THE RELATIVE counting and assessment of the blood cells in the bone marrow of patients are very informative in clinical practice. It is particularly important for patients suffering from leukemia in the observation of the development stage of the illness and the preparation of the treatment of patients. To achieve proper diagnosis of the disease, we have to recognize the cells at different stages of their development and calculate their relative quantity in the aspirated bone marrow. There are different cell lines in the bone marrow, the most important of which are the granulocytic and lymphocytic (white blood cells) and erythrocytic (red blood cells) series .
The blood cells in the human bone marrow are continuously developing, transforming themselves from one type to another within the same development line. In the development of the white blood cells, the specialists recognize the myeloblast, promyelocyte, myelocyte, metamyelocyte, band neutrophil, and segmented neutrophil. In the case of the erythrocytic line,three different stages are recognized:
1) basophilic erythroblast;
2) polychromatic erythroblast; and
3) pyknotic erythroblast.
In the lymphocyte line, we recognize the prolymphocyte and lymphocyte cells. The most difficult problem is the recognition between two neighboring cells in their development line since the cells are very similar and the border point between two neighbors is not well defined (even for specialists).
This project presents the application of a genetic algorithm (GA) and a support vector machine (SVM) to the recognition of blood cells based on the image of the bone marrow aspirate. The main task of the GA is the selection of the features used by the SVM in the final recognition and classification of cells. The automatic recognition system has been developed, and the results of its numerical verification are presented and discussed. They show that the application of the GA is a powerful tool for the selection of the diagnostic features, leading to a significant improvement of the accuracy of the whole system.
The blood cells in the human bone marrow are continuously developing, transforming themselves from one type to another within the same development line. In the development of the white blood cells, the specialists recognize the myeloblast, promyelocyte, myelocyte, metamyelocyte, band neutrophil, and segmented neutrophil. In the case of the erythrocytic line,three different stages are recognized:
1) basophilic erythroblast;
2) polychromatic erythroblast; and
3) pyknotic erythroblast.
In the lymphocyte line, we recognize the prolymphocyte and lymphocyte cells. The most difficult problem is the recognition between two neighboring cells in their development line since the cells are very similar and the border point between two neighbors is not well defined (even for specialists).
This project presents the application of a genetic algorithm (GA) and a support vector machine (SVM) to the recognition of blood cells based on the image of the bone marrow aspirate. The main task of the GA is the selection of the features used by the SVM in the final recognition and classification of cells. The automatic recognition system has been developed, and the results of its numerical verification are presented and discussed. They show that the application of the GA is a powerful tool for the selection of the diagnostic features, leading to a significant improvement of the accuracy of the whole system.
No comments:
Post a Comment