SWAN -- Enabling Fast and Mobile Histopathology Image Annotation through Swipeable Interfaces

2025-11-11

AI Summary

Low annotation efficiency and poor scalability in large-scale digital pathology image labeling hinder the development of deep learning models for clinical tasks such as mitosis detection. To address this, we propose a cross-platform (desktop/mobile) intelligent annotation framework based on sliding interaction, integrating gesture recognition, real-time metadata capture, and flexible label mapping to support collaborative annotation and responsive synchronization. This work introduces sliding gestures—previously unexplored in pathology annotation—as a lightweight, low-fatigue, and highly consistent mobile-first annotation paradigm. In a pilot study involving four pathologists annotating 600 whole-slide images, inter-annotator agreement reached Cohen’s Kappa values of 0.61–0.80—comparable to conventional methods—while annotation speed improved significantly and user acceptability scores were excellent. The system is implemented using open, web-based technologies, ensuring high deployability and extensibility.

Technology Category

• Computer Vision: Segmentation
• Intelligent Robots: Motion and Path Planning
• Humans and AI: Intelligent User Interfaces

Application Category

• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

The annotation of large scale histopathology image datasets remains a major bottleneck in developing robust deep learning models for clinically relevant tasks, such as mitotic figure classification. Folder-based annotation workflows are usually slow, fatiguing, and difficult to scale. To address these challenges, we introduce SWipeable ANnotations (SWAN), an open-source, MIT-licensed web application that enables intuitive image patch classification using a swiping gesture. SWAN supports both desktop and mobile platforms, offers real-time metadata capture, and allows flexible mapping of swipe gestures to class labels. In a pilot study with four pathologists annotating 600 mitotic figure image patches, we compared SWAN against a traditional folder-sorting workflow. SWAN enabled rapid annotations with pairwise percent agreement ranging from 86.52% to 93.68% (Cohen's Kappa = 0.61-0.80), while for the folder-based method, the pairwise percent agreement ranged from 86.98% to 91.32% (Cohen's Kappa = 0.63-0.75) for the task of classifying atypical versus normal mitotic figures, demonstrating high consistency between annotators and comparable performance. Participants rated the tool as highly usable and appreciated the ability to annotate on mobile devices. These results suggest that SWAN can accelerate image annotation while maintaining annotation quality, offering a scalable and user-friendly alternative to conventional workflows.

Problem

• Accelerating histopathology image annotation for deep learning
• Replacing slow folder-based workflows with mobile interfaces
• Improving annotation scalability while maintaining quality consistency

Innovation

• Uses swipe gestures for image classification
• Supports desktop and mobile platforms
• Enables real-time metadata capture