Yu-Sen Huang, Jenny Ling-Yu Chen, Wei-Chun Ko, Yu-Han Chang, Chin-Hao Chang, Yeun-Chung Chang
{"title":"Clinical Variables and Radiomics Features for Predicting Pneumothorax in Patients Undergoing CT-guided Transthoracic Core Needle Biopsy.","authors":"Yu-Sen Huang, Jenny Ling-Yu Chen, Wei-Chun Ko, Yu-Han Chang, Chin-Hao Chang, Yeun-Chung Chang","doi":"10.1148/ryct.230278","DOIUrl":null,"url":null,"abstract":"<p><p>Purpose To develop a prediction model combining both clinical and CT texture analysis radiomics features for predicting pneumothorax complications in patients undergoing CT-guided core needle biopsy. Materials and Methods A total of 424 patients (mean age, 65.6 years ± 12.7 [SD]; 232 male, 192 female) who underwent CT-guided core needle biopsy between January 2021 and October 2022 were retrospectively included as the training data set. Clinical and procedure-related characteristics were documented. Texture analysis radiomics features were extracted from the subpleural lung parenchyma traversed by needle. Moderate pneumothorax was defined as a postprocedure air rim of 2 cm or greater. The prediction model was developed using logistic regression with backward elimination, presented by linear fusion of the selected features weighted by their coefficients. Model performance was assessed using the area under the receiver operating characteristic curve (AUC). Validation was conducted in an external cohort (<i>n</i> = 45; mean age, 58.2 years ± 12.7; 19 male, 26 female) from a different hospital. Results Moderate pneumothorax occurred in 12.0% (51 of 424) of the training cohort and 8.9% (four of 45) of the external test cohort. Patients with emphysema (<i>P</i> < .001) or a longer needle path length (<i>P</i> = .01) exhibited a higher incidence of moderate pneumothorax in the training cohort. Texture analysis features, including gray-level co-occurrence matrix cluster shade (<i>P</i> < .001), gray-level run-length matrix low gray-level run emphasis (<i>P</i> = .049), gray-level run-length matrix run entropy (<i>P</i> = .003), gray-level size-zone matrix gray-level variance (<i>P</i> < .001), and neighboring gray-tone difference matrix complexity (<i>P</i> < .001), showed higher values in patients with moderate pneumothorax. The combined clinical-radiomics model demonstrated satisfactory performance in both the training (AUC 0.78, accuracy = 71.9%) and external test cohorts (AUC 0.86, accuracy 73.3%). Conclusion The model integrating both clinical and radiomics features offered practical diagnostic performance and accuracy for predicting moderate pneumothorax in patients undergoing CT-guided core needle biopsy. <b>Keywords:</b> Biopsy/Needle Aspiration, Thorax, CT, Pneumothorax, Core Needle Biopsy, Texture Analysis, Radiomics, CT <i>Supplemental material is available for this article</i>. © RSNA, 2024.</p>","PeriodicalId":21168,"journal":{"name":"Radiology. Cardiothoracic imaging","volume":null,"pages":null},"PeriodicalIF":3.8000,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11211933/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Radiology. Cardiothoracic imaging","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1148/ryct.230278","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING","Score":null,"Total":0}
引用次数: 0
Abstract
Purpose To develop a prediction model combining both clinical and CT texture analysis radiomics features for predicting pneumothorax complications in patients undergoing CT-guided core needle biopsy. Materials and Methods A total of 424 patients (mean age, 65.6 years ± 12.7 [SD]; 232 male, 192 female) who underwent CT-guided core needle biopsy between January 2021 and October 2022 were retrospectively included as the training data set. Clinical and procedure-related characteristics were documented. Texture analysis radiomics features were extracted from the subpleural lung parenchyma traversed by needle. Moderate pneumothorax was defined as a postprocedure air rim of 2 cm or greater. The prediction model was developed using logistic regression with backward elimination, presented by linear fusion of the selected features weighted by their coefficients. Model performance was assessed using the area under the receiver operating characteristic curve (AUC). Validation was conducted in an external cohort (n = 45; mean age, 58.2 years ± 12.7; 19 male, 26 female) from a different hospital. Results Moderate pneumothorax occurred in 12.0% (51 of 424) of the training cohort and 8.9% (four of 45) of the external test cohort. Patients with emphysema (P < .001) or a longer needle path length (P = .01) exhibited a higher incidence of moderate pneumothorax in the training cohort. Texture analysis features, including gray-level co-occurrence matrix cluster shade (P < .001), gray-level run-length matrix low gray-level run emphasis (P = .049), gray-level run-length matrix run entropy (P = .003), gray-level size-zone matrix gray-level variance (P < .001), and neighboring gray-tone difference matrix complexity (P < .001), showed higher values in patients with moderate pneumothorax. The combined clinical-radiomics model demonstrated satisfactory performance in both the training (AUC 0.78, accuracy = 71.9%) and external test cohorts (AUC 0.86, accuracy 73.3%). Conclusion The model integrating both clinical and radiomics features offered practical diagnostic performance and accuracy for predicting moderate pneumothorax in patients undergoing CT-guided core needle biopsy. Keywords: Biopsy/Needle Aspiration, Thorax, CT, Pneumothorax, Core Needle Biopsy, Texture Analysis, Radiomics, CT Supplemental material is available for this article. © RSNA, 2024.
预测 CT 引导下经胸腔穿刺活检患者气胸的临床变量和放射组学特征
目的 建立一个结合临床和CT纹理分析放射组学特征的预测模型,用于预测接受CT引导下核心穿刺活检患者的气胸并发症。材料与方法 回顾性纳入 2021 年 1 月至 2022 年 10 月期间接受 CT 引导下核心针活检的 424 例患者(平均年龄 65.6 岁 ± 12.7 [SD];男性 232 例,女性 192 例)作为训练数据集。记录了临床和手术相关特征。从穿刺针穿过的胸膜下肺实质中提取纹理分析放射组学特征。中度气胸的定义是手术后气圈大于或等于 2 厘米。预测模型的建立采用了带反向消除的逻辑回归,通过对所选特征进行线性融合,并根据其系数进行加权。模型性能通过接收者操作特征曲线下面积(AUC)进行评估。在一家不同医院的外部队列(n = 45;平均年龄 58.2 岁 ± 12.7;男性 19 人,女性 26 人)中进行了验证。结果 12.0%(424 人中有 51 人)的培训组群和 8.9%(45 人中有 4 人)的外部测试组群出现了中度气胸。在训练队列中,肺气肿患者(P < .001)或针路径长度较长的患者(P = .01)中度气胸发生率较高。纹理分析特征,包括灰度级共现矩阵群阴影(P < .001)、灰度级运行长度矩阵低灰度级运行强调度(P = .049)、灰度级运行长度矩阵运行熵(P = .003)、灰度级大小区矩阵灰度级方差(P < .001)和相邻灰度级差异矩阵复杂度(P < .001),在中度气胸患者中显示出更高的值。临床-放射组学联合模型在训练组(AUC 0.78,准确率 = 71.9%)和外部测试组(AUC 0.86,准确率 73.3%)中均表现出令人满意的性能。结论 综合临床和放射组学特征的模型在预测接受CT引导下核心针活检患者的中度气胸方面具有实用的诊断性能和准确性。关键词活检/针吸,胸部,CT,气胸,核心针活检,纹理分析,放射组学,CT 本文有补充材料。© RSNA, 2024.
本文章由计算机程序翻译,如有差异,请以英文原文为准。