Contrast enhanced MRI synthesis on glioma subjects using generative adversarial networks
Résumé
Magnetic resonance imaging (MRI) provides detailed anatomical information critical for radiologists in assessing and diagnosing. Moreover, omplementary information obtained from multiple contrasts MRI can improve the clarity of internal structures, specially in detecting unusual objects. However, acquiring contrast-enhanced MRI is usually time-consuming, expensive or requires contrast agent injection. Medical image synthesis has been demonstrated as an effective alternative. Within the scope of project, we aim to provide non-invasive method to synthesize contrast-enhanced MRI from given MRI modality. We present different generative frameworks to learn the mappings between T1-weighted and constrasted T1 MRI.
Frameworks jointly exploit different features between cross modalities to resolve the challenging complexity in synthesis. Methods are trained on multimodal brain MRI dataset consisting of different contrasts samples. Quantitative assessments were made through computing peak signal-to-noise ratio, structural similarity index measurement. Results on synthesized output are clear with a low distortion, showing the potential of study in
practice.