School of Computing and Mathematical Sciences, 4488University of Leicester, Leicester LE1 7RH, UK.
Technol Cancer Res Treat. 2022 Jan-Dec;21:15330338221124372. doi: 10.1177/15330338221124372.
The only possible solution to increase the patients' fatality rate is lung cancer early-stage detection. Recently, deep learning techniques became the most promising methods in medical image analysis compared with other numerous computer-aided diagnostic techniques. However, deep learning models always get lower performance when the model is overfitting. We present a Lung Cancer Data Augmented Ensemble (LCDAE) framework to solve the overfitting and lower performance problems in the lung cancer classification tasks. The LCDAE has 3 parts: The Lung Cancer Deep Convolutional GAN, which can synthesize images of lung cancer; A Data Augmented Ensemble model (DA-ENM), which ensembled 6 fine-tuned transfer learning models for training, testing, and validating on a lung cancer dataset; The third part is a Hybrid Data Augmentation (HDA) which combines all the data augmentation techniques in the LCDAE. By comparing with existing state-of-the-art methods, the LCDAE obtains the best accuracy of 99.99%, the precision of 99.99%, and the F1-score of 99.99%. Our proposed LCDAE can overcome the overfitting issue for the lung cancer classification tasks by applying different data augmentation techniques, our method also has the best performance compared to state-of-the-art approaches.
唯一可能增加患者死亡率的方法是肺癌早期检测。最近，与其他许多计算机辅助诊断技术相比，深度学习技术成为医学图像分析中最有前途的方法。然而，当模型过拟合时，深度学习模型的性能总是会降低。我们提出了一种肺癌数据增强集成（LCDAE）框架，以解决肺癌分类任务中的过拟合和性能下降问题。LCDAE 有 3 个部分：肺癌深度卷积生成对抗网络（Lung Cancer Deep Convolutional GAN），它可以合成肺癌图像；数据增强集成模型（Data Augmented Ensemble model，DA-ENM），它集成了 6 个经过微调的迁移学习模型，用于在肺癌数据集上进行训练、测试和验证；第三部分是混合数据增强（Hybrid Data Augmentation，HDA），它结合了 LCDAE 中的所有数据增强技术。通过与现有的最先进方法进行比较，LCDAE 在肺癌分类任务中获得了最佳的准确率 99.99%、精度 99.99%和 F1 得分 99.99%。我们提出的 LCDAE 可以通过应用不同的数据增强技术来克服肺癌分类任务中的过拟合问题，与最先进的方法相比，我们的方法也具有最佳的性能。
