Shi Wensong, Hu Yuzhui, Chang Guotao, Qian He, Yang Yulun, Song Yinsen, Wei Zhengpan, Gao Liang, Yi Hang, Wu Sikai, Wang Kun, Huo Huandong, Wang Shuaibo, Mao Yousheng, Ai Siyuan, Zhao Liang, Li Xiangnan, Zheng Huiyu
Department of Thoracic Surgery, The Fifth Clinical Medical College of Henan, University of Chinese Medicine (Zhengzhou People's Hospital), Zhengzhou, 450003, China.
Department of Thoracic Surgery, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, 450052, China.
BMC Med Imaging. 2025 Jan 17;25(1):21. doi: 10.1186/s12880-024-01533-9.
In clinical practice, diagnosing the benignity and malignancy of solid-component-predominant pulmonary nodules is challenging, especially when 3D consolidation-to-tumor ratio (CTR) ≥ 50%, as malignant ones are more invasive. This study aims to develop and validate an AI-driven radiomics prediction model for such nodules to enhance diagnostic accuracy.
Data of 2,591 pulmonary nodules from five medical centers (Zhengzhou People's Hospital, etc.) were collected. Applying exclusion criteria, 370 nodules (78 benign, 292 malignant) with 3D CTR ≥ 50% were selected and randomly split 7:3 into training and validation cohorts. Using R programming, Lasso regression with 10-fold cross-validation filtered features, followed by univariate and multivariate logistic regression to construct the model. Its efficacy was evaluated by ROC, DCA curves and calibration plots.
Lasso regression picked 18 non-zero coefficients from 108 features. Three significant factors-patient age, solid component volume and mean CT value-were identified. The logistic regression equation was formulated. In the training set, the ROC AUC was 0.721 (95%CI: 0.642-0.801); in the validation set, AUC was 0.757 (95%CI: 0.632-0.881), showing the model's stability and predictive ability.
The model has moderate accuracy in differentiating benign from malignant 3D CTR ≥ 50% nodules, holding clinical potential. Future efforts could explore more to improve its precision and value.
Not applicable.
在临床实践中，诊断以实性成分为主的肺结节的良恶性具有挑战性，尤其是当三维实变与肿瘤比率（CTR）≥50%时，因为恶性结节具有更强的侵袭性。本研究旨在开发并验证一种用于此类结节的人工智能驱动的放射组学预测模型，以提高诊断准确性。
收集了来自五个医疗中心（郑州市人民医院等）的2591个肺结节的数据。应用排除标准，选择了370个三维CTR≥50%的结节（78个良性，292个恶性），并随机按7:3比例分为训练组和验证组。使用R编程，通过10倍交叉验证的Lasso回归筛选特征，随后进行单变量和多变量逻辑回归以构建模型。通过ROC、DCA曲线和校准图评估其效能。
Lasso回归从108个特征中挑选出18个非零系数。确定了三个显著因素——患者年龄、实性成分体积和平均CT值。制定了逻辑回归方程。在训练集中，ROC曲线下面积（AUC）为0.721（95%CI：0.642 - 0.801）；在验证集中，AUC为0.757（95%CI：0.632 - 0.881），显示了模型的稳定性和预测能力。
该模型在区分三维CTR≥50%的良恶性结节方面具有中等准确性，具有临床应用潜力。未来可进一步探索以提高其精度和价值。
不适用。
