Leveraging Sparse Annotations for Leukemia Diagnosis on the Large Leukemia Dataset

2025-03-25

bioRxiv

AI Summary

Leukemia analysis is hindered by small-scale, low-diversity annotated datasets, impeding clinical deployment. To address this, we introduce LLD—the first million-scale, multi-source peripheral blood smear dataset for leukocyte analysis—supporting three core tasks: cell localization, classification, and prediction of seven morphological attributes. We propose a sparse-label-driven whole-slide multitask learning framework that enables global modeling using only local region annotations, thereby drastically reducing annotation effort. Our method integrates morphology-aware interpretable annotations, domain adaptation, and attribute-decoupled prediction to enhance generalizability and clinical relevance. Experiments demonstrate a >90% reduction in annotation cost (to <10% of full annotation), achieving 92.4% mAP for WBC detection, 86.7% mean accuracy for morphological attribute prediction, and a 23.5% improvement in cross-device and cross-center generalization performance.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Lexical Semantics and Morphology
• Computer Vision: Large Vision Models

Application Category

• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Leukemia is 10th most frequently diagnosed cancer and one of the leading causes of cancer-related deaths worldwide. Realistic analysis of Leukemia requires White Blook Cells (WBC) localization, classification, and morphological assessment. Despite deep learning advances in medical imaging, leukemia analysis lacks a large, diverse multi-task dataset, while existing small datasets lack domain diversity, limiting real-world applicability. To overcome dataset challenges, we present a large-scale WBC dataset named ‘Large Leukemia Dataset’ (LLD) and novel methods for detecting WBC with their attributes. Our contribution here is threefold. First, we present a large-scale Leukemia dataset collected through Peripheral Blood Films (PBF) from several patients, through multiple microscopes, multi-cameras, and multi-magnification. To enhance diagnosis explainability and medical expert acceptance, each leukemia cell is annotated at 100x with 7 morphological attributes, ranging from Cell Size to Nuclear Shape. Secondly, we propose a multi-task model that not only detects WBCs but also predicts their attributes, providing an interpretable and clinically meaningful solution. Third, we propose a method for WBC detection with attribute analysis using sparse annotations. This approach reduces the annotation burden on hematologists, requiring them to mark only a small area within the field of view. Our method enables the model to leverage the entire field of view rather than just the annotated regions, enhancing learning efficiency and diagnostic accuracy. From diagnosis explainability to overcoming domain-shift challenges, presented datasets could be used for many challenging aspects of microscopic image analysis. The datasets, code, and demo are available at: https://im.itu.edu.pk/sparse-leukemiaattri/.

Problem

• Lack of large diverse dataset for leukemia analysis
• Need for interpretable multi-task WBC detection model
• Reducing annotation burden with sparse annotation method

Innovation

• Large-scale Leukemia dataset with multi-source collection
• Multi-task model for WBC detection and attribute prediction
• Sparse annotation method reducing expert marking burden