Leukocyte Segmentation using Saliency Map and Stepwise Region-merging

Abstract

ABSTRACT Leukocyte in blood smear image provides significant information to doctors for diagnosis of patient health status. Therefore, it is necessary step to separate leukocyte from blood smear image among various blood cells for early disease prediction. In this paper, we present a saliency map and stepwise region merging based leukocyte segmentation method. Since leukocyte region has salient color and texture, we create a saliency map using these feature map. Saliency map is used for sub-image separation. Then, clustering is performed on each sub-image using mean-shift. After mean-shift is applied, stepwise region-merging is applied to particle clusters to obtain final leukocyte nucleus. The experimental results show that our system can indeed improve segmentation performance compared to previous researches with average accuracy rate of 71%.Keywords:Saliency Map, Mean-shift, Stepwise Region-merging, Leukocyte Segmentation 1. 서 론 1) 혈액 세포 영상에서 백혈구의 비율은 환자의 건강상태를 파악하는데 중요한 정보를 제공하며, 이를 통해 백혈병과 같은 질병을 초기에 예측할 수 있다[1]. 혈액을 이용한 질병 예측을 위해 개발된 자동혈구 측정검사(Automatic Complete Bood Cell Count: ACBC) 방법은 임상검사실에서 시행하는 다빈도 혈액 검사의 하나로 각종 혈구 세포들의 수를 측정하여 질병 진단에 필요한 기본적인 정보를 제공한다. 일반