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

Classification of Leukocytes01:30

Classification of Leukocytes

4.9K
Leukocytes are classified into two groups based on the presence or absence of cytoplasmic granules. Granular leukocytes, which contain granules, belong to the myeloid lineage and are divided into three subtypes: neutrophils, eosinophils, and basophils. These cells are roughly spherical and characterized by the granules in their cytoplasm.
Neutrophils are the most abundant type of granular leukocytes, comprising 50-70% of all leukocytes. They feature small, evenly distributed granules and a...
4.9K
Flow Cytometry01:23

Flow Cytometry

15.6K
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...
15.6K

You might also read

Related Articles

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

Sort by
Same author

Understanding the Barriers to Translating Artificial Intelligence into the Clinical Laboratory.

European journal of internal medicine·2026
Same author

PhotIQA: A photoacoustic image data set with image quality ratings.

Scientific data·2026
Same author

Machine Diagnostics and Machine Phenotyping of Migraine: A HUNT Study.

Neurology·2026
Same author

Real-time CBCT reconstructions using Krylov solvers in repeated scanning procedures.

Physics in medicine and biology·2026
Same author

Hierarchical Multiscale Structure-Function Coupling for Brain Connectome Integration.

ArXiv·2026
Same author

Global Mind Project data in the United States: A comparison with national statistics.

International journal of population data science·2026
Same journal

Algorithm-hardware co-design of neuromorphic networks with dual memory pathways.

Nature machine intelligence·2026
Same journal

Plagiarism in the Age of Generative Artificial Intelligence: The advent of generative artificial intelligence (GenAI) tools is challenging the scientific community's understanding of the meaning and significance of plagiarism. A new definition of research misconduct is needed that specifically addresses the use of GenAI writing tools.

Nature machine intelligence·2026
Same journal

Platonic representation of foundation machine learning interatomic potentials.

Nature machine intelligence·2026
Same journal

Immunotherapy drug target identification using machine learning and patient-derived tumour explant validation.

Nature machine intelligence·2026
Same journal

A generative artificial intelligence approach for peptide antibiotic optimization.

Nature machine intelligence·2026
Same journal

LLMs displaying less cognitive bias are not necessarily better decision makers.

Nature machine intelligence·2026
See all related articles

Related Experiment Video

Updated: Jan 10, 2026

Automated Quantification of Hematopoietic Cell – Stromal Cell Interactions in Histological Images of Undecalcified Bone
09:31

Automated Quantification of Hematopoietic Cell – Stromal Cell Interactions in Histological Images of Undecalcified Bone

Published on: April 8, 2015

12.0K

Deep generative classification of blood cell morphology.

Simon Deltadahl1, Julian Gilbey1, Christine Van Laer2

  • 1Department of Applied Mathematics and Theoretical Physics, University of Cambridge, Cambridge, UK.

Nature Machine Intelligence
|November 24, 2025
PubMed
Summary
This summary is machine-generated.

CytoDiffusion, a new generative AI classifier, accurately analyzes blood cell morphology for diagnostics. It surpasses expert performance in anomaly detection and handles data variations effectively.

Keywords:
Biomedical engineeringComputational models

More Related Videos

Morphology-Based Distinction Between Healthy and Pathological Cells Utilizing Fourier Transforms and Self-Organizing Maps
08:59

Morphology-Based Distinction Between Healthy and Pathological Cells Utilizing Fourier Transforms and Self-Organizing Maps

Published on: October 28, 2018

7.5K
Discrimination and Characterization of Heterocellular Populations Using Quantitative Imaging Techniques
09:48

Discrimination and Characterization of Heterocellular Populations Using Quantitative Imaging Techniques

Published on: June 30, 2017

7.8K

Related Experiment Videos

Last Updated: Jan 10, 2026

Automated Quantification of Hematopoietic Cell – Stromal Cell Interactions in Histological Images of Undecalcified Bone
09:31

Automated Quantification of Hematopoietic Cell – Stromal Cell Interactions in Histological Images of Undecalcified Bone

Published on: April 8, 2015

12.0K
Morphology-Based Distinction Between Healthy and Pathological Cells Utilizing Fourier Transforms and Self-Organizing Maps
08:59

Morphology-Based Distinction Between Healthy and Pathological Cells Utilizing Fourier Transforms and Self-Organizing Maps

Published on: October 28, 2018

7.5K
Discrimination and Characterization of Heterocellular Populations Using Quantitative Imaging Techniques
09:48

Discrimination and Characterization of Heterocellular Populations Using Quantitative Imaging Techniques

Published on: June 30, 2017

7.8K

Area of Science:

  • Medical Diagnostics
  • Computational Pathology
  • Artificial Intelligence in Healthcare

Background:

  • Blood cell morphology assessment is vital for diagnosing diseases but is challenging for automated systems due to subtle variations and imaging factors.
  • Conventional machine learning models struggle with domain shifts, variability within cell types, and identifying rare cell variants, limiting their clinical use.
  • Accurate and robust automated analysis of blood cell morphology is needed to improve diagnostic efficiency and accuracy.

Purpose of the Study:

  • To introduce CytoDiffusion, a diffusion-based generative classifier for blood cell morphology analysis.
  • To demonstrate CytoDiffusion's capabilities in accurate classification, anomaly detection, and resistance to distributional shifts.
  • To establish a new benchmark for medical image analysis in haematology.

Main Methods:

  • Developed CytoDiffusion, a diffusion-based generative classifier modeling blood cell morphology distribution.
  • Evaluated CytoDiffusion against state-of-the-art discriminative models on anomaly detection, domain shift resistance, and low-data performance.
  • Assessed the clinical realism of generated synthetic blood cell images by expert haematologists.
  • Implemented counterfactual heat maps for enhanced model interpretability.

Main Results:

  • CytoDiffusion achieved superior performance in anomaly detection (AUC 0.990 vs 0.916) and resistance to domain shifts (85.4% vs 73.8% accuracy).
  • The model excelled in low-data regimes, achieving 96.2% balanced accuracy compared to 92.4% for discriminative models.
  • Generated synthetic blood cell images were indistinguishable from real ones by expert haematologists (accuracy 0.523).
  • CytoDiffusion demonstrated data efficiency, interpretability, and uncertainty quantification exceeding clinical experts.

Conclusions:

  • CytoDiffusion offers a powerful new approach for blood cell morphology analysis, surpassing current methods in accuracy and robustness.
  • The generative model's ability to accurately simulate blood cell morphology enhances diagnostic capabilities and provides interpretable insights.
  • CytoDiffusion sets a new standard for medical image analysis in haematology, paving the way for improved clinical diagnostic accuracy.