Deep learning for MRI-based CT synthesis: a comparison of MRI sequences and neural network architectures
| Autor: | Andrés Larroza, Laura Moliner, Sandra Oliver, Marina Vergara-Diaz, Maria J. Rodriguez-Alvarez, Juan M. Alvarez-Gomez, Hector Espinos-Morato |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2019 |
| Předmět: |
Artificial neural network
medicine.diagnostic_test Computer science business.industry Deep learning Magnetic resonance imaging Pattern recognition Image processing 02 engineering and technology 030218 nuclear medicine & medical imaging 03 medical and health sciences 0302 clinical medicine Positron emission tomography 0202 electrical engineering electronic engineering information engineering medicine 020201 artificial intelligence & image processing Segmentation Artificial intelligence business MATEMATICA APLICADA Correction for attenuation Entire head |
| Zdroj: | RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia instname |
| DOI: | 10.1109/nss/mic42101.2019.9060051 |
| Popis: | [EN] Synthetic computed tomography (CT) images derived from magnetic resonance images (MRI) are of interest for radiotherapy planning and positron emission tomography (PET) attenuation correction. In recent years, deep learning implementations have demonstrated improvement over atlasbased and segmentation-based methods. Nevertheless, several open questions remain to be addressed, such as which is the best of MRI sequences and neural network architectures. In this work, we compared the performance of different combinations of two common MRI sequences (T1- and T2-weighted), and three state-of-the-art neural networks designed for medical image processing (Vnet, HighRes3dNet and ScaleNet). The experiments were conducted on brain datasets from a public database. Our results suggest that T1 images perform better than T2, but the results further improve when combining both sequences. The lowest mean average error over the entire head (MAE = 101.76 ± 10.4 HU) was achieved combining T1 and T2 scans with HighRes3dNet. All tested deep learning models achieved significantly lower MAE (p < 0.01) than a well-known atlas-based method. This work was supported by the Spanish Government grants TEC2016-79884-C2 and RTC-2016-5186-1, and by the European Union through the European Regional Development Fund (ERDF) |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|