Page 81 - AIH-2-3

Artificial Intelligence in Health CNN model for leukemia diagnosis

The findings emphasize the importance of leveraging References
advanced computational techniques to address 1. Varga D. No-reference image quality assessment with
challenges in medical diagnostics, such as imbalanced multi-scale orderless pooling of deep features. J Imaging.
datasets and data complexity. The model’s performance, 2021;7(7):112.
validated through rigorous testing on the C-NMC
dataset, highlights the effectiveness of CNNs in handling doi: 10.3390/jimaging7070112
complex classification tasks while ensuring robustness 2. Li G, Yu Y. Visual saliency detection based on multiscale
and adaptability. This not only reduces the time and deep CNN features. IEEE Transact Image Process.
resources required for manual diagnosis but also ensures 2016;25:5012-5024.
consistency in medical image analysis across diverse doi: 10.1109/TIP.2016.2602079
clinical environments.
3. Chen Y, Zheng WS, Lai JH, Yuen PC. An asymmetric
Looking ahead, the integration of this DL framework distance model for cross-view feature mapping in person
into real-world healthcare systems could lead to significant reidentification. In: IEEE Transactions on Circuits and
improvements in leukemia management. By automating Systems for Video Technology. United States: IEEE; 2016. p. 1.
the diagnostic process, healthcare providers can focus more doi: 10.1109/TCSVT.2016.2515309
on personalized treatment strategies, improving patient 4. Arivuselvam B, Sudha S. Leukemia classification using
outcomes. In addition, the scalability of the model to the deep learning method of CNN. J Xray Sci Technol.
other medical imaging datasets offers a promising avenue 2022;30(2):199-210.
for broader applications in automated disease detection,
making this a pivotal advancement at the intersection of doi: 10.3233/xst-211055
AI and medical diagnostics. 5. Kadhim KA, Najjar FH, Waad AA, Al-Kharsan IH,
Khudhair ZN, Salim AA. Leukemia classification using a
Acknowledgments convolutional neural network of AML images. Malays J
Fundam Appl Sci. 2023;19(3):560-570.
None.
doi: 10.11113/mjfas.v19n3.2901
Funding 6. Talaat FM, Gamel SA. Machine learning in detection
None. and classification of leukemia using C-NMC_Leukemia.
Multimed Tools Appl. 2023;83:8063-8076.
Conflict of interest doi: 10.1007/s11042-023-15923-8
The authors declare that they have no competing interests. 7. Rodrigues LF, Backes A, Travençolo B, De Oliveira GD.
Optimizing a deep residual neural network with genetic
Author contributions algorithm for acute lymphoblastic leukemia classification.
Conceptualization: All authors J Dig Imaging. 2022;35(2):425-435.
Formal analysis: Rahul Dev Garg doi: 10.1007/s10278-022-00600-3
Investigation: Kumari Pritee 8. Mallick P, Mohapatra SK, Chae G, Mohanty M. Convergent
Methodology: Kumari Pritee learning-based model for leukemia classification from gene
Writing–original draft: Kumari Pritee expression. Pers Ubiquitous Comput. 2023;25(5):897-906.
Writing–review & editing: All authors
doi: 10.1007/s00779-020-01467-3
Ethics approval and consent to participate 9. Arif R, Akbar S, Farooq A, Hassan SA, Gull S. Automatic
detection of leukemia through convolutional neural
Not applicable.
network. In: International Conference on Frontiers of
Consent for publication Information Technology Proceedings; 2022.
doi: 10.1109/FIT57066.2022.00044
Not applicable.
10. Alsaykhan LK, Maashi MS. A hybrid detection model
Availability of data for acute lymphocytic leukemia using support vector
machine and particle swarm optimization (SVM-PSO). Sci
The data used in the study are publicly available in the Rep. 2024;14:23483.
C-NMC dataset. The data utilized in this study, primarily
from the publicly accessible C-NMC leukemia dataset, doi: 10.1038/s41598-024-74889-1
have been thoroughly analyzed to support the findings. 11. Abhishek A, Deb SD, Jha RK, Sinha R, Jha K. Ensemble

Volume 2 Issue 3 (2025) 75 doi: 10.36922/aih.4710