Abstract:
Objective. This paper aims to propose an advanced methodology for assessing lung nodules using automated techniques with computed tomography (CT) images to detect lung cancer at an early stage.Approach. The proposed methodology utilizes a fixed-size 3 × 3 kernel in a convolution neural network (CNN) for relevant feature extraction. The network architecture comprises 13 layers, including six convolution layers for deep local and global feature extraction. The nodule detection architecture is enhanced by incorporating a transfer learning-based EfficientNetV_2 network (TLEV2N) to improve training performance. The classification of nodules is achieved by integrating the EfficientNet_V2 architecture of CNN for more accurate benign and malignant classification. The network architecture is fine-tuned to extract relevant features using a deep network while maintaining performance through suitable hyperparameters.Main results. The proposed method significantly reduces the false-negative rate, with the network achieving an accuracy of 97.56% and a specificity of 98.4%. Using the 3 × 3 kernel provides valuable insights into minute pixel variation and enables the extraction of information at a broader morphological level. The continuous responsiveness of the network to fine-tune initial values allows for further optimization possibilities, leading to the design of a standardized system capable of assessing diversified thoracic CT datasets.Significance. This paper highlights the potential of non-invasive techniques for the early detection of lung cancer through the analysis of low-dose CT images. The proposed methodology offers improved accuracy in detecting lung nodules and has the potential to enhance the overall performance of early lung cancer detection. By reconfiguring the proposed method, further advancements can be made to optimize outcomes and contribute to developing a standardized system for assessing diverse thoracic CT datasets.
摘要:
Objective.本文旨在提出一种先进的方法,用于使用具有计算机断层扫描(CT)图像的自动技术评估肺结节,以在早期检测肺癌。方法。所提出的方法在卷积神经网络(CNN)中利用固定大小的3×3内核进行相关特征提取。网络体系结构包括13层,包括六个卷积层,用于深度局部和全局特征提取。通过合并基于迁移学习的EfficientNetV_2网络(TLEV2N)来增强结节检测体系结构,以提高训练性能。结节的分类是通过整合CNN的EfficientNet_V2架构来实现的,以实现更准确的良性和恶性分类。网络架构经过微调,可以使用深度网络提取相关特征,同时通过合适的超参数保持性能。主要结果。该方法显著降低了假阴性率,该网络的准确率为97.56%,特异性为98.4%。使用3×3内核提供了对微小像素变化的有价值的见解,并能够在更广泛的形态学水平上提取信息。网络对微调初始值的连续响应允许进一步优化的可能性,导致能够评估多种胸部CT数据集的标准化系统的设计。意义。本文通过分析低剂量CT图像,重点介绍了非侵入性技术在早期发现肺癌方面的潜力。所提出的方法提高了检测肺结节的准确性,并有可能提高早期肺癌检测的整体性能。通过重新配置所提出的方法,可以进一步改进以优化结果,并有助于开发用于评估不同胸部CT数据集的标准化系统.