| Title: |
Brain MRI Synthesis Using Stylegan2-ADA |
| Authors: |
Lai M.; Marzi C.; Mascalchi M.; Diciotti S. |
| Contributors: |
Lai, M.; Marzi, C.; Mascalchi, M.; Diciotti, S. |
| Publisher Information: |
IEEE Computer Society; USA; Piscataway |
| Publication Year: |
2024 |
| Collection: |
IRIS Università degli Studi di Bologna (CRIS - Current Research Information System) |
| Subject Terms: |
Alzheimer's Disease Neuroimaging Initiative (ADNI); Deep Learning (DL); Generative Adversarial Network (GAN) |
| Description: |
Deep learning (DL) applications in the medical field often face challenges related to limited data availability, resulting in issues like overfitting and imbalanced datasets. Synthetic data offers a promising solution to these problems by enabling data augmentation and enhancing the performance of DL models. In this study, we trained the state-of-the-art generative model StyleGAN2-ADA on 1412 images from the Alzheimer's disease neuroimaging initiative (ADNI) dataset to generate synthetic slices of T1-weighted brain MRI of healthy subjects. The quality of the synthetic images has been evaluated through quantitative and qualitative assessments, including a visual Turing test conducted by an expert observer with 2000 images. The observer achieved an accuracy of 52.95%, indicative of a performance level comparable to random guessing. These results demonstrate the capability of StyleGAN2-ADA to generate anatomically relevant synthetic brain MRI data. |
| Document Type: |
conference object |
| File Description: |
ELETTRONICO |
| Language: |
English |
| Relation: |
info:eu-repo/semantics/altIdentifier/wos/WOS:001305705101004; ispartofbook:Proceedings - International Symposium on Biomedical Imaging; 21st IEEE International Symposium on Biomedical Imaging, ISBI 2024; firstpage:1; lastpage:5; numberofpages:5; serie:PROCEEDINGS INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING; https://hdl.handle.net/11585/1013356; https://ieeexplore.ieee.org/document/10635279 |
| DOI: |
10.1109/ISBI56570.2024.10635279 |
| Availability: |
https://hdl.handle.net/11585/1013356; https://doi.org/10.1109/ISBI56570.2024.10635279; https://ieeexplore.ieee.org/document/10635279 |
| Rights: |
info:eu-repo/semantics/openAccess ; license:Licenza per accesso libero gratuito ; license uri:iris.PUB01 |
| Accession Number: |
edsbas.34F6558D |
| Database: |
BASE |