arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2502.21187cs.LG
收藏

虚拟患者,真实获益:基于数字孪生的模拟CT用于多任务肺结节分析

Virtual Patients, Real Gains: Digital Twin-Based Simulated CT for Multitask Lung Nodule Analysis

Center for Virtual Imaging trials, Dept. of Radiology, Duke University Medical Center(虚拟成像中心,放射科,杜克大学医学中心);Dept. of Electrical and Computer Engineering, Pratt School of Engineering, Duke University(电气与计算机工程系,工程学院,杜克大学)

Fakrul Islam Tushar, Lavsen Dahal, Paul Segars, Joseph Y. Lo

AI总结:

该研究基于Virtual Lung Screening Trial框架生成虚拟CT数据,训练相关模型提升肺结节检测、分割、分类性能,可解决医学AI的标注CT数据稀缺问题。

摘要:

基于AI的肺癌筛查受限于标注CT数据稀缺,尤其是罕见结节表现的情况。本研究探究基于物理、解剖学的模拟CT能否提升三项肺结节任务(检测、分割、良恶性分类)的AI性能。使用Virtual Lung Screening Trial框架,生成174个数字人孪生体(XCAT3),植入512个经程序控制的结节(X-Lesions,尺寸4-30mm),在两种扫描仪配置下用DukeSim模拟CT,得到1044幅标注扫描图像。结合临床数据,分别训练检测模型(MONAI)、分割模型(VISTA3D、nnU-Net)、分类模型(Med3D),在外部测试集上评估:检测在1假阳性/扫描时的灵敏度从0.37升至0.56(p<0.001);分割性能小幅提升(Dice从0.61升至0.64、0.66升至0.69);分类AUC从0.78升至0.87(p<0.001)。基于物理的虚拟成像试验可助力解决医学AI中的数据稀缺问题。

英文摘要:

AI-based lung cancer screening is constrained by scarce, annotated CT data, particularly for rare nodule presentations. We investigate whether physics-based, anatomy-informed simulated CT can improve AI performance across three lung-nodule tasks: detection, segmentation, and malignancy classification. Using the Virtual Lung Screening Trial framework, we generated 174 digital human twins (XCAT3), embedded 512 procedurally controlled nodules (X-Lesions, 4-30 mm), and simulated CT (DukeSim) under two scanner configurations, yielding 1,044 annotated scans. Combined with clinical data, these trained models for detection (MONAI), segmentation (VISTA3D, nnU-Net), and classification (Med3D), evaluated on external test sets. Detection sensitivity at 1 FP/scan rose from 0.37 to 0.56 (p < 0.001); segmentation improved modestly (Dice 0.61 to 0.64, 0.66 to 0.69); classification AUC rose from 0.78 to 0.87 (p < 0.001). Physics-based virtual imaging trials can help address data scarcity in medical AI.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