EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Imaging Flow Cytometry and Convolutional Neural Network-Based Classification Enable Discrimination of Hematopoietic and Leukemic Stem Cells in Acute Myeloid Leukemia

Trine Engelbrecht Hybel iD, Sofie Hesselberg Jensen, Matthew A Rodrigues iD, Thomas Engelbrecht Hybel, Maya Nautrup Pedersen, Signe Håkansson Qvick, Marie Hairing Enemark, Marie Bill, Carina Agerbo Rosenberg iD, Maja Ludvigsen iD

International Journal of Molecular Sciences · 12.06.2024 · 25 (12) · 6465

DOI: 10.3390/ijms25126465 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Molecular Sciences, online erschienen am 12.06.2024. Verfasst von Trine Engelbrecht Hybel und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Hematology, Aarhus University Hospital, 8200 Aarhus N, Denmark. Hauptthemen laut MEDLINE: Leukemia, Myeloid, Acute, Flow Cytometry, Neural Networks, Computer, Hematopoietic Stem Cells. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 80 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Danish Cancer Society, Max Wørzner and wife Inger Wørzner's Foundation, Department of Clinical Medicine, Aarhus University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Acute myeloid leukemia (AML) is a heterogenous blood cancer with a dismal prognosis. It emanates from leukemic stem cells (LSCs) arising from the genetic transformation of hematopoietic stem cells (HSCs). LSCs hold prognostic value, but their molecular and immunophenotypic heterogeneity poses challenges: there is no single marker for identifying all LSCs across AML samples. We hypothesized that imaging flow cytometry (IFC) paired with artificial intelligence-driven image analysis could visually distinguish LSCs from HSCs based solely on morphology. Initially, a seven-color IFC panel was employed to immunophenotypically identify LSCs and HSCs in bone marrow samples from five AML patients and ten healthy donors, respectively. Next, we developed convolutional neural network (CNN) models for HSC-LSC discrimination using brightfield (BF), side scatter (SSC), and DNA images. Classification using only BF images achieved 86.96% accuracy, indicating significant morphological differences. Accuracy increased to 93.42% when combining BF with DNA images, highlighting differences in nuclear morphology, although DNA images alone were inadequate for accurate HSC-LSC discrimination. Model development using SSC images revealed minor granularity differences. Performance metrics varied substantially between AML patients, indicating considerable morphologic variations among LSCs. Overall, we demonstrate proof-of-concept results for accurate CNN-based HSC-LSC differentiation, instigating the development of a novel technique within AML monitoring.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Leukemia, Myeloid, AcuteFlow CytometryNeural Networks, ComputerHematopoietic Stem CellsNeoplastic Stem CellsHumansImmunophenotypingFemaleMaleImage Processing, Computer-AssistedMiddle Aged

Stichwörter der Autor:innen

acute myeloid leukemiaartificial intelligenceconvolutional neural networkdeep learninghematopoietic stem cellsimaging flow cytometryleukemic stem cells

Autor:innen und Institutionen

  • Department of Hematology, Aarhus University Hospital, 8200 Aarhus N, Denmark.
  • Department of Clinical Medicine, Aarhus University, 8200 Aarhus N, Denmark.
  • Amnis Flow Cytometry, Cytek Biosciences, Seattle, WA 98119, USA.

ORCID-Profile: Trine Engelbrecht Hybel, Matthew A Rodrigues, Carina Agerbo Rosenberg, Maja Ludvigsen

Förderung

  • Danish Cancer Society
  • Max Wørzner and wife Inger Wørzner's Foundation
  • Department of Clinical Medicine, Aarhus University
  • Dagmar Marshalls Fond
  • The Toyota Foundation
  • Eva and Henry Frænkel's Memorial Foundation
  • Poul and Ellen Hertz's Foundation
  • Aase og Ejnar Danielsens Fond

Zitieren

APA

Hybel, T. E., Jensen, S. H., Rodrigues, M. A., Hybel, T. E., Pedersen, M. N., Qvick, S. H., Enemark, M. H., Bill, M., Rosenberg, C. A., & Ludvigsen, M. (2024). Imaging Flow Cytometry and Convolutional Neural Network-Based Classification Enable Discrimination of Hematopoietic and Leukemic Stem Cells in Acute Myeloid Leukemia. International Journal of Molecular Sciences, 25(12), 6465. https://doi.org/10.3390/ijms25126465

Vancouver

Hybel TE, Jensen SH, Rodrigues MA, Hybel TE, Pedersen MN, Qvick SH, et al. Imaging Flow Cytometry and Convolutional Neural Network-Based Classification Enable Discrimination of Hematopoietic and Leukemic Stem Cells in Acute Myeloid Leukemia. International Journal of Molecular Sciences. 2024;25(12):6465. doi:10.3390/ijms25126465

BibTeX
@article{Hybel2024,
  author = {Hybel, Trine Engelbrecht and Jensen, Sofie Hesselberg and Rodrigues, Matthew A and Hybel, Thomas Engelbrecht and Pedersen, Maya Nautrup and Qvick, Signe Håkansson and Enemark, Marie Hairing and Bill, Marie and Rosenberg, Carina Agerbo and Ludvigsen, Maja},
  title = {Imaging Flow Cytometry and Convolutional Neural Network-Based Classification Enable Discrimination of Hematopoietic and Leukemic Stem Cells in Acute Myeloid Leukemia},
  journal = {International Journal of Molecular Sciences},
  year = {2024},
  volume = {25},
  number = {12},
  pages = {6465},
  doi = {10.3390/ijms25126465}
}
Kostenlos starten →