计算机科学
人工智能
先验概率
推论
深度学习
迭代重建
模式识别(心理学)
一致性(知识库)
对抗制
无监督学习
机器学习
贝叶斯概率
作者
Yilmaz Korkmaz,Salman Uh. Dar,Mahmut Yurt,Muzaffer Özbey,Tolga Çukur
出处
期刊:IEEE Transactions on Medical Imaging
[Institute of Electrical and Electronics Engineers]
日期:2022-07-01
卷期号:41 (7): 1747-1763
被引量:60
标识
DOI:10.1109/tmi.2022.3147426
摘要
Supervised reconstruction models are characteristically trained on matched pairs of undersampled and fully-sampled data to capture an MRI prior, along with supervision regarding the imaging operator to enforce data consistency. To reduce supervision requirements, the recent deep image prior framework instead conjoins untrained MRI priors with the imaging operator during inference. Yet, canonical convolutional architectures are suboptimal in capturing long-range relationships, and priors based on randomly initialized networks may yield suboptimal performance. To address these limitations, here we introduce a novel unsupervised MRI reconstruction method based on zero-Shot Learned Adversarial TransformERs (SLATER). SLATER embodies a deep adversarial network with cross-attention transformers to map noise and latent variables onto coil-combined MR images. During pre-training, this unconditional network learns a high-quality MRI prior in an unsupervised generative modeling task. During inference, a zero-shot reconstruction is then performed by incorporating the imaging operator and optimizing the prior to maximize consistency to undersampled data. Comprehensive experiments on brain MRI datasets clearly demonstrate the superior performance of SLATER against state-of-the-art unsupervised methods.
科研通智能强力驱动
Strongly Powered by AbleSci AI