Zhao Fen-Hua, Fan Hong-Jie, Shan Kang-Fei, Zhou Long, Pang Zhen-Zhu, Fu Chun-Long, Yang Ze-Bin, Wu Mei-Kang, Sun Ji-Hong, Yang Xiao-Ming, Huang Zhao-Hui
Department of Radiology, Affiliated Dongyang Hospital of Wenzhou Medical University, Dongyang, China.
Department of Radiology, Sir Run Run Shaw Hospital, Zhejiang University School of Medicine, Hangzhou, China.
Front Oncol. 2022 May 12;12:872503. doi: 10.3389/fonc.2022.872503. eCollection 2022.
To establish and verify the ability of a radiomics prediction model to distinguish invasive adenocarcinoma (IAC) and minimal invasive adenocarcinoma (MIA) presenting as ground-glass nodules (GGNs).
We retrospectively analyzed 118 lung GGN images and clinical data from 106 patients in our hospital from March 2016 to April 2019. All pathological classifications of lung GGN were confirmed as IAC or MIA by two pathologists. R language software (version 3.5.1) was used for the statistical analysis of the general clinical data. ITK-SNAP (version 3.6) and A.K. software (Analysis Kit, American GE Company) were used to manually outline the regions of interest of lung GGNs and collect three-dimensional radiomics features. Patients were randomly divided into training and verification groups (ratio, 7:3). Random forest combined with hyperparameter tuning was used for feature selection and prediction modeling. The receiver operating characteristic curve and the area under the curve (AUC) were used to evaluate model prediction efficacy. The calibration curve was used to evaluate the calibration effect.
There was no significant difference between IAC and MIA in terms of age, gender, smoking history, tumor history, and lung GGN location in both the training and verification groups (P>0.05). For each lung GGN, the collected data included 396 three-dimensional radiomics features in six categories. Based on the training cohort, nine optimal radiomics features in three categories were finally screened out, and a prediction model was established. We found that the training group had a high diagnostic efficacy [accuracy, sensitivity, specificity, and AUC of the training group were 0.89 (95%CI, 0.73 - 0.99), 0.98 (95%CI, 0.78 - 1.00), 0.81 (95%CI, 0.59 - 1.00), and 0.97 (95%CI, 0.92-1.00), respectively; those of the validation group were 0.80 (95%CI, 0.58 - 0.93), 0.82 (95%CI, 0.55 - 1.00), 0.78 (95%CI, 0.57 - 1.00), and 0.92 (95%CI, 0.83 - 1.00), respectively]. The model calibration curve showed good consistency between the predicted and actual probabilities.
The radiomics prediction model established by combining random forest with hyperparameter tuning effectively distinguished IAC from MIA presenting as GGNs and represents a noninvasive, low-cost, rapid, and reproducible preoperative prediction method for clinical application.
建立并验证一种影像组学预测模型区分表现为磨玻璃结节（GGN）的浸润性腺癌（IAC）和微浸润性腺癌（MIA）的能力。
回顾性分析我院2016年3月至2019年4月106例患者的118幅肺GGN图像及临床资料。两位病理学家将所有肺GGN的病理分类确认为IAC或MIA。采用R语言软件（版本3.5.1）对一般临床资料进行统计分析。使用ITK-SNAP（版本3.6）和A.K.软件（分析套件，美国通用电气公司）手动勾勒肺GGN的感兴趣区域并收集三维影像组学特征。患者随机分为训练组和验证组（比例为7:3）。采用随机森林结合超参数调整进行特征选择和预测建模。采用受试者工作特征曲线及曲线下面积（AUC）评估模型预测效能。采用校准曲线评估校准效果。
训练组和验证组中，IAC和MIA在年龄、性别、吸烟史、肿瘤病史及肺GGN位置方面均无显著差异（P>0.05）。对于每个肺GGN，收集的数据包括六类396个三维影像组学特征。基于训练队列，最终筛选出三类九个最佳影像组学特征，并建立了预测模型。我们发现训练组具有较高的诊断效能[训练组的准确率、灵敏度、特异度及AUC分别为0.89（95%CI，0.73 - 0.99）、0.98（95%CI，0.78 - 1.00）、0.81（95%CI，0.59 - 1.00）及0.97（95%CI，0.92 - 1.00）；验证组分别为0.80（95%CI，0.58 - 0.93）、0.82（95%CI，0.55 - 1.00）、0.78（95%CI，0.57 - 1.00）及0.92（95%CI，0.83 - 1.00）]。模型校准曲线显示预测概率与实际概率之间具有良好的一致性。
通过随机森林结合超参数调整建立 的影像组学预测模型能有效区分表现为GGN的IAC和MIA，是一种无创、低成本、快速且可重复的术前预测方法，可用于临床应用。
