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

TL;DR

WBCAtt+ is a comprehensive dataset with detailed pixel-level annotations of white blood cells, enabling advanced research in morphology-based diagnosis and explainable AI.

Contribution

The paper introduces WBCAtt+, the first dataset with detailed morphological and segmentation annotations for WBC images, and provides baseline models and applications.

Findings

Dataset contains 113k image labels and 10k segmentation maps.

Baseline models achieve improved attribute recognition and segmentation.

Applications include explainable AI and 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}}.