Piskorski Lars, Debic Manuel, von Stackelberg Oyunbileg, Schlamp Kai, Welzel Linn, Weinheimer Oliver, Peters Alan Arthur, Wielpütz Mark Oliver, Frauenfelder Thomas, Kauczor Hans-Ulrich, Heußel Claus Peter, Kroschke Jonas
Diagnostic and Interventional Radiology, Heidelberg University Hospital, Heidelberg, Germany.
Translational Lung Research Center Heidelberg (TLRC), Member of the German Center for Lung Research (DZL), Heidelberg, Germany.
Eur Radiol. 2025 Jul;35(7):3812-3822. doi: 10.1007/s00330-024-11256-8. Epub 2025 Jan 2.
Incidentally detected pulmonary nodules present a challenge in clinical routine with demand for reliable support systems for risk classification. We aimed to evaluate the performance of the lung-cancer-prediction-convolutional-neural-network (LCP-CNN), a deep learning-based approach, in comparison to multiparametric statistical methods (Brock model and Lung-RADS®) for risk classification of nodules in cohorts with different risk profiles and underlying pulmonary diseases.
Retrospective analysis was conducted on non-contrast and contrast-enhanced CT scans containing pulmonary nodules measuring 5-30 mm. Ground truth was defined by histology or follow-up stability. The final analysis was performed on 297 patients with 422 eligible nodules, of which 105 nodules were malignant. Classification performance of the LCP-CNN, Brock model, and Lung-RADS® was evaluated in terms of diagnostic accuracy measurements including ROC-analysis for different subcohorts (total, screening, emphysema, and interstitial lung disease).
LCP-CNN demonstrated superior performance compared to the Brock model in total and screening cohorts (AUC 0.92 (95% CI: 0.89-0.94) and 0.93 (95% CI: 0.89-0.96)). Superior sensitivity of LCP-CNN was demonstrated compared to the Brock model and Lung-RADS® in total, screening, and emphysema cohorts for a risk threshold of 5%. Superior sensitivity of LCP-CNN was also shown across all disease groups compared to the Brock model at a threshold of 65%, compared to Lung-RADS® sensitivity was better or equal. No significant differences in the performance of LCP-CNN were found between subcohorts.
This study offers further evidence of the potential to integrate deep learning-based decision support systems into pulmonary nodule classification workflows, irrespective of the individual patient risk profile and underlying pulmonary disease.
Question Is a deep-learning approach (LCP-CNN) superior to multiparametric models (Brock model, Lung-RADS®) in classifying pulmonary nodule risk across varied patient profiles? Findings LCP-CNN shows superior performance in risk classification of pulmonary nodules compared to multiparametric models with no significant impact on risk profiles and structural pulmonary diseases. Clinical relevance LCP-CNN offers efficiency and accuracy, addressing limitations of traditional models, such as variations in manual measurements or lack of patient data, while producing robust results. Such approaches may therefore impact clinical work by complementing or even replacing current approaches.
偶然发现的肺结节给临床常规工作带来了挑战，需要可靠的风险分类支持系统。我们旨在评估基于深度学习的肺癌预测卷积神经网络（LCP-CNN）与多参数统计方法（Brock模型和Lung-RADS®）在不同风险特征和潜在肺部疾病队列中对结节进行风险分类的性能。
对包含5-30毫米肺结节的非增强和增强CT扫描进行回顾性分析。通过组织学或随访稳定性确定真实情况。最终对297例患者的422个符合条件的结节进行分析，其中105个结节为恶性。根据诊断准确性测量评估LCP-CNN、Brock模型和Lung-RADS®的分类性能，包括对不同亚组（总体、筛查、肺气肿和间质性肺疾病）的ROC分析。
在总体和筛查队列中，LCP-CNN的表现优于Brock模型（AUC分别为0.92（95%CI：0.89-0.94）和0.93（95%CI：0.89-0.96））。在总体、筛查和肺气肿队列中，对于5%的风险阈值，LCP-CNN的敏感性高于Brock模型和Lung-RADS®。在所有疾病组中，对于65%的阈值，LCP-CNN的敏感性也高于Brock模型，与Lung-RADS®相比，敏感性更好或相当。各亚组之间LCP-CNN的性能无显著差异。
本研究进一步证明了将基于深度学习的决策支持系统整合到肺结节分类工作流程中的潜力，无论个体患者的风险特征和潜在肺部疾病如何。
问题 在对不同患者特征的肺结节风险进行分类时，深度学习方法（LCP-CNN）是否优于多参数模型（Brock模型、Lung-RADS®）？ 发现 与多参数模型相比，LCP-CNN在肺结节风险分类中表现更优，对风险特征和结构性肺部疾病无显著影响。 临床意义 LCP-CNN提供了效率和准确性，解决了传统模型的局限性，如手动测量的差异或患者数据的缺乏，同时产生可靠的结果。因此，此类方法可能通过补充甚至取代当前方法来影响临床工作。
