Ensemble of Small Classifiers For Imbalanced White Blood Cell Classification

TL;DR

This paper presents a lightweight ensemble of pretrained models for classifying white blood cells, addressing class imbalance and achieving high accuracy in distinguishing rare cell types for leukemia diagnosis.

Contribution

It introduces a simple ensemble approach using lightweight pretrained models and dataset expansion to improve classification of imbalanced white blood cell types.

Findings

Ensemble achieves high performance on challenging dataset.

Dataset expansion helps alleviate class imbalance.

Model confuses similar cell types like myelocytes and lymphocytes.

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.