Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Jun 1, 2026

Automation of the Micronucleus Assay Using Imaging Flow Cytometry and Artificial Intelligence

Automation of the Micronucleus Assay Using Imaging Flow Cytometry and Artificial Intelligence

Published on: January 27, 2023

Automated leukemia detection from microscopic images using deep transfer learning with explainable AI-based analysis.

Md Ashikuzzaman¹, Mir Md Julhash¹, Md Feroz Ali²

¹Department of Electrical and Electronic Engineering, Pabna University of Science and Technology, Pabna, 6600, Bangladesh.

Scientific Reports

|May 30, 2026

Summary

Related Concept Videos

You might also read

Related Articles

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

Sort by

Same author

Adversarial vulnerability and robustness of deep learning models for panoramic dental X-ray segmentation.

Scientific reports·2026

Same author

Techno-economic optimization and sensitivity analysis of a hybrid renewable microgrid for local market electrification in developing countries.

Scientific reports·2026

Same author

Techno-Economic Assessment of a Hydrogen-Assisted Hybrid Renewable Microgrid with Fuel Cells for Off-Grid Electrification.

Global challenges (Hoboken, NJ)·2026

Same author

Breed-specific immune responses to Eimeria tenella infection in chickens of Bangladesh.

Veterinary immunology and immunopathology·2026

Same author

Sustainable removal of Acid Black 172 from wastewater using Lantana camara derived biochar insights from adsorption and statistical physics modeling.

Scientific reports·2026

Same author

Design and optimization of a climate-resilient hybrid renewable microgrid for rural electrification in flood-affected regions.

Scientific reports·2026

Same journal

Peripheral B-cell receptor repertoire predicts immune-related adverse events following immune checkpoint inhibitor therapy in advanced renal cell carcinoma.

Scientific reports·2026

Same journal

Effects of black soldier fly (Hermetia illucens L.) larvae zoocompost on the mineral element content of blue honeysuckle berries.

Scientific reports·2026

Same journal

Investigation on absorption refrigeration performance of R1243zf with imidazolium ionic liquid as the working pairs.

Scientific reports·2026

Same journal

DeepTriage-CN: integrating clinical text with vital signs for emergency department admission prediction in an aging population.

Scientific reports·2026

Same journal

Gold nanoparticles as dual-action antiviral agents: disruption of SARS-CoV-2 viral envelopes and RNA integrity.

Scientific reports·2026

Same journal

Comparison of capillary microsampling and venous blood for multi-pathogen serosurveillance.

Scientific reports·2026

See all related articles

This summary is machine-generated.

This study evaluated fourteen Convolutional Neural Network (CNN) models for automated leukemia detection from blood smear images. EfficientNetB1, EfficientNetB5, Xception, and ResNet50 achieved high accuracy, demonstrating potential for clinical use.

Area of Science:

Hematology
Medical Imaging
Artificial Intelligence

Background:

Leukemia diagnosis relies on timely and accurate methods, but traditional microscopy is slow and subjective.
Existing deep learning studies for leukemia detection often use limited models and lack interpretability.
There is a need for comprehensive evaluations of various deep learning architectures for automated leukemia diagnosis.

Purpose of the Study:

To conduct a comparative evaluation of fourteen pre-trained Convolutional Neural Network (CNN) architectures for automated leukemia detection.
To assess the performance of models like EfficientNet, Xception, Inception, DenseNet, ResNet, VGG, and MobileNet using microscopic blood smear images.
To integrate Explainable AI (XAI) techniques for enhanced transparency and clinical trust in automated diagnostic models.

Keywords:

Convolutional neural networks (CNNs)Deep learning Leukemia detection Microscopic image analysis Transfer learning

Related Experiment Videos

Last Updated: Jun 1, 2026

Automation of the Micronucleus Assay Using Imaging Flow Cytometry and Artificial Intelligence

Automation of the Micronucleus Assay Using Imaging Flow Cytometry and Artificial Intelligence

Published on: January 27, 2023

Main Methods:

Utilized a public Kaggle dataset of 10,700 labeled microscopic blood smear images.
Compared fourteen pre-trained CNN architectures, including EfficientNetB1/B3/B5, Xception, InceptionV3, InceptionResNetV2, DenseNet201, ResNet variants, VGG16/19, and MobileNet.
Employed stratified sampling for data splitting (70% train, 15% validation, 15% test) and repeated experiments ten times with different random seeds for statistical robustness.
Integrated Grad-CAM and LIME for explainability analysis.

Main Results:

EfficientNetB1, EfficientNetB5, Xception, and ResNet50 demonstrated high performance, achieving test accuracies up to 96%, recall up to 98%, F1-scores up to 97%, and AUC values up to 0.987.
These models showed excellent threshold-independent discriminative capability in classifying leukemia from blood smear images.
Explainable AI techniques provided insights into model decision-making, enhancing transparency.

Conclusions:

The study provides a comprehensive comparison of CNN architectures for automated leukemia detection, outperforming many existing methods.
Selected models show significant potential for clinical translation in early and accurate leukemia diagnosis.
Future work requires external validation on multi-center datasets to ensure generalizability across different imaging devices and clinical settings.