Lung Cancer Segmentation With Transfer Learning: Usefulness of a Pretrained Model Constructed From an Artificial Dataset Generated Using a Generative Adversarial Network

Mizuho Nishio; Koji Fujimoto; Hidetoshi Matsuo; Chisako Muramatsu; Ryo Sakamoto; Hiroshi Fujita

doi:10.3389/frai.2021.694815

Lung Cancer Segmentation With Transfer Learning: Usefulness of a Pretrained Model Constructed From an Artificial Dataset Generated Using a Generative Adversarial Network

Front Artif Intell. 2021 Jul 16:4:694815. doi: 10.3389/frai.2021.694815. eCollection 2021.

Authors

Mizuho Nishio^{1

2}, Koji Fujimoto^{1

3}, Hidetoshi Matsuo², Chisako Muramatsu⁴, Ryo Sakamoto^{1

5}, Hiroshi Fujita⁶

Affiliations

¹ Department of Diagnostic Imaging and Nuclear Medicine, Kyoto University Graduate School of Medicine, Kyoto, Japan.
² Department of Radiology, Kobe University Hospital, Kobe, Japan.
³ Department of Real World Data Research and Development, Kyoto University Graduate School of Medicine, Hikone, Japan.
⁴ Faculty of Data Science, Shiga University, Gifu, Japan.
⁵ Preemptive Medicine and Lifestyle-Related Disease Research Center, Kyoto University Hospital, Kyoto, Japan.
⁶ Department of Electrical, Electronic and Computer Engineering, Faculty of Engineering, Gifu University, Gifu, Japan.

Abstract

Purpose: The purpose of this study was to develop and evaluate lung cancer segmentation with a pretrained model and transfer learning. The pretrained model was constructed from an artificial dataset generated using a generative adversarial network (GAN). Materials and Methods: Three public datasets containing images of lung nodules/lung cancers were used: LUNA16 dataset, Decathlon lung dataset, and NSCLC radiogenomics. The LUNA16 dataset was used to generate an artificial dataset for lung cancer segmentation with the help of the GAN and 3D graph cut. Pretrained models were then constructed from the artificial dataset. Subsequently, the main segmentation model was constructed from the pretrained models and the Decathlon lung dataset. Finally, the NSCLC radiogenomics dataset was used to evaluate the main segmentation model. The Dice similarity coefficient (DSC) was used as a metric to evaluate the segmentation performance. Results: The mean DSC for the NSCLC radiogenomics dataset improved overall when using the pretrained models. At maximum, the mean DSC was 0.09 higher with the pretrained model than that without it. Conclusion: The proposed method comprising an artificial dataset and a pretrained model can improve lung cancer segmentation as confirmed in terms of the DSC metric. Moreover, the construction of the artificial dataset for the segmentation using the GAN and 3D graph cut was found to be feasible.

Keywords: computed tomography; deep learning; generative adversarial network 3; lung cancer; lung nodule; segmentation.