EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Peripheral Blood Leukocyte Detection Based on an Improved Detection Transformer Algorithm

Mingjing Li, Shu Fang, Xiaoli Wang, Shuang Chen, Lixia Cao, Jinye Han, Haijiao Yun

Sensors · 2023

DOI: 10.3390/s23167226 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, 2023. Verfasst von Mingjing Li und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Electronic Information Engineering, Changchun University, Changchun 130000, China. Hauptthemen laut MEDLINE: Leukocytes, Algorithms. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Jilin Provincial Department of Education, Jilin Provincial Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The combination of a blood cell analyzer and artificial microscopy to detect white blood cells is used in hospitals. Blood cell analyzers not only have large throughput, but they also cannot detect cell morphology; although artificial microscopy has high accuracy, it is inefficient and prone to missed detections. In view of the above problems, a method based on Fourier ptychographic microscopy (FPM) and deep learning to detect peripheral blood leukocytes is proposed in this paper. Firstly, high-resolution and wide-field microscopic images of human peripheral blood cells are obtained using the FPM system, and the cell image data are enhanced with DCGANs (deep convolution generative adversarial networks) to construct datasets for performance evaluation. Then, an improved DETR (detection transformer) algorithm is proposed to improve the detection accuracy of small white blood cell targets; that is, the residual module Conv Block in the feature extraction part of the DETR network is improved to reduce the problem of information loss caused by downsampling. Finally, CIOU (complete intersection over union) is introduced as the bounding box loss function, which avoids the problem that GIOU (generalized intersection over union) is difficult to optimize when the two boxes are far away and the convergence speed is faster. The experimental results show that the mAP of the improved DETR algorithm in the detection of human peripheral white blood cells is 0.936. In addition, this algorithm is compared with other convolutional neural networks in terms of average accuracy, parameters, and number of inference frames per second, which verifies the feasibility of this method in microscopic medical image detection.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

LeukocytesAlgorithmsHumansNeural Networks, ComputerElectric Power SuppliesHospitals

Stichwörter der Autor:innen

DETRFourier ptychographic microscopytarget detectionwhite blood cell

Autor:innen und Institutionen

  • School of Electronic Information Engineering, Changchun University, Changchun 130000, China.

Förderung

  • Jilin Provincial Department of Education
  • Jilin Provincial Natural Science Foundation of China

Zitieren

APA

Li, M., Fang, S., Wang, X., Chen, S., Cao, L., Han, J., & Yun, H. (2023). Peripheral Blood Leukocyte Detection Based on an Improved Detection Transformer Algorithm. Sensors. https://doi.org/10.3390/s23167226

Vancouver

Li M, Fang S, Wang X, Chen S, Cao L, Han J, et al. Peripheral Blood Leukocyte Detection Based on an Improved Detection Transformer Algorithm. Sensors. 2023. doi:10.3390/s23167226

BibTeX
@article{Li2023,
  author = {Li, Mingjing and Fang, Shu and Wang, Xiaoli and Chen, Shuang and Cao, Lixia and Han, Jinye and Yun, Haijiao},
  title = {Peripheral Blood Leukocyte Detection Based on an Improved Detection Transformer Algorithm},
  journal = {Sensors},
  year = {2023},
  doi = {10.3390/s23167226}
}
Kostenlos starten →