Generative Adversarial Network (GAN) for Medical Image Synthesis and Augmentation

Simple item page
dc.contributor.advisorHuang, Jimmy
dc.contributor.authorLiang, Zhaohui
dc.date.accessioned2023-03-28T21:19:57Z
dc.date.available2023-03-28T21:19:57Z
dc.date.copyright2022-12-01
dc.date.issued2023-03-28
dc.date.updated2023-03-28T21:19:57Z
dc.degree.disciplineComputer Science
dc.degree.levelDoctoral
dc.degree.namePhD - Doctor of Philosophy
dc.description.abstractMedical image processing aided by artificial intelligence (AI) and machine learning (ML) significantly improves medical diagnosis and decision making. However, the difficulty to access well-annotated medical images becomes one of the main constraints on further improving this technology. Generative adversarial network (GAN) is a DNN framework for data synthetization, which provides a practical solution for medical image augmentation and translation. In this study, we first perform a quantitative survey on the published studies on GAN for medical image processing since 2017. Then a novel adaptive cycle-consistent adversarial network (Ad CycleGAN) is proposed. We respectively use a malaria blood cell dataset (19,578 images) and a COVID-19 chest X-ray dataset (2,347 images) to test the new Ad CycleGAN. The quantitative metrics include mean squared error (MSE), root mean squared error (RMSE), peak signal-to-noise ratio (PSNR), universal image quality index (UIQI), spatial correlation coefficient (SCC), spectral angle mapper (SAM), visual information fidelity (VIF), Frechet inception distance (FID), and the classification accuracy of the synthetic images. The CycleGAN and variant autoencoder (VAE) are also implemented and evaluated as comparison. The experiment results on malaria blood cell images indicate that the Ad CycleGAN generates more valid images compared to CycleGAN or VAE. The synthetic images by Ad CycleGAN or CycleGAN have better quality than those by VAE. The synthetic images by Ad CycleGAN have the highest accuracy of 99.61%. In the experiment on COVID-19 chest X-ray, the synthetic images by Ad CycleGAN or CycleGAN have higher quality than those generated by variant autoencoder (VAE). However, the synthetic images generated through the homogenous image augmentation process have better quality than those synthesized through the image translation process. The synthetic images by Ad CycleGAN have higher accuracy of 95.31% compared to the accuracy of the images by CycleGAN of 93.75%. In conclusion, the proposed Ad CycleGAN provides a new path to synthesize medical images with desired diagnostic or pathological patterns. It is considered a new approach of conditional GAN with effective control power upon the synthetic image domain. The findings offer a new path to improve the deep neural network performance in medical image processing.
dc.identifier.urihttp://hdl.handle.net/10315/41011
dc.languageen
dc.rightsAuthor owns copyright, except where explicitly noted. Please contact the author directly with licensing requests.
dc.subjectComputer science
dc.subjectArtificial intelligence
dc.subjectInformation science
dc.subject.keywordsDeep neural network
dc.subject.keywordsDeep learning
dc.subject.keywordsGenerative adversarial network
dc.subject.keywordsImage processing
dc.subject.keywordsMedical informatics
dc.subject.keywordsComputer simulation
dc.subject.keywordsMachine learning
dc.titleGenerative Adversarial Network (GAN) for Medical Image Synthesis and Augmentation
dc.typeElectronic Thesis or Dissertation

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Liang_Zhaohui_2022_PhD_resubmit.pdf
Size:
3.74 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 2 of 2
No Thumbnail Available
Name:
license.txt
Size:
1.87 KB
Format:
Plain Text
Description:
Download
No Thumbnail Available
Name:
YorkU_ETDlicense.txt
Size:
3.39 KB
Format:
Plain Text
Description:
Download

Collections

Computer Science

All items in the YorkSpace institutional repository are protected by copyright, with all rights reserved except where explicitly noted.