Computational microscopic imaging for malaria parasite detection: a systematic review.
D K Das1, R Mukherjee2, C Chakraborty1
1School of Medical Science & Technology, IIT Kharagpur, India.
Journal of Microscopy
|June 6, 2015
Summary
Accurate malaria diagnosis is crucial for treatment. This review explores computational methods for analyzing microscopic images to detect malaria parasites, improving accuracy and speed over manual methods.
Area of Science:
- Digital pathology
- Medical imaging
- Computational microscopy
Background:
- Malaria diagnosis relies on microscopic examination of blood smears, which is time-consuming and prone to errors.
- Automated detection of malaria parasites is needed to improve diagnostic speed and accuracy.
- Computational microscopic imaging offers a promising approach to address these challenges.
Purpose of the Study:
- To review advancements in computational methods for malaria parasite detection.
- To cover techniques for image enhancement, segmentation, feature extraction, and computer-aided classification.
- To highlight the potential of digital pathology in malaria diagnosis.
Main Methods:
- Review of literature on image processing techniques for malaria detection.
- Analysis of methods for erythrocyte segmentation and parasite identification.
- Exploration of computer-aided classification algorithms.
Main Results:
- Computational methods show potential for accurate and rapid malaria diagnosis.
- Image enhancement and segmentation techniques improve parasite visualization.
- Automated classification systems can reduce diagnostic errors.
Conclusions:
- Computational microscopy and digital pathology offer significant advantages over traditional methods for malaria diagnosis.
- Further development in automated systems can enhance global malaria control efforts.
- This review provides a comprehensive overview of current techniques and future directions.
