期刊
MEDICAL IMAGE ANALYSIS
卷 70, 期 -, 页码 -出版社
ELSEVIER
DOI: 10.1016/j.media.2020.101944
关键词
Magnetic resonance imaging (MRI); Multi-contrast; Generative adversarial networks (GAN); Image synthesis; Multi-stream; Fusion
类别
资金
- European Molecular Biology Organization Installation Grant [IG 3028]
- TUBA GEBIP 2015 fellowship
- TUBITAK 1001 Research Grant [118E256]
- NVIDIA under a GPU grant
- TUBA GEBIP 2018 fellowship
- BAGEP 2017 fellowship
Multi-contrast MRI protocols provide more morphological information for diagnosis, but the number and quality of contrasts are limited in practice due to factors like scan time and patient motion. A proposed multi-stream approach aggregates information from multiple source images, combining multiple one-to-one streams and a joint many-to-one stream to enhance image synthesis performance.
Multi-contrast MRI protocols increase the level of morphological information available for diagnosis. Yet, the number and quality of contrasts are limited in practice by various factors including scan time and patient motion. Synthesis of missing or corrupted contrasts from other high-quality ones can alleviate this limitation. When a single target contrast is of interest, common approaches for multi-contrast MRI involve either one-to-one or many-to-one synthesis methods depending on their input. One-to-one methods take as input a single source contrast, and they learn a latent representation sensitive to unique features of the source. Meanwhile, many-to-one methods receive multiple distinct sources, and they learn a shared latent representation more sensitive to common features across sources. For enhanced image synthesis, we propose a multi-stream approach that aggregates information across multiple source images via a mixture of multiple one-to-one streams and a joint many-to-one stream. The complementary feature maps generated in the one-to-one streams and the shared feature maps generated in the many to-one stream are combined with a fusion block. The location of the fusion block is adaptively modified to maximize task-specific performance. Quantitative and radiological assessments on T-1,- T-2-, PD-weighted, and FLAIR images clearly demonstrate the superior performance of the proposed method compared to previous state-of-the-art one-to-one and many-to-one methods. (C) 2020 Elsevier B.V. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据