A Leukocytes count system from blood smear images: Segmentation and counting of white blood cells based on learning by sampling

Automated blood cell counting instruments are very important tools, daily used by haematologists and medical analysts to perform a complete blood count (CBC). The results of the CBC may be complex to interpret but could lead to important decisions regarding the patient medical treatment. The main focus of this research is oriented to a CBC technique, named white blood cell count (WBCC). Generally, the WBCC is performed by skilled medical operators on peripheral blood smears in order to make a correct count and to obtain useful information such as cell abnormalities or the physical status. The manual WBCC is associated with several challenges, in fact it is a time-consuming, labour intensive and expensive process. This paper introduces a reliable automated WBCC system based on image processing techniques. The main aims are to speed up and to improve the accuracy of the WBCC process. The proposed automated system introduces a new approach to segment white blood cells taking into account the knowledge acquired from a training set formed of the three main classes elements, the white blood cells, the red blood cells and the plasma present in a blood smear image. The segmented regions containing only the white blood cells are subjected to a further step in which the count is performed using the circular Hough transform exploiting the grey-level information. The method has been tested on three different public datasets, in order to highlight the accuracy of the segmentation approach with different colour images and illumination conditions. The experimental results obtained on these datasets demonstrate that the proposed method is very accurate and robust achieving an accuracy of at least 99.2 % in white blood cells counting.