Related Experiment Video
Updated: Feb 4, 2026

In Vivo Imaging of Leishmania infantum-infected Hamsters by Gingival Inoculation of Axenic Amastigotes Expressing Luciferase
Published on: April 4, 2025
AIR-LEISH: A Dataset of Giemsa-Stained Microscopy Images for AI-based Leishmania amastigotes Detection
Rafeh Oualha1, Nesrine Fekih-Romdhane1, Donia Driss1,2
1Laboratory of Molecular Epidemiology and Experimental Pathology - LR16IPT04, Institut Pasteur de Tunis, Université de Tunis El Manar, Tunis, Tunisia.
A new dataset, AIR-LEISH, aids artificial intelligence (AI) in analyzing microscopic images of leishmaniases. This resource accelerates AI development for parasite detection, improving drug discovery and public health efforts.
Area of Science:
- Parasitology
- Medical Entomology
- Computational Biology
Background:
- Leishmaniases is a significant parasitic disease affecting millions globally, transmitted by sandflies.
- Microscopy is the standard for quantifying Leishmania parasite burden but is labor-intensive and requires expertise.
- Current AI applications for automating parasite detection are hindered by a lack of annotated datasets.
Purpose of the Study:
- To introduce AIR-LEISH, a novel, expertly annotated dataset for Leishmania amastigote detection.
- To facilitate the development of AI-driven tools for leishmaniases research and drug discovery.
- To enable automated classification, detection, and counting of Leishmania amastigotes in microscopic images.
Main Methods:
- Creation of AIR-LEISH: 180 Giemsa-stained microscopic images with annotations of 8,140 Leishmania amastigotes and 1,511 macrophages from two infection models.
- Annotation focused on enabling AI object detection and image segmentation tasks.
- Training and testing of YOLOv8 and U-Net architectures using the AIR-LEISH dataset.
Main Results:
- The AIR-LEISH dataset comprises 180 annotated images, detailing parasite and host cell counts.
- YOLOv8 and U-Net models showed promising performance in classifying, detecting, and counting Leishmania amastigotes.
- The dataset supports AI-based analysis for leishmaniases research.
Conclusions:
- AIR-LEISH addresses the critical need for annotated data in AI-driven leishmaniases research.
- The dataset and demonstrated AI model performance will accelerate the development of automated diagnostic and research tools.
- Availability of AIR-LEISH on Zenodo promotes collaboration for public health advancements in combating leishmaniases.
Related Concept Videos
Air-entraining Agents
Imaging Biological Samples with Optical Microscopy
In optical microscopy, the specimen to be viewed is placed on a glass slide and clipped on the stage...
Effects of Air-entrainment in Concrete
Measurement of Air Content in Concrete
The pressure method,...
Simple Staining Technique
Differential Staining Technique

