Research on Lung Diagnosis Methods based on Data Augmentation

DOI

10.2991/978-94-6463-300-9_55How to use a DOI?

Keywords

Lung cancer; CT scans; Machine learning; Artificial intelligence

Abstract

The objective of this research endeavor is to propose an innovative methodology for diagnosing lung cancer through a sophisticated approach to data augmentation. In essence, the proposed method harnesses the potential of the Swin-Unet model, a unique architectural design for feature extraction and classification. Further, it employs StyleGAN3-a state-of-the-art technique from the realm of Generative Adversarial Networks - to enhance and expand the dataset. In tandem with these techniques, the Copy-Paste method is deployed to amplify the diversity and volume of the dataset, effectively bolstering the network model’s generalization capabilities. A comparative analysis, observing the impact of dataset enhancement and different data augmentation techniques on the Swin-Unet’s classification task, is conducted to validate the study’s hypothesis. The study aims to elucidate the effectiveness of using Generative Adversarial Networks for dataset expansion and their role in improving the diagnostic precision of the model used for lung cancer diagnosis. The research findings aspire to contribute valuable insights that could potentially enhance the accuracy, standardization, and efficiency of lung cancer diagnosis. This is particularly beneficial in scenarios where the available sample sizes are limited, posing challenges to effective diagnosis and treatment planning. As such, the value of the proposed method is paramount, given its potential to revolutionize current practices in lung cancer diagnostics.

Copyright

© 2023 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Ruoshi Zhu
PY  - 2023
DA  - 2023/11/27
TI  - Research on Lung Diagnosis Methods based on Data Augmentation
BT  - Proceedings of the 2023 International Conference on Image, Algorithms and Artificial Intelligence (ICIAAI 2023)
PB  - Atlantis Press
SP  - 537
EP  - 547
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-300-9_55
DO  - 10.2991/978-94-6463-300-9_55
ID  - Zhu2023
ER  -