Three-level Local Thresholding Berbasis Metode Otsu untuk Segmentasi Leukosit pada Citra Leukemia Limfoblastik Akut
DOI:
https://doi.org/10.24002/jbi.v7i1.483Abstract
Abstract. Segmentation of Acute Lymphoblastic Leukemia (ALL) images can be used to identify the presence of ALL disease. In this paper, three-level local thresholdings based on Otsu method is presented for leucocytes segmentation in ALL image. Firstly, a method based on Gram-Schmidt orthogonalization theory is applied to partition the input image into several sub-images. The proposed method extends Otsu’s bi-level thresholding to three-level thresholding method to find two local threshold values that maximize between-class variance. Using the two local threshold values and three-level local thresholding technique then segmenting each of sub-images into three regions, e.g. nucleus, cytoplasm, and background. To evaluate the performance of the proposed method, 32 peripheral blood smear images are used. The performance of the proposed method is compared with manually segmented ground truth using Zijdenbos similarity index (ZSI), precision, and recall. An experimental evaluation demonstrates superior performance over three-level global thresholding for ALL image segmentation.
Keywords: three-level local thresholding, acute lymphoblastic leukemia, three-level Otsu thresholding, gram-schmidt orthogonalization
Abstrak. Segmentasi citra Limfoblastik Leukemia Akut (LLA) dapat digunakan untuk mengidentifikasi kehadiran penyakit LLA. Pada penelitian ini diusulkan metode three-level local thresholding berbasis metode Otsu untuk segmentasi leukosit pada citra LLA. Pertama-tama, metode berbasis teori ortogonalisasi Gram-Schmidt diaplikasikan untuk membagi citra LLA menjadi sub-sub citra. Metode yang diusulkan memperluas metode bi-level thresholding Otsu ke dalam kasus three-level thresholding untuk pencarian dua nilai ambang lokal tiap sub-citra yang memaksimumkan varian antar kelas. Dengan nilai ambang jamak lokal tersebut, teknik three-level local thresholding selanjutnya mensegmentasi tiap sub-citra ke dalam tiga region, yaitu nukelus, sitoplasma, dan latar belakang. Untuk mengevaluasi performa metode usulan, 32 citra uji digunakan. Performa metode yang diusulkan dibandingkan dengan citra segmentasi manual menggunakan Zijdenbos similarity index (ZSI), presisi, dan recall. Hasil uji coba menunjukkan performa three-level local thresholding lebih unggul daripada metode three-level global thresholding untuk segmentasi citra LLA.
Kata Kunci: three-level local thresholding, leukemia limfoblastik akut, three-level Otsu thresholding, ortogonalisasi gram-schmidt
References
. Albitar, M., Giles, F.J. & Kantarjian, H.M. 2008. Diagnosis of Acute Lymphoblastic Leukemia. Dalam E.H. Estey, S.H. Faderl, dan H.M. Kantarjian (Eds.), Acute Leukemias (hlm. 119-130). New York: Springer Berlin Heidelberg.
. Fatichah, C., Tangel, M. L., Widyanto, M. R., Dong, F., & Hirota, K. 2012. Interest-Based Ordering for Fuzzy Morphology on White Blood Cell Image Segmentation. JACIII, 16, (1): 76-86.
. Gao, H., Xu, W., Sun, J., & Tang, Y. 2010. Three-level thresholding for image segmentation through an improved quantum-behaved particle swarm algorithm. Instrumentation and Measurement, IEEE Transactions on, 59(4): 934-946.
. Labati, R. D., Piuri, V., & Scotti, F. 2011,“All-IDB: The Acute Lymphoblastic Leukemia Image Database for Image Processing”, Proceedings of the 18th IEEE ICIP International Conference on Image Processing, Eds: Macq, B., dan Schelkens, P.,IEEE Signal Processing Society, Brussels, hal. 2045-2048.
. Larson, R.A. & Anastasi, J. 2008. Acute Lymphoblastic Leukemia: Clinical Presentation, Diagnosis, and Classification. Dalam E.H. Estey, S.H. Faderl, dan H.M. Kantarjian (Eds.), Acute Leukemias (hlm. 109-118). New York: Springer Berlin Heidelberg.
. Madhloom, H. T., Kareem, S. A., & Ariffin, H. 2012. An Image Processing Application for the Localization and Segmentation of Lymphoblast Cell using Peripheral Blood Images. Journal of medical systems, 36(4): 2149-2158.
. Mohapatra, S., Patra, D., & Satpathy, S. 2014. An Ensemble Classifier System for Early Diagnosis of Acute Lymphoblastic Leukemia in Blood Microscopic Images. Neural Computing and Applications, 24(7-8): 1887-1904.
. Piuri, V., & Scotti, F. (2004), “Morphological Classification of Blood Leucocytes by Microscope Images”, Proceedings of the 2004 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications, Eds: Alippi, C. et al., IEEE, Boston, hal. 103-108.
. Putzu, L., Caocci, G., & Di Ruberto, C. 2014. Leucocyte Classification for Leukaemia Detection using Image Processing Techniques. Artificial Intelligence in Medicine, 62(3): 179-191.
. Rezatofighi, S. H. & Soltanian-Zadeh, H. 2011. Automatic Recognition of Five Types of White Blood Cells in Peripheral Blood. Computerized Medical Imaging and Graphics, 35(4): 333-343.
. Scotti, F. (2006), “Robust Segmentation and Measurements Techniques of White Cells in Blood Microscope Images”, Proceedings of the 2006 IEEE Instrumentation and Measurement Technology Conference, Eds: Daponte, P. et al., IEEE Instrumentation and Measurement Society, Sorrento, hal. 43-48.
. Wang, E. Y., Gou, Z., Miao, A. M., Peng, S. Q., Niu, Z. Y., & Shi, X. L. (2009), “Recognition of Blood Cell Images based on Color Fuzzy Clustering”, dalam Fuzzy Information and Engineering Volume 2, eds. Cao, B., Li, T., dan Zhang, C., Springer Berlin Heidelberg, New York, hal. 69-75.
Downloads
Published
Issue
Section
License
Copyright of this journal is assigned to Jurnal Buana Informatika as the journal publisher by the knowledge of author, whilst the moral right of the publication belongs to author. Every printed and electronic publications are open access for educational purposes, research, and library. The editorial board is not responsible for copyright violation to the other than them aims mentioned before. The reproduction of any part of this journal (printed or online) will be allowed only with a written permission from Jurnal Buana Informatika.
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
