Related Experiment Video
Updated: Jan 10, 2026
08:20
Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
Published on: October 27, 2023
2.4K
Investigating blood cell images for enhanced hematologic disorder detection using multi-scale feature learning with a
Mutasim Al Sadig1, Jamal Alsamri2, Nouf Helal Alharbi3
1Department of Computer Science, College of Science, Majmaah University, 11952, Al Majmaah, Saudi Arabia.
Scientific Reports
|November 23, 2025
Summary
A new deep learning model accurately detects hematologic disorders from blood cell images. This hybrid approach achieves 99.67% accuracy, improving diagnosis for blood diseases.
Area of Science:
- Hematology
- Medical Imaging
- Artificial Intelligence
Background:
- Hematologic diseases affect blood components and bone marrow, leading to severe health issues.
- Accurate diagnosis of blood disorders relies on laboratory tests and expert analysis.
- Deep learning shows promise in enhancing the detection of hematologic disorders.
Purpose of the Study:
- To develop an accurate deep learning model for detecting and classifying hematologic disorders.
- To utilize microscopic blood cell images for automated diagnosis.
Main Methods:
- A Multi-Scale Feature Learning-Based Enhanced Hematologic Disorder Detection Using Hybrid Deep Classification Model (MSFLHDD-HDCM) was developed.
- Image pre-processing used a geometric mean filter for noise reduction and data standardization.
- Feature extraction employed inception modules, and classification utilized a hybrid CNN-BiGRU model.
Main Results:
- The MSFLHDD-HDCM method achieved a superior accuracy of 99.67% in detecting hematologic disorders.
- Experimental results demonstrated the model's effectiveness on a blood cell image dataset.
- The approach outperformed existing techniques in classification accuracy.
Conclusions:
- The MSFLHDD-HDCM model offers a highly accurate and efficient method for diagnosing hematologic disorders.
- Deep learning, particularly hybrid models, can significantly advance automated blood disorder detection.
- This approach has the potential to improve early diagnosis and treatment of blood diseases.
