Neural Cellular Automata for Weakly Supervised Segmentation of White Blood Cells

2025-08-17

AI Summary

Addressing the challenge of scarce fine-grained segmentation annotations in leukemia cell image segmentation, this paper proposes a weakly supervised method based on Neural Cellular Automata (NCA). Unlike conventional approaches, it requires no additional pixel-level segmentation labels; instead, it leverages feature maps extracted from intermediate layers of a pre-trained classification network and employs NCA to dynamically evolve these features into pixel-level segmentation masks—thereby jointly modeling classification and segmentation. To our knowledge, this is the first application of NCAs to weakly supervised medical image segmentation. Extensive experiments on three leukocyte microscopic image datasets demonstrate that the proposed method significantly outperforms existing weakly supervised approaches, achieving high segmentation accuracy while drastically reducing reliance on manual annotations. Moreover, it exhibits strong generalizability and scalability across diverse imaging conditions and cell morphologies.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Semi-Supervised Learning
• Reasoning under Uncertainty: Causality

Application Category

• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

The detection and segmentation of white blood cells in blood smear images is a key step in medical diagnostics, supporting various downstream tasks such as automated blood cell counting, morphological analysis, cell classification, and disease diagnosis and monitoring. Training robust and accurate models requires large amounts of labeled data, which is both time-consuming and expensive to acquire. In this work, we propose a novel approach for weakly supervised segmentation using neural cellular automata (NCA-WSS). By leveraging the feature maps generated by NCA during classification, we can extract segmentation masks without the need for retraining with segmentation labels. We evaluate our method on three white blood cell microscopy datasets and demonstrate that NCA-WSS significantly outperforms existing weakly supervised approaches. Our work illustrates the potential of NCA for both classification and segmentation in a weakly supervised framework, providing a scalable and efficient solution for medical image analysis.

Problem

• Weakly supervised segmentation of white blood cells
• Reducing reliance on labeled data for medical diagnostics
• Leveraging neural cellular automata for efficient segmentation

Innovation

• Neural cellular automata for weakly supervised segmentation
• Leveraging NCA feature maps for mask extraction
• Scalable solution for medical image analysis