Search research articles

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

Transcriptomic Analysis Reveals Multilayer Regulation Underlying Development and Pregnancy in the Malayan Pangolin.

Animal genetics·2026

Same author

Cardiac echocardiographic analysis with multi-scale effective fusion module: a novel stroke prediction approach.

BMC medical imaging·2026

Same author

A lightweight GhostYOLO framework with GhostDynamic Module and multi-scale attention for thyroid nodule diagnosis.

Scientific reports·2026

Same author

A Multimodal Diagnostic Model for Breast Cancer Invasiveness Based on Ultrasound Imaging and Serum Biomarkers.

Medicina (Kaunas, Lithuania)·2025

Same author

Unveiling Novel Viral Diversity, Biogeography, and Host Networks in Wildlife Through High-Throughput Sequencing Data Mining.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2025

Same author

Dual-stage artificial intelligence-powered screening for accurate classification of thyroid nodules: enhancing fine needle aspiration biopsy precision.

Quantitative imaging in medicine and surgery·2025

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: Jul 14, 2025

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

Multiclass malaria parasite recognition based on transformer models and a generative adversarial network.

Dianhuan Tan¹, Xianghui Liang²

¹Department of Clinical Laboratory, Xiangya Hospital, Central South University, No.87 Xiangya Road, Kaifu District, Changsha, 410008, Hunan, China.

Scientific Reports

|October 10, 2023

Summary

Transformer models and generative adversarial networks enhance malaria diagnosis from blood smear images. Swin Transformer achieves high accuracy, while MobileViT offers efficient deployment on edge devices for precise malaria detection.

More Related Videos

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

Published on: May 10, 2024

Generating Genetically Modified Plasmodium berghei Sporozoites

Generating Genetically Modified Plasmodium berghei Sporozoites

Published on: May 5, 2023

Related Experiment Videos

Last Updated: Jul 14, 2025

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

Published on: May 10, 2024

Generating Genetically Modified Plasmodium berghei Sporozoites

Generating Genetically Modified Plasmodium berghei Sporozoites

Published on: May 5, 2023

Area of Science:

Medical diagnostics
Computer vision
Machine learning

Background:

Malaria remains a major global health threat, necessitating accurate and efficient diagnostic methods.
Microscopic examination of thin blood smears is a standard malaria diagnostic technique.
Transformer models show promise in image classification tasks due to their feature extraction capabilities.

Purpose of the Study:

To develop an effective framework using transformer models and generative adversarial networks for multi-class Plasmodium classification and malaria diagnosis.
To enhance the robustness of diagnostic models by generating extended training samples.
To achieve a balance between high accuracy and low resource consumption in malaria diagnosis.

Main Methods:

Utilized transformer models, specifically Swin Transformer and MobileViT, for image classification.
Employed a Generative Adversarial Network (GAN) to augment training data with synthetic cell images.
Compared the performance of transformer models against state-of-the-art methods on thin blood smear images.

Main Results:

Swin Transformer achieved superior detection performance with up to 99.8% accuracy.
MobileViT demonstrated lower memory usage and shorter inference times, suitable for edge devices.
Both models outperformed baseline architectures in precision, recall, F1-score, specificity, and FPR.

Conclusions:

Transformer-based models, augmented by GANs, offer an efficient and accurate approach to malaria diagnosis.
Swin Transformer provides high diagnostic accuracy, while MobileViT enables practical deployment on resource-constrained devices.
This framework assists healthcare professionals in precise malaria diagnosis and facilitates wider accessibility of diagnostic tools.