EUVIMEDEUVIMED entdecken
Crossref

Label‐Free Typing of Colorectal Cancer by Optical Time‐Stretch Imaging Flow Cytometry With Multi‐Instance Learning

Sini Pi, Liye Mei iD, Liang Tao, Sisi Mei, Zhaoyi Ye

Journal of Biophotonics · 2025

DOI: 10.1002/jbio.70026 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Biophotonics, 2025. Verfasst von Sini Pi und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Medicine, Wuhan City College, Wuhan, China. Hauptthemen laut MEDLINE: Colorectal Neoplasms, Flow Cytometry, Machine Learning, Optical Imaging. Die Arbeit nennt 42 Literaturangaben. Gefördert von: Science and Technology Research Project of Education Department of Hubei Province, Advanced Research Foundation of Wuhan City College, Hubei Province Young Science and Technology Talent Morning Hight Lift Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Colorectal cancer (CRC) is one of the most prevalent gastrointestinal malignancies, necessitating the study of cellular and molecular changes within the tumor microenvironment. While pathological image analysis remains the gold standard, its labor‐intensive nature limits its broad application. This study proposes a label‐free CRC typing approach using intelligent optical time‐stretch (OTS) imaging flow cytometry combined with multi‐instance learning. Specifically, we construct a high‐throughput cell image acquisition system by integrating OTS imaging with microfluidic cell focusing, capturing 363 931 cell images from 10 clinical samples. To address cell diversity and heterogeneity, we employ a multi‐instance learning framework, which incorporates a multi‐level attention mechanism to explore feature interactions at both channel and instance levels. Finally, we apply a majority voting mechanism to enable efficient label‐free CRC typing. Our method achieves an accuracy of 85.78% in distinguishing normal and cancerous cells, while encouraging CRC typing performance across all 10 clinical samples.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Colorectal NeoplasmsFlow CytometryMachine LearningOptical ImagingHumansTime FactorsImage Processing, Computer-Assisted

Stichwörter der Autor:innen

colorectal cancermulti‐instance learningmulti‐level attentionoptical time‐stretch imagingvoting mechanism

Autor:innen und Institutionen

  • School of Medicine, Wuhan City College, Wuhan, China.
  • School of Computer Science, Hubei University of Technology, Wuhan, China.
  • The Institute of Technological Sciences, Wuhan University, Wuhan, China.
  • People's Hospital of Anshun City Guizhou Province, Anshun, China.

ORCID-Profile: Liye Mei

Förderung

  • Science and Technology Research Project of Education Department of Hubei Province
  • Advanced Research Foundation of Wuhan City College
  • Hubei Province Young Science and Technology Talent Morning Hight Lift Project
  • Hubei Provincial Natural Science Foundation of China
  • Doctoral Starting Up Foundation of Hubei University of Technology

Zitieren

APA

Pi, S., Mei, L., Tao, L., Mei, S., & Ye, Z. (2025). Label‐Free Typing of Colorectal Cancer by Optical Time‐Stretch Imaging Flow Cytometry With Multi‐Instance Learning. Journal of Biophotonics. https://doi.org/10.1002/jbio.70026

Vancouver

Pi S, Mei L, Tao L, Mei S, Ye Z. Label‐Free Typing of Colorectal Cancer by Optical Time‐Stretch Imaging Flow Cytometry With Multi‐Instance Learning. Journal of Biophotonics. 2025. doi:10.1002/jbio.70026

BibTeX
@article{Pi2025,
  author = {Pi, Sini and Mei, Liye and Tao, Liang and Mei, Sisi and Ye, Zhaoyi},
  title = {Label‐Free Typing of Colorectal Cancer by Optical Time‐Stretch Imaging Flow Cytometry With Multi‐Instance Learning},
  journal = {Journal of Biophotonics},
  year = {2025},
  doi = {10.1002/jbio.70026}
}
Kostenlos starten →