Adjacent slices feature transformer network for single anisotropic 3D brain MRI image super-resolution. (February 2022)

• Record Type: Journal Article
• Authors: Wang, Lulu; Zhu, Huazheng; He, Zhongshi; Jia, Yuanyuan; Du, Jinglong
• Is Part Of: Biomedical signal processing and control. Volume 72(2022)Part B
• Publication Date: 2022-02
• Subjects: Convolutional neural network -- Magnetic resonance imaging -- Super-resolution -- Attention mechanism -- Multi-branch network; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2021.103339
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: A multi-branch network improves the resolution of anisotropic MRI image. Transforming adjacent slices feature to enhance the resolution of target slice. Spatial attention adaptively highlights meaningful features. Hybrid loss encourages the learning of fine contents and structures. Abstract: Magnetic resonance imaging (MRI) is widely used in clinical applications. However, due to the limitations in signal-to-noise ratio, physical properties of the scanner and scanning time, MRI images are usually acquired in low resolution, which restrains the accuracy of segmentation and recognition tasks. Recently, convolutional neural network (CNN) super-resolution methods have shown great potential in improving the resolution of MRI. Unfortunately, current methods neglect the data continuity and prior information of MRI images. In this paper, we handle the anisotropic 3D brain MRI images SR task as the problem of inserting new slices between adjacent in-plane slices. Then, we propose a novel adjacent slices feature transformer (ASFT) network to utilize the similarity of adjacent slices. Specifically, the backbone of the ASFT network consists of a series of stacked multi-branch features transformation and extraction (MFTE) blocks. In each MFTE block, we construct new spatial attention to focus on features from specific areas in reference branches and use channel attention to enhance the most valuable information. In addition, we propose a hybrid loss function with content and gradient information to refine the pixels and structures of the reconstructed image. We also introduce global residual learning to reduce the difficulty of network training. Experimental results show that the ASFT network gains the PSNR of 43.68 dB, 40.96 dB, and 41.22 dB with the scale factor of × 2 on the public Kirby21, ANVIL-adult, and MSSEG datasets, respectively. When compared with state-of-the-art MRI SR methods, the ASFT network achieves superior quantitative and qualitative performance.