EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Artificial Intelligence-Driven Morphology-Based Enrichment of Malignant Cells from Body Fluid

Anastasia Mavropoulos, Chassidy Johnson, Vivian Lu, Jordan Nieto, Emilie C Schneider, Kiran Saini, Michael L Phelan, Linda X Hsie, Maggie J Wang, Janifer Cruz, Jeanette Mei, Julie J Kim und 11 weitere

Modern Pathology · 2023-08 · 36 (8) · 100195

DOI: 10.1016/j.modpat.2023.100195 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Modern Pathology, 2023-08. Verfasst von Anastasia Mavropoulos und 22 weiteren Autor:innen. Beteiligte Einrichtung: Deepcell, Inc, Menlo Park, California. Hauptthemen laut MEDLINE: Pleural Effusion, Malignant, Body Fluids, Carcinoma. Die Arbeit wurde bisher 34-mal zitiert (Crossref) und nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: University of California, Los Angeles.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Cell morphology is a fundamental feature used to evaluate patient specimens in pathologic analysis. However, traditional cytopathology analysis of patient effusion samples is limited by low tumor cell abundance coupled with the high background of nonmalignant cells, restricting the ability of downstream molecular and functional analyses to identify actionable therapeutic targets. We applied the Deepcell platform that combines microfluidic sorting, brightfield imaging, and real-time deep learning interpretations based on multidimensional morphology to enrich carcinoma cells from malignant effusions without cell staining or labels. Carcinoma cell enrichment was validated with whole genome sequencing and targeted mutation analysis, which showed a higher sensitivity for detection of tumor fractions and critical somatic variant mutations that were initially at low levels or undetectable in presort patient samples. Our study demonstrates the feasibility and added value of supplementing traditional morphology-based cytology with deep learning, multidimensional morphology analysis, and microfluidic sorting.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Pleural Effusion, MalignantBody FluidsCarcinomaHumansArtificial Intelligence

Stichwörter der Autor:innen

carcinomacytologyeffusionenrichmentmachine learningmorphology

Autor:innen und Institutionen

  • Deepcell, Inc, Menlo Park, California.
  • Department of Pathology and Laboratory Medicine, University of California Los Angeles (UCLA), Los Angeles, California.
  • Department of Pathology and Laboratory Medicine, University of California Los Angeles (UCLA), Los Angeles, California. Electronic address: JRao@mednet.ucla.edu.

Förderung

  • University of California, Los Angeles

Zitieren

APA

Mavropoulos, A., Johnson, C., Lu, V., Nieto, J., Schneider, E. C., Saini, K., Phelan, M. L., Hsie, L. X., Wang, M. J., Cruz, J., Mei, J., Kim, J. J., Lian, Z., Li, N., Boutet, S. C., Wong-Thai, A. Y., Yu, W., Lu, Q. Y., Kim, T., …, & Rao, J. (2023). Artificial Intelligence-Driven Morphology-Based Enrichment of Malignant Cells from Body Fluid. Modern Pathology, 36(8), 100195. https://doi.org/10.1016/j.modpat.2023.100195

Vancouver

Mavropoulos A, Johnson C, Lu V, Nieto J, Schneider EC, Saini K, et al. Artificial Intelligence-Driven Morphology-Based Enrichment of Malignant Cells from Body Fluid. Modern Pathology. 2023;36(8):100195. doi:10.1016/j.modpat.2023.100195

BibTeX
@article{Mavropoulos2023,
  author = {Mavropoulos, Anastasia and Johnson, Chassidy and Lu, Vivian and Nieto, Jordan and Schneider, Emilie C and Saini, Kiran and Phelan, Michael L and Hsie, Linda X and Wang, Maggie J and Cruz, Janifer and Mei, Jeanette and Kim, Julie J and Lian, Zhouyang and Li, Nianzhen and Boutet, Stephane C and Wong-Thai, Amy Y and Yu, Weibo and Lu, Qing-Yi and Kim, Teresa and Geng, Yipeng and Masaeli, Maddison Mahdokht and Lee, Thomas D and Rao, Jianyu},
  title = {Artificial Intelligence-Driven Morphology-Based Enrichment of Malignant Cells from Body Fluid},
  journal = {Modern Pathology},
  year = {2023},
  volume = {36},
  number = {8},
  pages = {100195},
  doi = {10.1016/j.modpat.2023.100195}
}
Kostenlos starten →