1. RSUIR at Rangsit University
  2. RSU Digital Collection
  3. วิทยาลัยวิศวกรรมชีวการแพทย์ COLLEGE OF BIOMEDICAL ENGINEERING
  4. BioEng-BE-D-Thesis
Please use this identifier to cite or link to this item: https://rsuir-library.rsu.ac.th/handle/123456789/2833
Full metadata record
DC FieldValueLanguage
dc.contributor.advisorJamie A. O'Reilly-
dc.contributor.authorAsadi, Fawad-
dc.date.accessioned2025-09-15T06:50:36Z-
dc.date.available2025-09-15T06:50:36Z-
dc.date.issued2024-
dc.identifier.urihttps://rsuir-library.rsu.ac.th/handle/123456789/2833-
dc.descriptionDissertation (D.Eng. (Biomedical Engineering)) -- Rangsit University, 2023en_US
dc.language.isoenen_US
dc.publisherRangsit Universityen_US
dc.subjectGenerative Adversarial Networksen_US
dc.subjectPerformance -- Evaluationen_US
dc.subjectComputational intelligenceen_US
dc.subjectArtificial intelligencen_US
dc.titleSynthetic data for deep learning medical applications : generation, evaluation, and utilizationen_US
dc.typeThesisen_US
dc.description.other-abstractDeep learning algorithms show promise in medicine for tasks like diagnosis, treatment planning, and health monitoring due to their ability to analyze diverse data and detect complex patterns, though their development is hindered by constraints such as the need for large, labeled, high-quality, and unbiased training datasets, posing challenges in their collection and preparation. Generative adversarial networks (GANs) can potentially address challenges. This research involved training progressively growing GAN (PGGAN) to generate synthetic computed tomography (CT) images of the lungs, investigating the impact of weight initialization methods on Inception v3 performance, and employing StyleGAN2 with adaptive discriminator augmentation (ADA) to generate synthetic fluid-attenuated inversion recovery (FLAIR) magnetic resonance (MRI) images with corresponding masks for deep learning training. The initial findings indicated that synthetic images generated by the PGGAN resembled real images, but there was room for improvement in GAN's performance. The subsequent study emphasized the superiority of pre-trained weights over randomly initialized models. Lastly, StyleGAN2-ADA performed well with a Fréchet inception distance (FID) score of 14.39. The addition of synthetic images did not significantly impact Unets' performance, but geometric augmentation alongside synthetic images enhanced generalization. Overall, despite their modest impact on training, synthetic data holds the potential to address data collection challenges, warranting broader exploration across other deep learning applications beyond segmentation tasks.en_US
dc.description.degree-nameDoctor of Engineeringen_US
dc.description.degree-levelDoctoral Degreeen_US
dc.contributor.degree-disciplineBiomedical Engineeringen_US
Appears in Collections:BioEng-BE-D-Thesis

Files in This Item:
File Description SizeFormat 
FAWAD ASADI.pdf3.15 MBAdobe PDFView/Open
Show simple item record


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.