Single MR image super-resolution via channel splitting and serial fusion network

In magnetic resonance imaging (MRI), spatial resolution is an important and critical imaging parameter that represents how much information is contained in a unit space. Acquiring high-resolution MRI data usually takes a long scanning time and is subject to motion artifacts due to hardware, physical, and physiological limitations. Single image super-resolution (SISR) based on deep learning is an effective and promising alternative technique to improve the native spatial resolution of magnetic resonance (MR) images. However, because of the simple diversity and single distribution of training samples, the effective training of deep models with medical training samples and improvement of the tradeoff between model performance and computing overhead are major challenges. In addition, deeper networks are more difficult to effectively train since the information is gradually weakened as the network deepens. In this paper, a novel channel splitting and serial fusion network (CSSFN) is presented for single MR image super-resolution. The proposed CSSFN splits hierarchical features into a series of subfeatures, which are then integrated together in a serial manner. Hence, the network becomes deeper and can discriminatively and reasonably deal with the subfeatures. Moreover, a dense global feature fusion (DGFF) is adopted to integrate the intermediate features, which further promotes the information flow in the network and helps to stabilize model training. Extensive experiments on several typical MR images show the superiority of our CSSFN models to other advanced SISR methods. • The compromise between model performance and computational overhead for MR image SR is improved by introducing a novel Serial Local Feature Fusion (SLFF) strategy. • We ease the dilemma between the trainability and network scale caused by the degradation of MR training samples. • Through pseudo 3D experiments, we confirm the speculation that degraded training samples are more likely to cause the fitting problem of large-scale deep models. • Aggressive channel splitting will exacerbate the problem of model fitting though it initially helps to reduce the risk of over-/under-fitting.