A novel white blood cells segmentation algorithm based on adaptive neutrosophic similarity score

• Published in: Health information science and systems 2017-12, Vol.6 (1), p.1-1, Article 1
• Main Authors: Shahin, A. I., Guo, Yanhui, Amin, K. M., Sharawi, Amr A.
• Format: Article
• Language: English
• Subjects: Bioinformatics; Computational Biology/Bioinformatics; Computer Science; Health Informatics; Information Systems and Communication Service; Leukocytes; Segmentation (Morphology); The Special Issue on Artificial Intelligence in Health and Medicine
• ISSN: 2047-2501; 2047-2501
• DOI: 10.1007/s13755-017-0038-5

Background White blood cells (WBCs) play a crucial role in the diagnosis of many diseases according to their numbers or morphology. The recent digital pathology equipments investigate and analyze the blood smear images automatically. The previous automated segmentation algorithms worked on healthy and non-healthy WBCs separately. Also, such algorithms had employed certain color components which leak adaptively with different datasets. Methods In this paper, a novel segmentation algorithm for WBCs in the blood smear images is proposed using multi-scale similarity measure based on the neutrosophic domain. We employ neutrosophic similarity score to measure the similarity between different color components of the blood smear image. Since we utilize different color components from different color spaces, we modify the neutrosphic score algorithm to be adaptive. Two different segmentation frameworks are proposed: one for the segmentation of nucleus, and the other for the cytoplasm of WBCs. Moreover, our proposed algorithm is applied to both healthy and non-healthy WBCs. in some cases, the single blood smear image gather between healthy and non-healthy WBCs which is considered in our proposed algorithm. Also, our segmentation algorithm is performed without any external morphological binary enhancement methods which may effect on the original shape of the WBC. Results Different public datasets with different resolutions were used in our experiments. We evaluate the system performance based on both qualitative and quantitative measurements. The quantitative results indicates high precision rates of the segmentation performance measurement A1 = 96.5% and A2 = 97.2% of the proposed method. The average segmentation performance results for different WBCs types reach to 97.6%. Conclusion In this paper, a method based on adaptive neutrosphic sets similarity score is proposed in order to detect WBCs from a blood smear microscopic image and segment its components (nucleus and the cytoplasm). The proposed segmentation algorithm can be utilized for fully-automated classification systems, such systems can be either for the healthy WBCs or even for non-healthy WBCs specially the leukemia cells.