Towards Effective and Efficient Context-aware Nucleus Detection in Histopathology Whole Slide Images

2025-03-04

AI Summary

To address the limitations of sliding-window approaches—neglecting long-range tissue context—and large-field-of-view (FoV) cropping—inducing high inference latency—in whole-slide image (WSI) nucleus detection, this paper proposes ContextNucleus. Our method introduces a novel temporal aggregation mechanism that fuses historical sliding-window features, eliminating the need for computationally expensive large-FoV cropping. We design Grid Pooling to compress dense features into sparse contextual tokens and integrate high-magnification local modeling with token injection for context-aware nucleus instance segmentation. We further establish OCELOT-seg, the first context-aware nucleus instance segmentation benchmark tailored for WSIs. Extensive experiments across multiple WSI datasets demonstrate state-of-the-art performance, achieving significant improvements in both detection and segmentation accuracy while reducing average inference latency by 37%. The code, dataset, and pretrained models are publicly released.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Multi-instance/Multi-view Learning
• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Location- and context-aware Web and WoT applications and services
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Nucleus detection in histopathology whole slide images (WSIs) is crucial for a broad spectrum of clinical applications. Current approaches for nucleus detection in gigapixel WSIs utilize a sliding window methodology, which overlooks boarder contextual information (eg, tissue structure) and easily leads to inaccurate predictions. To address this problem, recent studies additionally crops a large Filed-of-View (FoV) region around each sliding window to extract contextual features. However, such methods substantially increases the inference latency. In this paper, we propose an effective and efficient context-aware nucleus detection algorithm. Specifically, instead of leveraging large FoV regions, we aggregate contextual clues from off-the-shelf features of historically visited sliding windows. This design greatly reduces computational overhead. Moreover, compared to large FoV regions at a low magnification, the sliding window patches have higher magnification and provide finer-grained tissue details, thereby enhancing the detection accuracy. To further improve the efficiency, we propose a grid pooling technique to compress dense feature maps of each patch into a few contextual tokens. Finally, we craft OCELOT-seg, the first benchmark dedicated to context-aware nucleus instance segmentation. Code, dataset, and model checkpoints will be available at https://github.com/windygoo/PathContext.

Problem

• Improves nucleus detection in histopathology images
• Reduces computational overhead in context-aware methods
• Enhances accuracy with finer-grained tissue details

Innovation

• Aggregates contextual clues from historical sliding windows
• Uses grid pooling to compress dense feature maps
• Introduces OCELOT-seg for context-aware nucleus segmentation