Bębas Ewelina, Pauk Konrad, Pauk Jolanta, Daunoravičienė Kristina, Mojsak Małgorzata, Hładuński Marcin, Domino Małgorzata, Borowska Marta
Institute of Biomedical Engineering, Bialystok University of Technology, 15-351 Białystok, Poland.
Faculty of Medicine, Warsaw Medical University, 02-091 Warszawa, Poland.
J Clin Med. 2025 Aug 15;14(16):5776. doi: 10.3390/jcm14165776.
Non-small cell lung cancer (NSCLC), the most prevalent type of lung cancer, includes subtypes such as adenocarcinoma (ADC) and squamous cell carcinoma (SCC), which require distinct management approaches. Accurately differentiating NSCLC subtypes based on diagnostic imaging remains challenging. However, the extraction of radiomic features-such as first-order statistics (FOS), second-order statistics (SOS), and fractal dimension texture analysis (FDTA) features-from magnetic resonance (MR) images supports the development of quantitative NSCLC assessments. This study aims to evaluate whether the integration of FDTA features with FOS and SOS texture features in MR image analysis improves machine learning classification of NSCLC into ADC and SCC subtypes. The study was conducted on 274 MR images, comprising ADC (n = 122) and SCC (n = 152) cases. From the segmented MR images, 93 texture features were extracted. The random forest algorithm was used to identify informative features from both FOS/SOS and combined FOS/SOS/FDTA datasets. Subsequently, the k-nearest neighbors (kNN) algorithm was applied to classify MR images as ADC or SCC. The highest performance (accuracy = 0.78, precision = 0.81, AUC = 0.89) was achieved using 37 texture features selected from the combined FOS/SOS/FDTA dataset. Incorporating fractal descriptors into the texture-based classification of lung MR images enhances the differentiation of NSCLC subtypes.
非小细胞肺癌（NSCLC）是最常见的肺癌类型，包括腺癌（ADC）和鳞状细胞癌（SCC）等亚型，这些亚型需要不同的管理方法。基于诊断成像准确区分NSCLC亚型仍然具有挑战性。然而，从磁共振（MR）图像中提取放射组学特征，如一阶统计量（FOS）、二阶统计量（SOS）和分形维纹理分析（FDTA）特征，有助于开展NSCLC的定量评估。本研究旨在评估在MR图像分析中，将FDTA特征与FOS和SOS纹理特征相结合是否能改善NSCLC的机器学习分类，以区分ADC和SCC亚型。该研究对274幅MR图像进行，包括122例ADC和152例SCC病例。从分割后的MR图像中提取了93个纹理特征。使用随机森林算法从FOS/SOS数据集以及合并后的FOS/SOS/FDTA数据集中识别出信息特征。随后，应用k近邻（kNN）算法将MR图像分类为ADC或SCC。从合并后的FOS/SOS/FDTA数据集中选择的37个纹理特征实现了最高性能（准确率=0.78，精确率=0.81，AUC=0.89）。将分形描述符纳入基于纹理的肺部MR图像分类中可增强NSCLC亚型的区分能力。
