Fast and robust segmentation of white blood cell images by self-supervised learning

• Main Authors: ZHENG, Xin, WANG, Yong, WANG, Guoyou, LIU, Jianguo
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2018
• Subjects: Cell segmentation; Self-supervised learning; Support vector machine; White blood cell; Automatic labeling of training data; Health Information Technology; Software Engineering
• Online Access: https://ink.library.smu.edu.sg/sis_research/5884; https://ink.library.smu.edu.sg/context/sis_research/article/6885/viewcontent/miron_2018___pv.pdf
• Institution: Singapore Management University

A fast and accurate white blood cell (WBC) segmentation remains a challenging task, as different WBCs vary significantly in color and shape due to cell type differences, staining technique variations and the adhesion between the WBC and red blood cells. In this paper, a self-supervised learning approach, consisting of unsupervised initial segmentation and supervised segmentation refinement, is presented. The first module extracts the overall foreground region from the cell image by K-means clustering, and then generates a coarse WBC region by touching-cell splitting based on concavity analysis. The second module further uses the coarse segmentation result of the first module as automatic labels to actively train a support vector machine (SVM) classifier. Then, the trained SVM classifier is further used to classify each pixel of the image and achieve a more accurate segmentation result. To improve its segmentation accuracy, median color features representing the topological structure and a new weak edge enhancement operator (WEEO) handling fuzzy boundary are introduced. To further reduce its time cost, an efficient cluster sampling strategy is also proposed. We tested the proposed approach with two blood cell image datasets obtained under various imaging and staining conditions. The experiment results show that our approach has a superior performance of accuracy and time cost on both datasets.