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 Experiment Videos

Automated bone marrow cell classification using ensemble learning: performance, generalization, and clinical

Shahid Mehmood1,2, Muhammad Zubair2, Sagheer Abbas3

  • 1Department of Computer Science, Bahria University, Lahore, Pakistan.

Frontiers in Medicine
|June 19, 2026
PubMed
Summary

Related Concept Videos

Classification of Leukocytes01:30

Classification of Leukocytes

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...
Classification of Bones01:18

Classification of Bones

The bones of the human skeletal system are of varied shapes, sizes, and functions. They can be classified based on their shape and function into four major classes: long bones, short bones, flat bones, and irregular bones. Some classifications include a fifth type, the sesamoid bones, as a separate class, whereas others categorize them under short bones.
Long and Short Bones
The appendicular skeleton, particularly the upper and lower limbs, is primarily made of long and short bones. The long...

You might also read

Related Articles

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

Sort by
Same author

Deep learning-based region merging with adaptive threshold optimization for building segmentation in remote sensing images.

PloS one·2026
Same author

Development of an energy consumption map for turning inconel 718 through coupled chip-morphology and material-deformation analysis.

Scientific reports·2026
Same author

Evaluating Modified Early Warning Score Compliance to Minimize Unnecessary Intensive Care Unit Admissions: A Descriptive Cross-Sectional Needs Assessment at a University Teaching Tertiary Care Centre to Inform Quality Improvement Implementation.

Journal of evaluation in clinical practice·2026
Same author

Incorporation of MXene into brushite cement: Effects on mechanical, physical, and biological properties.

Journal of applied biomaterials & functional materials·2026
Same author

Determinants of parent satisfaction and trust towards healthcare service environment in a dedicated club foot clinic.

Journal of pediatric orthopedics. Part B·2026
Same author

Development of chitosan-selenium nanoparticle modified brushite cement: A potential strategy for improved clinical performance in bone regeneration.

Bio-medical materials and engineering·2026
Same journal

Integrated analysis of the aqueous humor microbiome and lens capsule transcriptome in high myopia cataract: a pilot study.

Frontiers in medicine·2026
Same journal

Internal jugular vein catheterization and catheter insertion slipped into the cervical spinal canal: a special case report.

Frontiers in medicine·2026
Same journal

Prediction models for mortality in patients with acute on chronic liver failure: systematic review and critical appraisal.

Frontiers in medicine·2026
Same journal

Hypertension among Middle Eastern and North African adults residing in the United States: addressing equity in health research representation using the All of Us Research Program, 2000-2024.

Frontiers in medicine·2026
Same journal

Effects of problem-focused versus emotion-focused behavioral interventions on peptic ulcer recurrence: a 4-year retrospective cohort study.

Frontiers in medicine·2026
Same journal

Infections and CAR-T cells for the treatment of lymphoid malignancies: a narrative review.

Frontiers in medicine·2026
See all related articles
This summary is machine-generated.

This study presents an AI framework for accurate bone marrow cell classification, improving hematological disorder diagnosis. The ensemble model enhances performance and interpretability, supporting AI-assisted diagnostics.

Area of Science:

  • Hematology
  • Medical Imaging
  • Artificial Intelligence

Background:

  • Accurate bone marrow (BM) cell classification is crucial for diagnosing hematological disorders.
  • Automated classification faces challenges like morphological overlap, class imbalance, and imaging artifacts.
  • Deep learning models (CNNs) show promise but can lack generalization and robustness.

Purpose of the Study:

  • To develop an ensemble-learning framework using MobileNetV3 and ResNet18 for enhanced BM cell classification.
  • To improve feature extraction, classification performance, and interpretability while maintaining low computational cost.
  • To evaluate the framework's accuracy, efficiency, and reliability in supporting AI-assisted hematological diagnostics.

Main Methods:

  • An ensemble-learning framework combining MobileNetV3 and ResNet18 was developed.
Keywords:
bone marrow cell classificationdeep learningensemble learningexplainable AIhematological diagnosticsmedical image analysistransfer learning

Related Experiment Videos

  • Four ensemble strategies (Soft Voting, Bagging, Boosting, Stacking) were evaluated on a large dataset (>420,000 images, 21 classes).
  • Explainable AI (XAI) methods (Grad-CAM, LIME) were used for interpretability, with Decision Impact Ratio and Confidence Impact Ratio for reliability assessment.

    • Main Results:

    • The Boosting ensemble strategy achieved the highest classification accuracy at 96%.
    • External validation confirmed robust performance across independent datasets and varying imaging conditions.
    • The ensemble model surpassed individual models in accuracy and interpretability stability, with XAI confirming focus on relevant morphological features.

    Conclusions:

    • The MobileNetV3-ResNet18 ensemble framework offers accurate, efficient, and interpretable BM cell classification.
    • This approach can enhance diagnostic performance and explanation reliability for AI-assisted hematological diagnostics.
    • The framework has the potential to reduce diagnostic time and interobserver variability.