WBCBench 2026: A Challenge for Robust White Blood Cell Classification Under Class Imbalance

TL;DR

WBCBench 2026 is a challenging benchmark for white blood cell classification that tests algorithms under class imbalance, domain shifts, and strict data separation, with standardized evaluation and open-source tools.

Contribution

This paper introduces a comprehensive challenge and benchmark for robust WBC classification, emphasizing realistic domain shifts and strict data separation.

Findings

Benchmark includes 13 WBC classes with severe imbalance.

Two phases: pristine data and degraded images with domain shifts.

Open-source evaluator and standardized submission schema.

Abstract

We present WBCBench 2026, an ISBI challenge and benchmark for automated WBC classification designed to stress-test algorithms under three key difficulties: (i) severe class imbalance across 13 morphologically fine-grained WBC classes, (ii) strict patient-level separation between training, validation and test sets, and (iii) synthetic scanner- and setting-induced domain shift via controlled noise, blur and illumination perturbations. All images are single-site microscopic blood smear acquisitions with standardised staining and expert hematopathologist annotations. This paper reviews the challenge and summarises the proposed solutions and final outcomes. The benchmark is organised into two phases. Phase 1 provides a pristine training set. Phase 2 introduces degraded images with split-specific severity distributions for train, validation and test, emulating a realistic shift between development and deployment conditions. We specify a standardised submission schema, open-source evaluator, and macro-averaged F1 score as the primary ranking metric.