Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Flow Cytometry01:23

Flow Cytometry

13.9K
The development of flow cytometry techniques began in 1934 with initial attempts by Andrew Moldavan, a bacteriologist who counted the cells in a flowing capillary system. Moldavan pumped cells through a capillary tube focused under a microscope for visualization. The invention of photometry allowed the measurement of differentially-stained cells, and Louis Kamentsky developed the first multiparameter flow cytometer in 1965 to identify and count the cancer cells in cervical tissue specimens.
In...
13.9K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

SHIELD: A weakly supervised graph attention neural network for decoding disease-relevant cell-cell interactions.

Patterns (New York, N.Y.)·2026
Same author

Cutaneous embryology: Physiological basis and clinical implications.

Journal of the European Academy of Dermatology and Venereology : JEADV·2026
Same author

Modern serum proteomics in precision medicine: Toward disease stratification and predictive, proactive treatment strategies.

The Journal of investigative dermatology·2026
Same author

Late syphilis presenting with extensive granulomatous cutaneous and pulmonary involvement.

IDCases·2026
Same author

Screen for Tissue-Specific Markers of Drug-Induced Phospholipidosis Using Mass Spectrometry Imaging.

Journal of the American Society for Mass Spectrometry·2026
Same author

Pathogenesis of cutaneous T-cell lymphoma: Malignant inflammation, immune reprogramming, and microenvironmental drivers.

The Journal of investigative dermatology·2026

Related Experiment Video

Updated: Sep 25, 2025

Label-Free Identification of Lymphocyte Subtypes Using Three-Dimensional Quantitative Phase Imaging and Machine Learning
08:58

Label-Free Identification of Lymphocyte Subtypes Using Three-Dimensional Quantitative Phase Imaging and Machine Learning

Published on: November 19, 2018

12.7K

A weakly supervised deep learning approach for label-free imaging flow-cytometry-based blood diagnostics.

Corin F Otesteanu1, Martina Ugrinic2, Gregor Holzner2

  • 1Institute for Molecular Systems Biology, ETH Zurich, Zurich, Switzerland.

Cell Reports Methods
|April 27, 2022
PubMed
Summary

A new deep learning method, iCellCnn, enables label-free diagnosis of hematological diseases using imaging flow cytometry (IFC). This weakly supervised approach achieved 100% accuracy in identifying Sézary syndrome (SS) from T-cell images.

Keywords:
Sézary syndromecancer cell imagingdeep learninghigh-throughput imagingimage flow cytometrymachine learningperipheral blood mononuclear samplesweakly supervised learning

More Related Videos

Two Flow Cytometric Approaches of NKG2D Ligand Surface Detection to Distinguish Stem Cells from Bulk Subpopulations in Acute Myeloid Leukemia
05:24

Two Flow Cytometric Approaches of NKG2D Ligand Surface Detection to Distinguish Stem Cells from Bulk Subpopulations in Acute Myeloid Leukemia

Published on: February 21, 2021

4.3K
Intracellular Phosphoflow Cytometry of Acute Myeloid Leukemia Patient-Derived Xenotransplants
07:38

Intracellular Phosphoflow Cytometry of Acute Myeloid Leukemia Patient-Derived Xenotransplants

Published on: June 6, 2025

292

Related Experiment Videos

Last Updated: Sep 25, 2025

Label-Free Identification of Lymphocyte Subtypes Using Three-Dimensional Quantitative Phase Imaging and Machine Learning
08:58

Label-Free Identification of Lymphocyte Subtypes Using Three-Dimensional Quantitative Phase Imaging and Machine Learning

Published on: November 19, 2018

12.7K
Two Flow Cytometric Approaches of NKG2D Ligand Surface Detection to Distinguish Stem Cells from Bulk Subpopulations in Acute Myeloid Leukemia
05:24

Two Flow Cytometric Approaches of NKG2D Ligand Surface Detection to Distinguish Stem Cells from Bulk Subpopulations in Acute Myeloid Leukemia

Published on: February 21, 2021

4.3K
Intracellular Phosphoflow Cytometry of Acute Myeloid Leukemia Patient-Derived Xenotransplants
07:38

Intracellular Phosphoflow Cytometry of Acute Myeloid Leukemia Patient-Derived Xenotransplants

Published on: June 6, 2025

292

Area of Science:

  • Hematology
  • Computational Biology
  • Medical Diagnostics

Background:

  • Machine learning (ML) in imaging flow cytometry (IFC) shows promise for diagnosing hematological diseases.
  • Clinical application of ML in IFC is hindered by the need for manually labeled single-cell images.
  • Weakly supervised learning offers a potential solution to overcome data labeling limitations.

Purpose of the Study:

  • To introduce iCellCnn, a weakly supervised deep learning model for label-free IFC-based blood diagnostics.
  • To demonstrate the efficacy of iCellCnn in diagnosing Sézary syndrome (SS) using bright-field IFC images.
  • To explore the broader potential of weakly supervised approaches for data-driven disease diagnosis with unknown morphological features.

Main Methods:

  • Development of iCellCnn, a deep learning algorithm utilizing weakly supervised learning.
  • Application of iCellCnn to analyze bright-field IFC images of T-cells from peripheral blood mononuclear cell specimens.
  • Classification of T-cells to differentiate between healthy donors and SS patients.

Main Results:

  • iCellCnn achieved 100% classification accuracy in distinguishing Sézary syndrome (SS) from healthy controls.
  • The model successfully diagnosed SS using only bright-field IFC images, without requiring specific labels.
  • The study utilized a small cohort: four healthy donors and five SS patients.

Conclusions:

  • Weakly supervised deep learning, exemplified by iCellCnn, can overcome data limitations in IFC-based diagnostics.
  • iCellCnn demonstrates a viable, label-free approach for diagnosing hematological conditions like SS.
  • This methodology holds potential for discovering and diagnosing diseases with previously unrecognized morphological characteristics through automated analysis.