Evaluating U-Net Segmentation in Vgg16-Based Leukemia Classification: A Comparative Study
DOI:
https://doi.org/10.47701/5d37ge60Keywords:
Comparative Study, Convolutional Neural Network, U-Net, VGG16, White Blood CellAbstract
Background: Leukemia is a malignant hematological disorder characterized by abnormal proliferation of white blood cells (WBCs), affecting over 474,000 patients globally each year, with manual diagnosis limited by inter-observer variability of up to 40%. Objective: This study evaluates whether U-Net-based WBC segmentation improves leukemia classification by comparing three configurations: VGG16 on original images, VGG16 with U-Net-predicted masks, and VGG16 with ground truth masks. Methods: A total of 3,256 ALL microscopic blood smear images were divided into training, validation, and testing sets (70:10:20). U-Net was trained using a combined Binary Cross-Entropy and Dice loss, and the segmentation outputs were used as inputs for VGG16 classification. Performance was evaluated using DSC, IoU, accuracy, precision, recall, F1-score, and AUC-ROC. Results: U-Net achieved a DSC of 0.7885 and an IoU of 0.7134. VGG16 with U-Net masks achieved 98.62% accuracy (AUC 0.9958), while VGG16 with ground truth masks achieved 98.31%. The baseline VGG16 achieved the highest performance with 99.69% accuracy (AUC 0.9999). Conclusion: Explicit segmentation did not improve classification performance for the dataset used in this study and may introduce unnecessary computational overhead when discriminative features are already preserved in the original images. Suggestion: Future studies should evaluate heterogeneous datasets and advanced segmentation architectures to further investigate the contribution of segmentation to leukemia classification.
Downloads
References
1. Shah A, Naqvi SS, Naveed K. Automated Diagnosis of Leukemia : A Comprehensive Review. IEEE Access. 2021;9:132097–124.
2. Saleem S, Amin J, Sharif M, Almas M, Muhammad A, Wang SH. A deep network designed for segmentation and classification of leukemia using fusion of the transfer learning models. Complex Intell Syst [Internet]. 2022;8(4):3105–20. Available from: https://doi.org/10.1007/s40747-021-00473-z
3. Tamas L, Bușoniu L. A reliable approach for identifying acute lymphoblastic leukemia in microscopic imaging. 2025;(July):1–14.
4. Leukemia CNMC. Machine learning in detection and classification of leukemia. Multimed Tools Appl [Internet]. 2024;83(3):8063–76. Available from: https://doi.org/10.1007/s11042-023-15923-8
5. Alsaykhan LK, Maashi MS. OPEN A hybrid detection model for acute lymphocytic leukemia using support vector machine and particle swarm optimization ( SVM- PSO ). 2024;
6. Sharma S, Guleria K, Tiwari S, Kumar S. Measurement : Sensors A deep learning based convolutional neural network model with VGG16 feature extractor for the detection of Alzheimer Disease using MRI scans. Meas Sensors [Internet]. 2022;24(September):100506. Available from: https://doi.org/10.1016/j.measen.2022.100506
7. Nadeu F, Royo R, Massoni-badosa R, Playa-albinyana H, Garcia-torre B, Duran-ferrer M, et al. transformation in chronic lymphocytic leukemia. 2022;28(August).
8. Alatawi AA, Alomani SM, Alhawiti NI, Ayaz M. Plant Disease Detection using AI based VGG-16 Model. 2022;13(4):718–28.
9. Farangis R, Kizi O, Poupi T, Armand T, Kim H cheol. A Review of Deep Learning Techniques for Leukemia Cancer Classification Based on Blood Smear Images. 2025;
10. Hasanaath AA, Mohammed AS, Latif G, Abdelhamid SE. Acute lymphoblastic leukemia detection using ensemble features from multiple deep CNN models. 2024;32(March):2407–23.
11. Shafique S, Tehsin S. Acute Lymphoblastic Leukemia Detection and Classification of Its Subtypes Using Pretrained Deep Convolutional Neural Networks. 2018;17:1–7.
12. Kamath A, Willmann J, Andratschke N, Reyes M. The impact of U-Net architecture choices and skip connections on the robustness of segmentation across texture variations. Comput Biol Med [Internet]. 2025;197(PB):111056. Available from: https://doi.org/10.1016/j.compbiomed.2025.111056
13. Kadry S, Rajinikanth V, Taniar D. Automated segmentation of leukocyte from hematological images — a study using various CNN schemes. J Supercomput [Internet]. 2022;78(5):6974–94. Available from: https://doi.org/10.1007/s11227-021-04125-4
14. Rafi A, Hutomo R. Segmentasi dan Penghitungan Otomatis Sel Darah Merah pada Citra Mikroskopis Menggunakan Transformasi Watershed Berbasis Kanal Saturasi. 2026;1–6.
15. Ghaderzadeh M, Asadi F, Hosseini A, Bashash D, Abolghasemi H, Roshanpour A. Machine Learning in Detection and Classification of Leukemia Using Smear Blood Images : A Systematic Review. 2021;2021.
