Detecting pediatric acute lymphoblastic leukemia using artificial intelligence
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
This project aims to create an intelligent computer vision system for automatically detecting and diagnosing acute lymphoblastic leukemia (ALL) in children through medical imaging. The system leverages advanced image processing and machine learning techniques, featuring a streamlined version of the VGG19 convolutional neural network (CNN) to enable transfer learning for efficient feature extraction. These extracted features are then used to train a variety of machine learning models, such as XGBoost, KNN, SVM, and Random Forest, to improve diagnostic accuracy. Additionally, a Stacking Classifier and a simple neural network are incorporated to enhance performance. The system’s efficacy is evaluated using F1-scores to measure improvements in diagnostic precision and speed, facilitating early intervention and treatment planning. Comprehensive documentation of the methodologies and challenges encountered throughout the development process is provided.
Fields of Study & Subjects
Digital Imaging for Blood Diseases
AI in cancer detection
Artificial Intelligence in Healthcare
Publication details
- Journal / source
- AIP conference proceedings
- Volume
- 3401
- Pages
- 020029–020029
- Publication date
- 1 January 2026
- Language
- EN