Services on Demand
Journal
Article
Indicators
- Cited by SciELO
- Access statistics
Related links
- Cited by Google
- Similars in SciELO
- Similars in Google
Share
Ingeniería
Print version ISSN 0121-750XOn-line version ISSN 2344-8393
Abstract
MEJIA F., Marcela and ALZATE M., Marco A.. Automatic classification of pathological shapes in human erythrocytes. ing. [online]. 2016, vol.21, n.1, pp.31-48. ISSN 0121-750X. https://doi.org/10.14483/udistrital.jour.reving.2016.1.a03.
Context: Classification of erythrocyte morphological changes is usually done by an expert through direct observation from the microscope based on qualitative criteria, leading to subjective diagnosis. Proposals to automate this process usually classified erythrocytes in normal or abnormal, without specifying the type of abnormality that indicates the presence of some disease. We develop a tool for diagnostic support that determines different pathological forms of erythrocytes using characteristics measured from the microscopic image. Method: We detect isolated erythrocytes using a segmentation processes based on color. Then we measure some differentiating features in each cell, including a new measure of central pallor. These features are presented to a neural network that labels the cell according to seven types of abnormality. Results: The resulting system achieves a high success rate (97.3%) compared to binary classifications found in the literature. The measure of central pallor is highly discriminant because it allows a perfect distinction between normocytes and spherocytes, when other morphological characteristics are very similar between them. Conclusions: Our contribution includes the classification of multiple types of erythrocytes and the proposal of a highly discriminating measure of the central pallor. We verified the usefulness of combining pre-processing techniques for extracting features and neural networks for classification in feature space. For future work, it would be desirable to have a greater number of images with statistically significant samples of other types of erythrocytes to verify the goodness of the proposed methodology to classify more cell types. Also, with a greater number of classified samples, different pattern classification techniques could be studied in order to evaluate, compare and select the most appropriate technique.
Keywords : medical image processing; peripheral blood smear; red blood cells.