Li Liangyu, Yang Jing, Por Lip Yee, Khan Mohammad Shahbaz, Hamdaoui Rim, Hussain Lal, Iqbal Zahoor, Rotaru Ionela Magdalena, Dobrotă Dan, Aldrdery Moutaz, Omar Abdulfattah
Center for Software Technology and Management, Faculty of Information Science and Technology, Universiti Kebangsaan Malaysia, 43600, Bangi, Selangor, Malaysia.
Health Informatics Laboratory, Cancer Research Institute, Chifeng Cancer Hospital (Second Affiliated Hospital of Chifeng University), Medical Department, Chifeng University, Chifeng City, Inner Mongolia Autonomous Region, 024000, China.
Heliyon. 2024 Feb 14;10(4):e26192. doi: 10.1016/j.heliyon.2024.e26192. eCollection 2024 Feb 29.
Machine learning offers significant potential for lung cancer detection, enabling early diagnosis and potentially improving patient outcomes. Feature extraction remains a crucial challenge in this domain. Combining the most relevant features can further enhance detection accuracy. This study employed a hybrid feature extraction approach, which integrates both Gray-level co-occurrence matrix (GLCM) with Haralick and autoencoder features with an autoencoder. These features were subsequently fed into supervised machine learning methods. Support Vector Machine (SVM) Radial Base Function (RBF) and SVM Gaussian achieved perfect performance measures, while SVM polynomial produced an accuracy of 99.89% when utilizing GLCM with an autoencoder, Haralick, and autoencoder features. SVM Gaussian achieved an accuracy of 99.56%, while SVM RBF achieved an accuracy of 99.35% when utilizing GLCM with Haralick features. These results demonstrate the potential of the proposed approach for developing improved diagnostic and prognostic lung cancer treatment planning and decision-making systems.
机器学习在肺癌检测方面具有巨大潜力，能够实现早期诊断并有可能改善患者预后。特征提取仍是该领域的一项关键挑战。组合最相关的特征可进一步提高检测准确率。本研究采用了一种混合特征提取方法，该方法将带有哈拉里克纹理特征的灰度共生矩阵（GLCM）与带有自动编码器的自动编码器特征相结合。随后将这些特征输入到监督式机器学习方法中。支持向量机（SVM）径向基函数（RBF）和SVM高斯核函数取得了完美的性能指标，而SVM多项式核函数在使用带有自动编码器的GLCM、哈拉里克纹理特征和自动编码器特征时，准确率达到了99.89%。使用带有哈拉里克纹理特征的GLCM时，SVM高斯核函数的准确率达到了99.56%，而SVM RBF的准确率达到了99.35%。这些结果证明了所提出的方法在开发改进的肺癌诊断和预后治疗规划及决策系统方面的潜力。
