Improving White Blood Cell Classification With Minimal Labels: a Semi-supervised Learning Framework
Year: 2025
Type: article
Abstract: The diagnosis of numerous blood disorders depends on the accurate classification of white blood cellsubtypes. Manually designed features are frequently needed for traditional computer vision techniques, which can betime-consuming and performance-limiting. On the other hand, machine learning techniques provide higher accuracybut usually require large labeled datasets, which are expensive and difficult to collect. This work presents a semisupervised learning strategy designed specifically for the classification of white blood cells. Through the utilizationof a limited quantity of labeled data and a more extensive collection of unlabeled data, the model is able to recognizeand classify various subtypes of white blood cells straight from microscopic pictures. This approach improvesclassification performance by leveraging the data's natural structure and patterns rather than depending just on preestablished features.The suggested method was assessed on a dataset of artificial images that depicted differentsubtypes of white blood cells. The results indicate promising accuracy in differentiating across cell types, indicatingpotential uses in clinical diagnostics. White blood cell analysis in medical settings can be automated and made moreefficient with this scalable method that reduces the need for manually labeled data while retaining excellentclassification accuracy
Authors: Zainab Uzma, Rubeena Afsar
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W4413877803