In diagnosing cancer and determining its progress, an important aspect is the identification of malignant cells. Blood diseases such as leukemia are generally detected when cancer cells are much larger than normal cells in the late stages. Due to strong morphological similarities, the differentiation of cancer cells from normal blood cells is a challenge. Compared with normal cells, the precise classification of malignant cells in a microscopic image of blood cells depends on the early diagnosis of leukaemia. Transfer learning and fine-tuning of the VGG16 convolutional neural network through batch normalization can resolve the malignant and normal white blood cells classification problem with higher accuracy. Applying CLAHE to enhance image data quality is then passed as input to the network for training purposes. The results acquired by the fine- tuning of triple-loss and cross-entropy or cross- entropy loss with L2 normalization are compared. Furthermore, fine-tuning on a combined training validation dataset using simple cross-entropy loss can improve the model's performance. As an effective technique for diagnosing leukaemia, computer-aided cell classification has become popular. Fine-tuning VGG16 neural networks to classify normal and malignant cell images through batch standardization is part of our classification method. The proposed convolutional neural network detects cancer and normal cells with greater accuracy and time efficiency.
| Published in | American Journal of Computer Science and Technology (Volume 5, Issue 3) |
| DOI | 10.11648/j.ajcst.20220503.16 |
| Page(s) | 190-197 |
| Creative Commons |
This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited. |
| Copyright |
Copyright © The Author(s), 2024. Published by Science Publishing Group |
Microscopic Images, Leukemia, Computer Aided Diagnosis, Deep Learning
| [1] | N. Thanh, K. AL-Dulaimi, J. Banks, V. Chandran, I. Tomeo-Reyes, and K. Nguyen, "Classification of White Blood Cell Types from Microscope Images: Techniques and Challenges," pp. 17–25, 2018. |
| [2] | I. Mehmood et al., "An efficient computerized decision support system for the analysis and 3D visualization of brain tumor," Multimed. Tools Appl., pp. 1–26, 2018. |
| [3] | A. Nedra, M. Shoaib, and S. Gattoufi, "Detection and classification of the breast abnormalities in Digital Mammograms via Linear Support Vector Machine," Middle East Conf. Biomed. Eng. MECBME, vol. 2018– March, pp. 141–146, 2018. |
| [4] | K. Kourou, T. P. Exarchos, K. P. Exarchos, M. V. Karamouzis, and D. I. Fotiadis, "Machine learning applications in cancer prognosis and prediction," Comput. Struct. Biotechnol. J., vol. 13, pp. 8–17, 2015. |
| [5] | C. E. Condrat et al., "miRNAs as Biomarkers in Disease: Latest Findings Regarding Their Role in Diagnosis and Prognosis," Cells, vol. 9, no. 2, p. 276, 2020. |
| [6] | N. Bibi, M. Sikandar, I. U. Din, A. Almogren, and S. Ali, "IOMT-based automated detection and classification of leukemia using deep learning," J. Healthc. Eng., vol. 2020, 2020. |
| [7] | W. Ladines-Castro et al., “Morphology of leukaemias,” Rev. Médica del Hosp. Gen. México, vol. 79, no. 2, pp. 107–113, 2016. |
| [8] | A. R. M. Al-shamasneh and U. H. B. Obaidellah, "Artificial Intelligence Techniques for Cancer Detection and Classification: Review Study," Eur. Sci. J., vol. 13, no. 3, pp. 342–370, 2017. |
| [9] | P. Szymak, P. Piskur, and K. Naus, "The effectiveness of using a pretrained deep learning neural networks for object classification in underwater video," Remote Sens., vol. 12, no. 18, pp. 1–19, 2020. |
| [10] | G. Ayana, K. Dese, and S. Choe, "Transfer Learning in Breast Cancer Diagnoses via Ultrasound Imaging," 2021. |
| [11] | A. Luque-Chang, E. Cuevas, F. Fausto, D. Zaldívar, and M. Pérez, “Social Spider Optimization Algorithm: Modifications, Applications, and Perspectives,” Math. Probl. Eng., vol. 2018, 2018. |
| [12] | A. T. Sahlol, P. Kollmannsberger, and A. A. Ewees, "Efficient Classification of White Blood Cell Leukemia with Improved Swarm Optimization of Deep Features," Sci. Rep., vol. 10, no. 1, pp. 1–11, 2020. |
| [13] | R. Aziz, C. K. Verma, and N. Srivastava, "Dimension reduction methods for microarray data: a review," AIMS Bioeng., vol. 4, no. 1, pp. 179–197, 2017. |
| [14] | N. Ahmed, A. Yigit, Z. Isik, and A. Alpkocak, "Identification of leukemia subtypes from microscopic images using convolutional neural network," Diagnostics, vol. 9, no. 3, 2019. |
| [15] | S. Agrawal and J. Agrawal, "Neural network techniques for cancer prediction: A survey," Procedia Comput. Sci., vol. 60, no. 1, pp. 769–774, 2015. |
| [16] | M. Adjouadi, M. Ayala, M. Cabrerizo, N. Zong, G. Lizarraga, and M. Rossman, "Classification of leukemia blood samples using neural networks," Ann. Biomed. Eng., vol. 38, no. 4, pp. 1473–1482, 2010. |
| [17] | T. J. Sejnowski, "The unreasonable effectiveness of deep learning in artificial intelligence," Proc. Natl. Acad. Sci., p. 201907373, 2020. |
