WBCAtt+: Fine-Grained Pixel-Level Morphological Annotations for White Blood Cell Images

2026-05-19

AI Summary

Existing white blood cell (WBC) image datasets lack fine-grained morphological annotations required for pathological diagnosis, hindering the development of interpretable medical AI. To address this gap, this work introduces WBCAtt+, the first large-scale WBC image dataset comprising 113k image-level morphological attribute labels across 11 fine-grained attributes and 10k pixel-level cellular component segmentation masks. Leveraging this dataset, we establish baseline models for semantic segmentation and attribute recognition and propose a novel attribute recognition method that integrates cellular compositional structure. Experimental results demonstrate that the proposed approach significantly improves attribute recognition performance, thereby providing critical support for interpretable AI applications such as counterfactual example generation.

Abstract

The microscopic examination of white blood cells (WBCs) plays a fundamental role in pathology and is essential for diagnosing blood disorders such as leukemia and anemia. To support further research on WBC images, multiple datasets have been proposed. However, they mainly annotate cell categories, and lack detailed morphological characteristics that pathologists use to explain their interpretations of cells. To address this gap, we introduce WBCAtt+, a novel dataset of WBC images densely annotated with 11 morphological attributes and five pixel-level cell components. With 113k image-level labels and 10k segmentation maps, WBCAtt+ is the first to provide comprehensive annotations for WBC images. Leveraging this dataset, we provide baseline models for attribute recognition and semantic segmentation. We also design an attribute recognition model to incorporate compositional structure of cells, further improving the recognition performance. Lastly, we showcase various applications enabled by our dataset, such as explainable AI models, including counterfactual example generation. \revision{The dataset and code are publicly available\footnote{https://doi.org/10.57967/hf/8143}}.

Problem

• white blood cell
• morphological annotation
• pixel-level segmentation
• fine-grained labeling
• medical image analysis

Innovation

• fine-grained annotation
• pixel-level segmentation
• morphological attributes
• explainable AI
• white blood cell dataset