LCDAE: Data Augmented Ensemble Framework for Lung Cancer Classification

Abstract

Objective: 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. Methods: 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. Results: 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%. Conclusion: 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.

ContourGAN: Auto‐contouring of organs at risk in abdomen computed tomography images using generative adversarial network

“…30,31 A fascinating development in machine learning is the invention of a technique called GANs, 10 in which two models compete with each other to make their predictions more accurate. Since their debut in 2014, GANs have excelled in generative image modeling and demonstrated exceptional performance across various medical imaging applications, including classification 32,33 and segmentation. 34 Ren et al 32 proposed a hybrid framework called LCGANT to solve the problem of lung cancer classification tasks.…”

“…Since their debut in 2014, GANs have excelled in generative image modeling and demonstrated exceptional performance across various medical imaging applications, including classification 32,33 and segmentation. 34 Ren et al 32 proposed a hybrid framework called LCGANT to solve the problem of lung cancer classification tasks. The framework consists of two parts: a deep convolutional GAN (LCGAN) that generates synthetic lung cancer images and a transfer learning model called VGG-DF that classifies lung cancer images into three classes.…”

Real‐time coloring method of laser surgery video based on generative adversarial network

“…Therefore, the computer method can be used to process the overexposed images in real‐time during the operation to obtain high‐definition and smooth surgical video. The purpose is to bring qualitative improvement in the curative effect, operation efficiency, and time of early cancer 4,5 …”

“…The purpose is to bring qualitative improvement in the curative effect, operation efficiency, and time of early cancer. 4,5 Medical endoscopy is needed in laser surgery to diagnose diseased organs in patients. 6 Current medical endoscopes mainly use CCD sensors as image sensor.…”

CA‐UNet: Convolution and attention fusion for lung nodule segmentation

“…The CoLe‐CNN proposed by Giuseppe et al obtains more features through two decoders and by using different loss functions. Ren et al proposed hybrid frameworks such as LCGANT 14 and LCDAE 15 based on convolutional neural networks to solve the overfitting problem of the model, and achieved good performance in lung cancer classification. Currently, CNN‐based methods have achieved great success in the field of medical image segmentation due to their powerful representation capabilities.…”