| [18] | M. M. Amin, S. Kermani, A. Talebi, and M. G. Oghli, "Recognition of acute lymphoblastic leukemia cells in microscopic images using k-means clustering and support vector machine classifier," J. Med. Signals Sens., vol. 5, no. 1, pp. 49–58, 2015. |
APA Style
Asad Ullah, Muhammad Shoaib. (2022). Normal Versus Malignant Cell Classification in B-allwhite Blood Cancer Microscopic Images Using Deep Learning. American Journal of Computer Science and Technology, 5(3), 190-197. https://doi.org/10.11648/j.ajcst.20220503.16
ACS Style
Asad Ullah; Muhammad Shoaib. Normal Versus Malignant Cell Classification in B-allwhite Blood Cancer Microscopic Images Using Deep Learning. Am. J. Comput. Sci. Technol. 2022, 5(3), 190-197. doi: 10.11648/j.ajcst.20220503.16
Share This Article
Twitter
Linked In
Facebook
Copy
Download@article{10.11648/j.ajcst.20220503.16,
author = {Asad Ullah and Muhammad Shoaib},
title = {Normal Versus Malignant Cell Classification in B-allwhite Blood Cancer Microscopic Images Using Deep Learning},
journal = {American Journal of Computer Science and Technology},
volume = {5},
number = {3},
pages = {190-197},
doi = {10.11648/j.ajcst.20220503.16},
url = {https://doi.org/10.11648/j.ajcst.20220503.16},
eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ajcst.20220503.16},
abstract = {In diagnosing cancer and determining its progress, an important aspect is the identification of malignant cells. Blood diseases such as leukemia are generally detected when cancer cells are much larger than normal cells in the late stages. Due to strong morphological similarities, the differentiation of cancer cells from normal blood cells is a challenge. Compared with normal cells, the precise classification of malignant cells in a microscopic image of blood cells depends on the early diagnosis of leukaemia. Transfer learning and fine-tuning of the VGG16 convolutional neural network through batch normalization can resolve the malignant and normal white blood cells classification problem with higher accuracy. Applying CLAHE to enhance image data quality is then passed as input to the network for training purposes. The results acquired by the fine- tuning of triple-loss and cross-entropy or cross- entropy loss with L2 normalization are compared. Furthermore, fine-tuning on a combined training validation dataset using simple cross-entropy loss can improve the model's performance. As an effective technique for diagnosing leukaemia, computer-aided cell classification has become popular. Fine-tuning VGG16 neural networks to classify normal and malignant cell images through batch standardization is part of our classification method. The proposed convolutional neural network detects cancer and normal cells with greater accuracy and time efficiency.},
year = {2022}
}
TY - JOUR T1 - Normal Versus Malignant Cell Classification in B-allwhite Blood Cancer Microscopic Images Using Deep Learning AU - Asad Ullah AU - Muhammad Shoaib Y1 - 2022/09/29 PY - 2022 N1 - https://doi.org/10.11648/j.ajcst.20220503.16 DO - 10.11648/j.ajcst.20220503.16 T2 - American Journal of Computer Science and Technology JF - American Journal of Computer Science and Technology JO - American Journal of Computer Science and Technology SP - 190 EP - 197 PB - Science Publishing Group SN - 2640-012X UR - https://doi.org/10.11648/j.ajcst.20220503.16 AB - In diagnosing cancer and determining its progress, an important aspect is the identification of malignant cells. Blood diseases such as leukemia are generally detected when cancer cells are much larger than normal cells in the late stages. Due to strong morphological similarities, the differentiation of cancer cells from normal blood cells is a challenge. Compared with normal cells, the precise classification of malignant cells in a microscopic image of blood cells depends on the early diagnosis of leukaemia. Transfer learning and fine-tuning of the VGG16 convolutional neural network through batch normalization can resolve the malignant and normal white blood cells classification problem with higher accuracy. Applying CLAHE to enhance image data quality is then passed as input to the network for training purposes. The results acquired by the fine- tuning of triple-loss and cross-entropy or cross- entropy loss with L2 normalization are compared. Furthermore, fine-tuning on a combined training validation dataset using simple cross-entropy loss can improve the model's performance. As an effective technique for diagnosing leukaemia, computer-aided cell classification has become popular. Fine-tuning VGG16 neural networks to classify normal and malignant cell images through batch standardization is part of our classification method. The proposed convolutional neural network detects cancer and normal cells with greater accuracy and time efficiency. VL - 5 IS - 3 ER -
Email: