Department of Biomedical Engineering, University of Iowa, Iowa City, IA, 52240, USA.
Department of Radiology, University of Iowa, Iowa City, IA, 52242, USA.
Med Phys. 2019 Jul;46(7):3207-3216. doi: 10.1002/mp.13592. Epub 2019 Jun 7.
Computed tomography (CT) is an effective method for detecting and characterizing lung nodules in vivo. With the growing use of chest CT, the detection frequency of lung nodules is increasing. Noninvasive methods to distinguish malignant from benign nodules have the potential to decrease the clinical burden, risk, and cost involved in follow-up procedures on the large number of false-positive lesions detected. This study examined the benefit of including perinodular parenchymal features in machine learning (ML) tools for pulmonary nodule assessment.
Lung nodule cases with pathology confirmed diagnosis (74 malignant, 289 benign) were used to extract quantitative imaging characteristics from computed tomography scans of the nodule and perinodular parenchyma tissue. A ML tool development pipeline was employed using k-medoids clustering and information theory to determine efficient predictor sets for different amounts of parenchyma inclusion and build an artificial neural network classifier. The resulting ML tool was validated using an independent cohort (50 malignant, 50 benign).
The inclusion of parenchymal imaging features improved the performance of the ML tool over exclusively nodular features (P < 0.01). The best performing ML tool included features derived from nodule diameter-based surrounding parenchyma tissue quartile bands. We demonstrate similar high-performance values on the independent validation cohort (AUC-ROC = 0.965). A comparison using the independent validation cohort with the Fleischner pulmonary nodule follow-up guidelines demonstrated a theoretical reduction in recommended follow-up imaging and procedures.
Radiomic features extracted from the parenchyma surrounding lung nodules contain valid signals with spatial relevance for the task of lung cancer risk classification. Through standardization of feature extraction regions from the parenchyma, ML tool validation performance of 100% sensitivity and 96% specificity was achieved.
计算机断层扫描（CT）是一种有效检测和描述体内肺结节的方法。随着胸部 CT 的广泛应用，肺结节的检测频率不断增加。通过非侵入性方法区分良恶性结节，有可能减少因大量假阳性病变而导致的后续程序的临床负担、风险和成本。本研究探讨了在肺结节评估的机器学习（ML）工具中纳入结节周围实质特征的益处。
使用具有病理证实诊断的肺结节病例（74 例恶性，289 例良性），从结节和结节周围实质组织的 CT 扫描中提取定量成像特征。使用 k-均值聚类和信息论的 ML 工具开发管道，确定不同数量的实质纳入的有效预测因子集，并构建人工神经网络分类器。使用独立队列（50 例恶性，50 例良性）验证所得 ML 工具。
纳入实质成像特征可提高 ML 工具的性能，优于仅结节特征（P<0.01）。表现最佳的 ML 工具包括基于结节直径的周围实质组织四分位带的特征。我们在独立验证队列中展示了类似的高性能值（AUC-ROC=0.965）。使用独立验证队列与弗莱舍纳肺部结节随访指南进行的比较表明，建议的随访影像学和程序有理论上的减少。
从肺结节周围实质中提取的放射组学特征包含与肺癌风险分类任务具有空间相关性的有效信号。通过实质提取区域的标准化，实现了 ML 工具验证的 100%敏感性和 96%特异性的性能。
