Connected Component based Medical Image Segmentation

Abstract: Medical image segmentation is a difficult problem due to the fact that these images commonly have poor contrast and missing details due to different types of noise and mostly medical images are fuzzy in nature, and segmenting regions based intensity is the most challenging task. Here region growing algorithm is used for segmentation in which selection of seed is important for that connected component is used. Our aim is to study anatomical structure, identify the region of interest, measure abnormality and help doctors in planning for early diagnosis. Connected component labelling works by scanning an image, pixel-by-pixel in order to identify connected pixel regions.\Blood Cell images for segmentation are taken. Leukaemia is a type of blood cancer, and if it is detected late, it will result in death. Leukaemia occurs when a lot of abnormal white blood cells produced by bone marrow. The existence of abnormal blood can be detected when the blood sample is taken and examined by haematologists. Microscopic images will be inspected visually by haematologists and the process is time consuming and tiring. Main objective of analysing through images is to gather information, detection of diseases, diagnosis diseases, control and therapy, monitoring and evaluation. At the end different parameters are calculated from quality metrics to define the accuracy of the algorithm.

Keywords: Leukemia, CLAHE, Connected Component, Region Growing Algorithm