Lv, Liping and Ma, Ping and Wu, Tao and Luo, Qun and Zhang, Ke and Zhang, Yanyu},
title = {Machine learning–enhanced digital microscopy for personalized assessment of red blood cell storage lesions},
journal = {Vox Sanguinis},
year = {2025},
doi = {10.1111/vox.70103}
}
EUVIMED