Improving blast segmentation of acute myelogenous leukaemia (AML) images using bright stretching technique

Abstract

Contrast enhancement and image segmentation techniques have fast becoming popular for computer vision and image processing area in the last few decades. In this paper, the combination between contrast enhancement and segmentation were used in order to obtain a fully segmented abnormal white blood cell (blast). The combinations of contrast enhancement that had been used were partial contrast and bright stretching techniques. The bright stretching technique enhanced the area of blast in acute leukaemia images to ease the segmentation process. The proposed segmentation technique based on HSI (Hue, Saturation, Intensity) colour space has successfully segmented the acute leukaemia images while preserving significant features. The combination between two contrast enhancements has good effect on improving the accuracy of blast segmentation. Hence, the resultant images would become useful to Hematologists for further analysis of acute leukaemia.