Related Experiment Video
Updated: Sep 3, 2025
08:20
Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
Published on: October 27, 2023
1.6K
Detection of WBC, RBC, and Platelets in Blood Samples Using Deep Learning
1Department of Management Information System, College of Business Administration, Taif University, P.O Box 11099, Taif 21944, Saudi Arabia.
Biomed Research International
|July 25, 2022
Summary
This study introduces a deep learning model for automated blood cell detection in medical images. The model achieved high accuracy in counting white blood cells (100%), platelets (96%), and red blood cells (89%).
Area of Science:
- Computational pathology
- Medical diagnostics
- Artificial intelligence in healthcare
Background:
- Blood counts are crucial diagnostic tools but laboratory delivery faces challenges due to expensive, high-maintenance equipment.
- Automated cell detection offers a potential solution to improve accessibility and efficiency in blood analysis.
Purpose of the Study:
- To develop and evaluate a deep learning computational model for automatic detection and counting of blood cells in digital images.
- To assess the accuracy of the model in identifying white blood cells, red blood cells, and platelets.
Main Methods:
- Utilized object detection libraries to train a deep learning model specifically for blood cell identification in sample images.
- The model was trained and validated on a dataset of blood sample images.
Main Results:
- The deep learning model demonstrated high accuracy in cell counting: 100% for white blood cells, 96% for platelets, and 89% for red blood cells.
- The study successfully developed core components for automated blood count analysis.
Conclusions:
- Deep learning offers a viable and accurate alternative for automated blood cell detection, addressing limitations of traditional laboratory methods.
- Further research can expand on this model, particularly for classifying different white blood cell types, pending larger datasets.
