Unsupervised MRI Super Resolution Using Deep External Learning and Guided Residual Dense Network With Multimodal Image Priors

• Published in: IEEE transactions on emerging topics in computational intelligence Vol. 7; no. 2; pp. 426 - 435
• Main Authors: Iwamoto, Yutaro, Takeda, Kyohei, Li, Yinhao, Shiino, Akihiko, Chen, Yen-Wei
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.04.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Artificial neural networks; Deep learning; Feature extraction; High resolution; Image enhancement; Image resolution; Magnetic resonance imaging; Medical diagnostic imaging; Medical imaging; Signal resolution; Super resolution; Three-dimensional displays; Training; unsupervised learning
• ISSN: 2471-285X; 2471-285X
• DOI: 10.1109/TETCI.2022.3215137

Deep learning techniques have led to state-of-the-art image super resolution with natural images. Normally, pairs of high-resolution and low-resolution images are used to train the deep learning models. These techniques have also been applied to medical image super-resolution. The characteristics of medical images differ significantly from natural images in several ways. First, it is difficult to obtain high-resolution images for training in real clinical applications due to the limitations of imaging systems and clinical requirements. Second, other modal high-resolution images are available (e.g., high-resolution T1-weighted images are available for enhancing low-resolution T2-weighted images). In this paper, we propose an unsupervised image super-resolution technique based on simple prior knowledge of the human anatomy. This technique does not require target T2WI high-resolution images for training. Furthermore, we present a guided residual dense network, which incorporates a residual dense network with a guided deep convolutional neural network for enhancing the resolution of low-resolution images by referring to different modal high-resolution images of the same subject. Experiments on a publicly available brain MRI database showed that our proposed method achieves better performance than the state-of-the-art methods.