English

Ensemble of Small Classifiers For Imbalanced White Blood Cell Classification

Computer Vision and Pattern Recognition 2026-03-24 v1 Machine Learning

Abstract

Automating white blood cell classification for diagnosis of leukaemia is a promising alternative to time-consuming and resource-intensive examination of cells by expert pathologists. However, designing robust algorithms for classification of rare cell types remains challenging due to variations in staining, scanning and inter-patient heterogeneity. We propose a lightweight ensemble approach for classification of cells during Haematopoiesis, with a focus on the biology of Granulopoiesis, Monocytopoiesis and Lymphopoiesis. Through dataset expansion to alleviate some class imbalance, we demonstrate that a simple ensemble of lightweight pretrained SwinV2-Tiny, DinoBloom-Small and ConvNeXT-V2-Tiny models achieves excellent performance on this challenging dataset. We train 3 instantiations of each architecture in a stratified 3-fold cross-validation framework; for an input image, we forward-pass through all 9 models and aggregate through logit averaging. We further reason on the weaknesses of our model in confusing similar-looking myelocytes in granulopoiesis and lymphocytes in lymphopoiesis. Code: https://gitlab.com/siddharthsrivastava/wbc-bench-2026.

Keywords

Cite

@article{arxiv.2603.20856,
  title  = {Ensemble of Small Classifiers For Imbalanced White Blood Cell Classification},
  author = {Siddharth Srivastava and Adam Smith and Scott Brooks and Jack Bacon and Till Bretschneider},
  journal= {arXiv preprint arXiv:2603.20856},
  year   = {2026}
}

Comments

Accepted at ISBI 2026 WBCBench Challenge

R2 v1 2026-07-01T11:31:31.842Z