16. Song Z, Fu L, Wu J, Liu Z, Li R, Cui Y. Kiwifruit detection in field images using Faster R-CNN with VGG16 Kiwifruit detection in field images using Faster R-CNN with VGG16 Kiwifruit detection in field images using Faster R-CNN with VGG16. IFAC Pap [Internet]. 2019;52(30):76–81. Available from: https://doi.org/10.1016/j.ifacol.2019.12.500
17. Hasanah AN, Sas O Al, Kosen YD. APPLICATION OF ARTIFICIAL INTELLIGENCE IN WHITE BLOOD CELL CLASSIFICATION BASED ON MICROSCOPIC IMAGES : A SCOPING REVIEW. 2025;18(2):124–31.
18. Mohan SB, Sathya S, Rajalakshmi S, Gurumoorthy G, Sivanraju R. Efficient convolutional neural networks for acute lymphoblastic leukaemia prediction in computer vision. 2026;1–15.
19. Anemia KJ jenis, Priandika A, Isnain AR. Application of Ensemble Learning Technique for Classification of Anemia Types Penerapan Teknik Ensemble Learning untuk. 2025;5(July):972–80.
20. Mara UT, Mara UT. Color Image Enhancement of Acute Leukemia Cells in Blood Microscopic Image for Leukemia Detection Sample. 2020;(3):24–9.
21. Raj R, Paliwal S, Meena G, Raj R, Raj R. ScienceDirect on Machine Learning using Image Forgery Detection System UNET Model Image Detection System using VGG16 UNET Model a VGG16 UNET Image Forgery Forgery Detection using Model Choudhary System. Procedia Comput Sci [Internet]. 2024;235:735–44. Available from: https://doi.org/10.1016/j.procs.2024.04.070
22. Williams C, Falck F, Deligiannidis G, Holmes C, Doucet A, Syed S. A Unified Framework for U-Net Design and Analysis. 2023;(NeurIPS):1–38.
23. Shah SR, Qadri S, Bibi H, Muhammad S, Shah W, Sharif MI, et al. 50 : A Case Study on Early Detection of a Rice Disease. 2023;1–13.
24. Aria, Mehrad; Ghaderzadeh, Mustafa; Bashash, Davood; Abolghasemi, Hassan; Asadi, Farkhondeh; Hosseini A. Acute Lymphoblastic Leukemia (ALL) image dataset [Internet]. Kaggle; 2021. Available from: https://www.kaggle.com/dsv/2175623
25. Aydin Atasoy, Nesrin; Faris Abdulla Al Rahhawi A. Examining the classification performance of pre-trained capsule networks on imbalanced bone marrow cell dataset. Int J Imaging Syst Technol. 2024;34(3):e23067.
26. Qu Z, Mei J, Liu L, Zhou D yang. Crack Detection of Concrete Pavement With Cross-Entropy Loss Function and Improved VGG16 Network Model. IEEE Access. 2020;8:54564–73.
27. Nasir MU, Khan MF, Khan MA, Zubair M, Abbas S, Alharbi M. Hematologic Cancer Detection Using White Blood Cancerous Cells Empowered with Transfer Learning and Image Processing. 2023;2023.
28. Alagu S, N AP, Kavitha G, K BB. Automatic Detection of Acute Lymphoblastic Leukemia Using UNET Based Segmentation and Statistical Analysis of Fused Deep Features. Appl Artif Intell [Internet]. 2021;00(00):1–18. Available from: https://doi.org/10.1080/08839514.2021.1995974
29. Yang H, Ni J, Gao J, Han Z, Luan T. OPEN A novel method for peanut variety identification and classification by Improved VGG16. Sci Rep [Internet]. 2021;1–17. Available from: https://doi.org/10.1038/s41598-021-95240-y
30. Pardede J. Implementation of Transfer Learning Using VGG16 on Fruit Ripeness Detection. 2021;(April):52–61.
31. Mohammad N, Azam M, Raiaan K, Ittesafun A. Biomedical Engineering Advances Advanced biomedical imaging for identifying blood cell type : Integrating segmentation , feature extraction , and GraphSAGE model. Biomed Eng Adv [Internet]. 2025;9(May):100174. Available from: https://doi.org/10.1016/j.bea.2025.100174
32. Zan X, Zhang X, Xing Z, Liu W, Zhang X, Liu Z, et al. Automatic Detection of Maize Tassels from UAV Images by Combining Random Forest Classifier. 2020;1–17.
33. Asghar R, Kumar S, Shaukat A, Id PH. Classification of white blood cells ( leucocytes ) from blood smear imagery using machine and deep learning models : A global scoping review. 2024;1–25. Available from: http://dx.doi.org/10.1371/journal.pone.0292026
34. Jiang Z peng, Liu Y yang, Shao Z en, Huang K wei. applied sciences An Improved VGG16 Model for Pneumonia Image Classification. 2021;
35. Narayanan KL, Krishnan RS, Robinson YH, Vimal S, Rashid TA, Kaushal C, et al. Measurement : Sensors Enhancing acute leukemia classification through hybrid fuzzy C means and random forest methods. 2025;39(April).
36. Faiz M, Gari B. Deep and Machine Learning for Acute Lymphoblastic Leukemia Diagnosis : A Comprehensive Review. 2024;13:1–24.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Rizky Vera Oktarina, Afu Ichsan Pradana, Vihi Atina, Farahwahida Mohd
This work is licensed under a Creative Commons Attribution 4.0 International License.
