Segmentation of leukocyte cells in bone marrow smears
Analyzing bone marrow is an important task for diagnosing diseases like certain types of leukemia and anemia. There are many different cell types in bone marrow. A certain ratio of these types is characteristic for a healthy human. Each deviation from that ratio is a significant indicator for diseases. Until now determining the ratio is done manually by an expert by counting and classifying the cells with a microscope. This is cumbersome and very time consuming. So there are efforts to automatize the cell counting. The most difficult step to achieve that is the automatic segmentation of leukocytes in bone marrow smears. Because the segmentation quality of existing algorithms is not good enough a new algorithm was developed in the scope of this paper. This new algorithm is robust concerning variations as color fluctuations in the bone marrow images. The evaluation of this algorithm was done by comparing the segmentation results with the results obtained by an existing algorithm. Therefore a set of 27 bone marrow images was segmented and compared against a manual annotation. The segmentation quality obtained by the state of the art algorithm was 0.4544 and the quality achieved by the novel algorithm was 0.645 on a scale from zero to one, zero representing only invalid segmentations and one representing only perfect segmentations.