Detection of Acute Lymphoblastic Leukemia using SMMT and Watershed with DenseNet121 Classification

Authors

  • Andhini Putri Arini Putri Arini
  • Anggraini Puspita Sari
  • Achmad Junaidi

DOI:

https://doi.org/10.26905/jeemecs.v8i2.15545

Keywords:

Acute Lymphoblastic Leukemia, Segmentation, Watershed, SMMT, DenseNet121

Abstract

Acute Lymphoblastic Leukemia (ALL) is a type of blood cancer that commonly affects children and requires early detection to improve treatment success. This study proposes a method for ALL detection based on microscopic images of white blood cells using a deep learning approach. The research stages include data preprocessing with augmentation and the Self-Dual Multiscale Morphological Toggle (SMMT) method, segmentation using the Watershed method to separate the cell nucleus and cytoplasm, and classification using the DenseNet121 architecture. The dataset used consists of four classes of blood cells and is processed to be balanced before being trained on the model. The evaluation was carried out based on three batch-size testing scenarios to measure the effect of configuration on model performance. The results showed that the combination of SMMT and Watershed segmentation methods improved the quality of visual image features, while classification using DenseNet121 provided high accuracy with the best results at batch size 8, reaching 97%. This study proves that the combination of segmentation and deep learning techniques effectively detects ALL and can be further developed for automatic diagnostic systems.

Downloads

Download data is not yet available.

References

[1] S. Devella, Y. Yohannes, and C. A. Putra, "The Use of Saliency-SURF Features for White Blood Cell Image Classification with SVM Method," JATISI (Journal of Information Technology and System Information), vol. 8, no. 4, pp. 1998-2009, 2021.

[2] Medical Technology, "Learn about the Five Common White Blood Cells," University of Wisconsin Oshkosh,2018. [Online]. Available: https://www.uwosh.edu/med_tech/what-is-elementary-hematology/white-blood-cells/ . Accessed: July 31, 2019.

[3] I.P. P. Banik, R. Saha, and K.-D. Kim, "An Automatic Nucleus Segmentation and CNN Model based Classification Method of White Blood Cell," Expert Systems with Applications, 113211, 2020, doi: 10.1016/j.eswa.2020.113211.

[4] D. Garniasih, S. Susanah, Y. Sribudiani, and D. Hilmanto, "The Incidence and Mortality of Childhood Acute Lymphoblastic Leukemia in Indonesia: A Systematic Review and Meta-Analysis," PloS One, vol. 17, no. 6, p. e0269706, 2022. [Online]. Available: https://doi.org/10.1371/journal.pone.0269706.

[5] L. M. Samsu and I. Fathurrahman, "Adaptive Thresholding Algorithms and Morphological to Improve the Quality of Takepan Sasak Image Readability," in Proc. Journal of Physics: Conference Series, vol. 1539, no. 1, p. 012031, IOP Publishing, May 2020.

[6] L. Lina, D. Reynaldo, D. Danny, and A. Chris, "White blood cells detection from unstained microscopic images using modified watershed segmentation," IAENG International Journal of Computer Science, vol. 48, no. 4, pp. 1151–1161, 2021.

[7] G. Hiremath, J. A. Mathew, and N. K. Boraiah, "Hybrid Statistical and Texture Features with DenseNet 121 for Breast Cancer Classification," International Journal of Intelligent Engineering & Systems, vol. 16, no. 2, pp. –, 2023.

[8] N. A. Pakpahan and I. M. H. Sinaga, "Acute Lymphoblastic Leukemia," Medical Methodist Journal, 2024. [Online]. Available: https://ejurnal.methodist.ac.id. [Accessed: Dec. 20, 2024].

[9] A. Bodzas, P. Kodytek, and J. Zidek, "Automated Detection of Acute Lymphoblastic Leukemia from Microscopic Images Based on Human Visual Perception," Frontiers in Bioengineering and Biotechnology, vol. 8, pp. 1005, 2020, doi: 10.3389/fbioe.2020.01005.

[10] Munir, "Definition of Image and Digital Image," Jurnal Teknologi Informasi, vol. 2, no. 1, pp. 13-19, 2004.

[11] Putra, "Introduction to Digital Image," Jurnal Sistem Komputer, vol. 5, no. 2, pp. 45-53, 2010.

[12] Fikriya, Irawan, and Soetrisno, "Fundamentals of Digital Image Processing," Jurnal Pengolahan Citra, vol. 11, no. 4, pp. 88-95, 2017.

[13] N. Nafi’iyah, "Kohonen Algorithm in Converting Graylevel Image to Binary Image," Jitika, vol. 9, no. 2, pp. 49–55, Aug. 2015.

[14] I. Basuki and A. Ramadijanti, "Digital Image Processing and Its Applications," 2005.

[15] R. P. Rianto and A. Harjoko, "Digital Image Processing Processes," 2017.

[16] "Glossary - Mathematical Morphology," [Online]. Available: http://homepages.inf.ed.ac.uk/rbf/HIPR2/matmorph.htm. [Accessed: Dec. 15, 2016].

[17] S. Zahrah, R. Saptono, and E. Suryani, "Identification of Rice Disease Symptoms Using Image Morphological Operations," in Seminar Nasional Ilmu Komputer (SNIK 2016), Semarang, Indonesia, Oct. 2016, vol. 10.

[18] R. Adipranata, A. Handojo, I. Prayogo, and O. Y. Yuliana, "Design and Development of an Image Segmentation Application Using the Morphological Watershed Method," Department of Computer Science, Petra University, 2015.

[19] E. S. F. Hutagalung and P. Sitompul, "Implementation of Deep Learning Using CNN Method for Classification of Toba Batak Ulos Types," Student Scientific Creativity Journal (SSCJ), vol. 1, pp. 1–19, 2023. [Online]. Available: https://doi.org/10.55606/sscj-amik.v1i4.1541.

[20] H. A. Firmansyah, M. Kurniawan, C. N. Prabiantissa, and S. Muharom, "Classification of Zingiberaceae Rhizome Plant Types Using CNN and VGG 19 Methods," Jurnal TIKA Fakultas Ilmu Komputer Universitas Almuslim, vol. 9, pp. 62–68, 2024.

[21] K. A. Baihaqi and Z. C. Zonyfar, "Detection of Agricultural Land Affected by Rat Pests Using Yolo v5," Syntax: Jurnal Informatika, vol. 11, pp. 1–9, 2022.

[22] J. Pardede and D. A. L. Putra, "Implementation of DenseNet for Identifying Melanoma Skin Cancer," Jurnal Teknik Informatika dan Sistem Informasi, vol. 6, no. 3, 2020.

Downloads

Published

2025-08-26

Issue

Section

Articles