From Data to Diagnosis: A Large, Comprehensive Bone Marrow Dataset and AI Methods for Childhood Leukemia Prediction

2025-09-19

AI Summary

Manual bone marrow morphology analysis for pediatric leukemia diagnosis is labor-intensive, subjective, and lacks standardized, large-scale public data. To address this, we introduce the first open, end-to-end benchmark dataset for pediatric leukemia—comprising over 10,000 high-quality, expert-annotated bone marrow images spanning cell detection, fine-grained classification (33 cell types), and clinical diagnosis. Leveraging this resource, we propose an integrated deep learning framework: (1) Faster R-CNN for precise cell localization (mAP = 0.96); (2) a fine-grained classification model achieving AUC = 0.98; and (3) a diagnostic prediction module incorporating cellular counts, attaining F1-score = 0.90. This work establishes the first publicly available, clinically grounded, full-pipeline benchmark, substantially enhancing reproducibility, generalizability, and clinical translatability of AI-assisted diagnosis—thereby advancing standardization and intelligence in pediatric leukemia care.

Technology Category

• Machine Learning: Evaluation and Analysis
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Computer Vision: Segmentation

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Leukemia diagnosis primarily relies on manual microscopic analysis of bone marrow morphology supported by additional laboratory parameters, making it complex and time consuming. While artificial intelligence (AI) solutions have been proposed, most utilize private datasets and only cover parts of the diagnostic pipeline. Therefore, we present a large, high-quality, publicly available leukemia bone marrow dataset spanning the entire diagnostic process, from cell detection to diagnosis. Using this dataset, we further propose methods for cell detection, cell classification, and diagnosis prediction. The dataset comprises 246 pediatric patients with diagnostic, clinical and laboratory information, over 40 000 cells with bounding box annotations and more than 28 000 of these with high-quality class labels, making it the most comprehensive dataset publicly available. Evaluation of the AI models yielded an average precision of 0.96 for the cell detection, an area under the curve of 0.98, and an F1-score of 0.61 for the 33-class cell classification, and a mean F1-score of 0.90 for the diagnosis prediction using predicted cell counts. While the proposed approaches demonstrate their usefulness for AI-assisted diagnostics, the dataset will foster further research and development in the field, ultimately contributing to more precise diagnoses and improved patient outcomes.

Problem

• Creating a public bone marrow dataset for childhood leukemia diagnosis
• Developing AI methods for cell detection and classification
• Improving diagnostic accuracy and efficiency through AI-assisted analysis

Innovation

• Public bone marrow dataset for leukemia diagnosis
• AI methods for cell detection and classification
• Comprehensive diagnostic pipeline from data to prediction