A carregar...
Publicação
Abdominal MRI Unconditional Synthesis with Medical Assessment
| Nome: | Descrição: | Tamanho: | Formato: | |
|---|---|---|---|---|
| 2.92 MB | Adobe PDF |
Orientador(es)
Resumo(s)
Current computer vision models require a significant amount of annotated data to improve their performance in a particular task. However, obtaining the required annotated data is challenging, especially in medicine. Hence, data augmentation techniques play a crucial role. In recent years, generative models have been used to create artificial medical images, which have shown promising results. This study aimed to use a state-of-the-art generative model, StyleGAN3, to generate realistic synthetic abdominal magnetic resonance images. These images will be evaluated using quantitative metrics and qualitative assessments by medical professionals. For this purpose, an abdominal MRI dataset acquired at Garcia da Horta Hospital in Almada, Portugal, was used. A subset containing only axial gadolinium-enhanced slices was used to train the model. The obtained Fréchet inception distance value (12.89) aligned with the state of the art, and a medical expert confirmed the significant realism and quality of the images. However, specific issues were identified in the generated images, such as texture variations, visual artefacts and anatomical inconsistencies. Despite these, this work demonstrated that StyleGAN3 is a viable solution to synthesise realistic medical imaging data, particularly in abdominal imaging.
Descrição
Funding Information: This work was funded by the FCT\u2014Portuguese Foundation for Science and Technology and Bee2Fire SA under a PhD grant with reference PD/BDE/150624/2020. Publisher Copyright: © 2024 by the authors.
Palavras-chave
generative adversarial networks medical imaging synthesis MRI synthesis StyleGAN3 unconditional synthesis Computer Science (miscellaneous) Medicine (miscellaneous) Health Informatics Health Professions (miscellaneous)