School of Computer and Information Technology, Beijing Jiaotong University, Beijing, 100044, China.
Beijing Advanced Innovation Center for Biomedical Engineering, Beihang University, Beijing, 100083, China.
Med Phys. 2019 Jul;46(7):3091-3100. doi: 10.1002/mp.13551. Epub 2019 May 11.
Histological subtypes of non-small cell lung cancer (NSCLC) are crucial for systematic treatment decisions. However, the current studies which used noninvasive radiomic methods to classify NSCLC histology subtypes mainly focused on two main subtypes: squamous cell carcinoma (SCC) and adenocarcinoma (ADC), while multi-subtype classifications that included the other two subtypes of NSCLC: large cell carcinoma (LCC) and not otherwise specified (NOS), were very few in the previous studies. The aim of this work was to establish a multi-subtype classification model for the four main subtypes of NSCLC and improve the classification performance and generalization ability compared with previous studies.
In this work, we extracted 1029 features from regions of interest in computed tomography (CT) images of 349 patients from two different datasets using radiomic methods. Based on "three-in-one" concept, we proposed a model called SLS wrapping three algorithms, synthetic minority oversampling technique, ℓ2,1-norm minimization, and support vector machines, into one hybrid technique to classify the four main subtypes of NSCLC: SCC, ADC, LCC, and NOS, which could cover the whole range of NSCLC.
We analyzed the 247 features obtained by dimension reduction, and found that the extracted features from three methods: first order statistics, gray level co-occurrence matrix, and gray level size zone matrix, were more conducive to the classification of NSCLC subtypes. The proposed SLS model achieved an average classification accuracy of 0.89 on the training set (95% confidence interval [CI]: 0.846 to 0.912) and a classification accuracy of 0.86 on the test set (95% CI: 0.779 to 0.941).
The experiment results showed that the subtypes of NSCLC could be well classified by radiomic method. Our SLS model can accurately classify and diagnose the four subtypes of NSCLC based on CT images, and thus it has the potential to be used in the clinical practice to provide valuable information for lung cancer treatment and further promote the personalized medicine.
非小细胞肺癌（NSCLC）的组织学亚型对系统治疗决策至关重要。然而，目前使用非侵入性放射组学方法对 NSCLC 组织学亚型进行分类的研究主要集中在两种主要亚型：鳞状细胞癌（SCC）和腺癌（ADC），而之前的研究中很少有包括 NSCLC 的其他两种亚型：大细胞癌（LCC）和未特指型（NOS）的多亚型分类。本研究旨在建立 NSCLC 四种主要亚型的多亚型分类模型，并提高与之前研究相比的分类性能和泛化能力。
本研究使用放射组学方法从两个不同数据集的 349 名患者的 CT 图像的感兴趣区域中提取了 1029 个特征。基于“三位一体”的概念，我们提出了一种名为 SLS 的模型，它将三种算法（合成少数过采样技术、ℓ2,1-范数最小化和支持向量机）集成到一种混合技术中，用于分类 NSCLC 的四种主要亚型：SCC、ADC、LCC 和 NOS，涵盖了 NSCLC 的整个范围。
我们对降维得到的 247 个特征进行了分析，发现从三种方法（一阶统计量、灰度共生矩阵和灰度大小区域矩阵）中提取的特征更有助于 NSCLC 亚型的分类。所提出的 SLS 模型在训练集上的平均分类准确率为 0.89（95%置信区间 [CI]：0.846 至 0.912），在测试集上的分类准确率为 0.86（95% CI：0.779 至 0.941）。
实验结果表明，放射组学方法可以很好地对 NSCLC 亚型进行分类。我们的 SLS 模型可以基于 CT 图像准确地对 NSCLC 的四种亚型进行分类和诊断，因此它有可能在临床实践中使用，为肺癌治疗提供有价值的信息，并进一步促进个性化医疗。
Zotero 插件