Acute lymphoblastic leukemia diagnosis and subtype segmentation in blood smears using CNN and U-Net
| Dublin Core | PKP Metadata Items | Metadata for this Document | |
| 1. | Title | Title of document | Acute lymphoblastic leukemia diagnosis and subtype segmentation in blood smears using CNN and U-Net |
| 2. | Creator | Author's name, affiliation, country | Hamim Reza; Bangladesh University of Business and Technology; Bangladesh |
| 2. | Creator | Author's name, affiliation, country | Nazrul Islam Tareq; Bangladesh University of Business and Technology; Bangladesh |
| 2. | Creator | Author's name, affiliation, country | M M Fazle Rabbi; Bangladesh University of Business and Technology; Bangladesh |
| 2. | Creator | Author's name, affiliation, country | Sharia Arfin Tanim; American International University-Bangladesh; Bangladesh |
| 2. | Creator | Author's name, affiliation, country | Rifat Al Mamun Rudro; American International University-Bangladesh; Bangladesh |
| 2. | Creator | Author's name, affiliation, country | Kamruddin Nur; American International University-Bangladesh; Bangladesh |
| 3. | Subject | Discipline(s) | Computer and Informatics |
| 3. | Subject | Keyword(s) | Acute lymphoblastic leukemia; CNN; Segmentation; Blood Smears; Hematogone |
| 4. | Description | Abstract | Acute lymphoblastic leukaemia (ALL) is a severe disease requiring invasive, expensive, and time-consuming diagnostic tests for definitive diagnosis. Initial diagnosis using blood smear pictures (BSP) is crucial but challenging due to the similar indications and symptoms of ALL, often leading to misdiagnoses. This study presents a custom approach using Convolutional Neural Networks (CNNs) to detect all cases and categorize subtypes. Utilizing publicly available databases, the study includes 3562 blood smear images from 89 patients. The innovative combination of U-Net for segmentation and various CNN architectures (U-Net, MobileNetV2, InceptionV3, ResNet50, NASNet) for feature extraction, with DenseNet201 being the most effective, forms the core of this method. The U-Net model achieved a segmentation accuracy of 98% by recognizing patterns within blood smear images. Following segmentation, CNN architectures extracted high-level features, with DenseNet201 proving the most effective in diagnostic and classification tasks. Our proposed custom CNN model achieved a test accuracy of 98%, with a training accuracy of 99.31% and validation accuracy of 97.09%. This approach enables an accurate distinction between ALL and non-pathologic cases. |
| 5. | Publisher | Organizing agency, location | Institute of Advanced Engineering and Science |
| 6. | Contributor | Sponsor(s) | Self |
| 7. | Date | (YYYY-MM-DD) | 2025-05-01 |
| 8. | Type | Status & genre | Peer-reviewed Article |
| 8. | Type | Type | |
| 9. | Format | File format | |
| 10. | Identifier | Uniform Resource Identifier | https://ijeecs.iaescore.com/index.php/IJEECS/article/view/38991 |
| 10. | Identifier | Digital Object Identifier (DOI) | http://doi.org/10.11591/ijeecs.v38.i2.pp950-959 |
| 11. | Source | Title; vol., no. (year) | Indonesian Journal of Electrical Engineering and Computer Science; Vol 38, No 2: May 2025 |
| 12. | Language | English=en | en |
| 14. | Coverage | Geo-spatial location, chronological period, research sample (gender, age, etc.) | |
| 15. | Rights | Copyright and permissions |
Copyright (c) 2025 Kamruddin Nur This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License. |