SYN-LUNGS: Towards Simulating Lung Nodules with Anatomy-Informed Digital Twins for AI Training

2025-02-28

AI Summary

AI-based lung cancer screening is hindered by the scarcity of high-quality clinical CT data, resulting in limited model generalizability and clinical robustness. To address this, we propose the first anatomy-aware digital twin framework for pulmonary nodule simulation. Our method innovatively integrates XCAT3—a high-fidelity anthropomorphic phantom platform—with X-Lesions, a parametric nodule generator supporting multi-attribute control, and DukeSim, a vendor-agnostic CT physics simulator, establishing a closed-loop synthetic paradigm capable of modeling rare nodule phenotypes and enabling interpretable synthesis. Leveraging this framework, we generate a synthetic CT dataset comprising 3,072 cases with pixel-level annotations. When used in joint training, the synthetic data improves nodule detection performance by 10%, while segmentation and classification accuracy increase by 2–9%. Critically, the augmented models demonstrate significantly enhanced generalizability across diverse CT scanners and heterogeneous patient populations, thereby improving clinical applicability.

Technology Category

• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Search and Optimization: Sampling/Simulation-based Search
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior

Application Category

• Web Mining and Content Analysis: Web data generation and simulation
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems

Abstract

AI models for lung cancer screening are limited by data scarcity, impacting generalizability and clinical applicability. Generative models address this issue but are constrained by training data variability. We introduce SYN-LUNGS, a framework for generating high-quality 3D CT images with detailed annotations. SYN-LUNGS integrates XCAT3 phantoms for digital twin generation, X-Lesions for nodule simulation (varying size, location, and appearance), and DukeSim for CT image formation with vendor and parameter variability. The dataset includes 3,072 nodule images from 1,044 simulated CT scans, with 512 lesions and 174 digital twins. Models trained on clinical + simulated data outperform clinical only models, achieving 10% improvement in detection, 2-9% in segmentation and classification, and enhanced synthesis.By incorporating anatomy-informed simulations, SYN-LUNGS provides a scalable approach for AI model development, particularly in rare disease representation and improving model reliability.

Problem

• Addresses data scarcity in AI lung cancer screening models.
• Generates high-quality 3D CT images with detailed annotations.
• Improves AI model performance in detection, segmentation, and classification.

Innovation

• Generates 3D CT images with detailed annotations
• Integrates XCAT3, X-Lesions, and DukeSim technologies
• Enhances AI model performance with simulated data