Zhang Tiening, Xu Zhihan, Liu Guixue, Jiang Beibei, de Bock Geertruida H, Groen Harry J M, Vliegenthart Rozemarijn, Xie Xueqian
Department of Radiation Oncology, Shanghai General Hospital, Shanghai Jiao Tong University School of Medicine, Haining Rd.100, Shanghai 200080, China.
Siemens Healthineers Ltd., Zhouzhu Rd.278, Shanghai 200120, China.
Cancers (Basel). 2021 Apr 10;13(8):1814. doi: 10.3390/cancers13081814.
To develop a machine learning-derived radiomics approach to simultaneously discriminate epidermal growth factor receptor (), Kirsten rat sarcoma viral oncogene (), Erb-B2 receptor tyrosine kinase 2 (), and tumor protein 53 () genetic mutations in patients with non-small cell lung cancer (NSCLC).
This study included consecutive patients from April 2018 to June 2020 who had histologically confirmed NSCLC, and underwent pre-surgical contrast-enhanced CT and post-surgical next-generation sequencing (NGS) tests to determine the presence of , , , and mutations. A dedicated radiomics analysis package extracted 1672 radiomic features in three dimensions. Discriminative models were established using the least absolute shrinkage and selection operator to determine the presence of , , , and mutations, based on radiomic features and relevant clinical factors.
In 134 patients (63.6 ± 8.9 years), the 20 most relevant radiomic features (13 for ) to mutations were selected to construct models. The areas under the curve (AUCs) of the combined model (radiomic features and relevant clinical factors) for discriminating and mutations were 0.78 (95% CI: 0.70-0.86), 0.81 (0.69-0.93), 0.87 (0.78-0.95), and 0.84 (0.78-0.91), respectively. In particular, the specificity to exclude mutations was 0.96 (0.87-0.99). The sensitivity to determine , , and mutations ranged from 0.82 (0.69-90) to 0.92 (0.62-0.99).
Machine learning-derived 3D radiomics can simultaneously discriminate the presence of , , , and mutations in patients with NSCLC. This noninvasive and low-cost approach may be helpful in screening patients before invasive sampling and NGS testing.
开发一种基于机器学习的放射组学方法，以同时鉴别非小细胞肺癌（NSCLC）患者的表皮生长因子受体（EGFR）、 Kirsten大鼠肉瘤病毒癌基因（KRAS）、 Erb-B2受体酪氨酸激酶2（HER2）和肿瘤蛋白53（TP53）基因突变。
本研究纳入了2018年4月至2020年6月期间组织学确诊为NSCLC的连续患者，这些患者在手术前接受了对比增强CT检查，并在手术后进行了下一代测序（NGS）检测，以确定EGFR、KRAS、HER2和TP53突变的存在情况。一个专门的放射组学分析软件包在三个维度上提取了1672个放射组学特征。基于放射组学特征和相关临床因素，使用最小绝对收缩和选择算子建立判别模型，以确定EGFR、KRAS、HER2和TP53突变的存在情况。
在134例患者（63.6±8.9岁）中，选择了与突变最相关的20个放射组学特征（EGFR为13个）来构建模型。鉴别EGFR、KRAS、HER2和TP53突变的联合模型（放射组学特征和相关临床因素）的曲线下面积（AUC）分别为0.78（95%CI：0.70-0.86）、0.81（0.69-0.93）、0.87（0.78-0.95）和0.84（0.78-0.91）。特别是，排除EGFR突变的特异性为0.96（0.87-0.99）。确定KRAS、HER2和TP53突变的敏感性范围为0.82（0.69-0.90）至0.92（0.62-0.99）。
基于机器学习的三维放射组学可以同时鉴别NSCLC患者中EGFR、KRAS、HER2和TP53突变的存在情况。这种非侵入性且低成本的方法可能有助于在进行侵入性采样和NGS检测之前对患者进行筛查。
