Journal
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
Volume 34, Issue 11, Pages 8802-8814Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TNNLS.2022.3153088
Keywords
Wavelet domain; Magnetic resonance imaging; Generative adversarial networks; Task analysis; Image reconstruction; Hafnium; Discrete wavelet transforms; Discrete wavelet transformation; generative adversarial network (GAN); magnetic resonance (MR) imaging; super-resolution (SR); textures enhance
Ask authors/readers for more resources
Magnetic resonance (MR) imaging is crucial in clinical and brain exploration, yet it is challenging to acquire high-resolution MR images due to hardware limitations, scanning time, and cost. In this article, the authors propose FP-GANs, a model that uses divide-and-conquer approach to generate super-resolution MR images. The model separates and processes the low-frequency and high-frequency components of MR images and achieves better structure recovery and classification performance.
Magnetic resonance (MR) imaging plays an important role in clinical and brain exploration. However, limited by factors such as imaging hardware, scanning time, and cost, it is challenging to acquire high-resolution MR images clinically. In this article, fine perceptive generative adversarial networks (FP-GANs) are proposed to produce super-resolution (SR) MR images from the low-resolution counterparts. By adopting the divide-and-conquer scheme, FP-GANs are designed to deal with the low-frequency (LF) and high-frequency (HF) components of MR images separately and parallelly. Specifically, FP-GANs first decompose an MR image into LF global approximation and HF anatomical texture subbands in the wavelet domain. Then, each subband generative adversarial network (GAN) simultaneously concentrates on super-resolving the corresponding subband image. In generator, multiple residual-in-residual dense blocks are introduced for better feature extraction. In addition, the texture-enhancing module is designed to trade off the weight between global topology and detailed textures. Finally, the reconstruction of the whole image is considered by integrating inverse discrete wavelet transformation in FP-GANs. Comprehensive experiments on the MultiRes_7T and ADNI datasets demonstrate that the proposed model achieves finer structure recovery and outperforms the competing methods quantitatively and qualitatively. Moreover, FP-GANs further show the value by applying the SR results in classification tasks.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available