Improving GAN Learning Dynamics for Thyroid Nodule Segmentation
Issued Date
2023-02-01
Resource Type
ISSN
03015629
eISSN
1879291X
Scopus ID
2-s2.0-85143613347
Pubmed ID
36424307
Journal Title
Ultrasound in Medicine and Biology
Volume
49
Issue
2
Start Page
416
End Page
430
Rights Holder(s)
SCOPUS
Bibliographic Citation
Ultrasound in Medicine and Biology Vol.49 No.2 (2023) , 416-430
Suggested Citation
Kunapinun A., Dailey M.N., Songsaeng D., Parnichkun M., Keatmanee C., Ekpanyapong M. Improving GAN Learning Dynamics for Thyroid Nodule Segmentation. Ultrasound in Medicine and Biology Vol.49 No.2 (2023) , 416-430. 430. doi:10.1016/j.ultrasmedbio.2022.09.010 Retrieved from: https://repository.li.mahidol.ac.th/handle/20.500.14594/81677
Title
Improving GAN Learning Dynamics for Thyroid Nodule Segmentation
Author's Affiliation
Other Contributor(s)
Abstract
Thyroid nodules are lesions requiring diagnosis and follow-up. Tools for detecting and segmenting nodules can help physicians with this diagnosis. Besides immediate diagnosis, automated tools can also enable tracking of the probability of malignancy over time. This paper demonstrates a new algorithm for segmenting thyroid nodules in ultrasound images. The algorithm combines traditional supervised semantic segmentation with unsupervised learning using GANs. The hybrid approach has the potential to upgrade the semantic segmentation model's performance, but GANs have the well-known problems of unstable learning and mode collapse. To stabilize the training of the GAN model, we introduce the concept of closed-loop control of the gain on the loss output of the discriminator. We find gain control leads to smoother generator training and avoids the mode collapse that typically occurs when the discriminator learns too quickly relative to the generator. We also find that the combination of the supervised and unsupervised learning styles encourages both low-level accuracy and high-level consistency. As a test of the concept of controlled hybrid supervised and unsupervised semantic segmentation, we introduce a new model named the StableSeg GAN. The model uses DeeplabV3+ as the generator, Resnet18 as the discriminator, and uses PID control to stabilize the GAN learning process. The performance of the new model in terms of IoU is better than DeeplabV3+, with mean IoU of 81.26% on a challenging test set. The results of our thyroid nodule segmentation experiments show that StableSeg GANs have flexibility to segment nodules more accurately than either comparable supervised segmentation models or uncontrolled GANs.