Variable Augmented Network for Invertible Modality Synthesis and Fusion.

As an effective way to integrate the information contained in multiple medical images under different modalities, medical image synthesis and fusion have emerged in various clinical applications such as disease diagnosis and treatment planning. In this paper, an invertible and variable augmented network (iVAN) is proposed for medical image synthesis and fusion. In iVAN, the channel number of the network input and output is the same through variable augmentation technology, and data relevance is enhanced, which is conducive to the generation of characterization information. Meanwhile, the invertible network is used to achieve the bidirectional inference processes. Empowered by the invertible and variable augmentation schemes, iVAN not only be applied to the mappings of multi-input to one-output and multi-input to multi-output, but also to the case of one-input to multi-output. Experimental results demonstrated superior performance and potential task flexibility of the proposed method, compared with existing synthesis and fusion methods.

Virtual coil augmentation for MR coil extrapoltion via deep learning.

Magnetic resonance imaging (MRI) is a widely used medical imaging modality. However, due to the limitations in hardware, scan time, and throughput, it is often clinically challenging to obtain high-quality MR images. In this article, we propose a method of using artificial intelligence to expand the coils to achieve the goal of generating the virtual coils. The main characteristic of our work is utilizing dummy variable technology to expand/extrapolate the receive coils in both image and k-space domains. The high-dimensional information formed by coil expansion is used as the prior information to improve the reconstruction performance of parallel imaging. Two main components are incorporated into the network design, namely variable augmentation technology and sum of squares (SOS) objective function. Variable augmentation provides the network with more high-dimensional prior information, which is helpful for the network to extract the deep feature information of the data. The SOS objective function is employed to solve the deficiency of k-space data training while speeding up convergence. Experimental results demonstrated its great potentials in accelerating parallel imaging reconstruction.

Phenotypes and outcomes in middle-aged patients with diabetic foot ulcers: a retrospective cohort study.

BACKGROUND: Although ageing could increase the risk of delayed healing in diabetic foot ulcers (DFUs) patients, data from middle-aged patients remains greatly limited. The purpose of this study was to explore the clinical phenotypes, outcomes and predictive factors of DFU in middle-aged patients. METHODS: A retrospective cohort study conducted with 422 consecutive inpatients with DFUs who visited our hospital between May 2010 and September 2017; participants were recruited and assigned according to age to either the middle-aged group or the elderly group. The Demographics, ulcer characteristics, comorbidities and diabetes complications, laboratory tests, socioeconomic data and final outcomes were collected. Moreover, predictive factors of adverse outcomes in middle-aged DFUs patients were assessed. RESULTS: Middle-aged patients were more likely to have worse lifestyle and glucose control, were more likely to have microangiopathy as a complication, and tended to have larger and deeper ulcers; however, these patients also had higher rates of healing and lower rates of mortality and major amputaion than elderly patients. Severe infection,living alone,current smoking cigarettes, and having a high white blood cell count were independent risk factors for adverse outcomes in middle-aged patients. CONCLUSIONS: DFUs are relatively common in middle-aged patients with diabetes, and these patients have unique clinical phenotypes and risk profiles. Nonetheless, further investigation is needed to clarify whether intervention targeting these easily recognizable risk factors can improve healing and survival rates in middle-aged DFU patients.

Increased phosphorylation of neurogranin in the brain of hypoxic preconditioned mice.

Neurogranin/RC3 (Ng/rodent cortex-enriched mRNA clone #3), a postsynaptic neuronal protein kinase C (PKC) substrate, binds calmodulin (CaM) at low Ca(2+) levels. Neurotransmitters triggering influx calcium induce neurogranin phosphorylation by PKC in physiological or pathophysiological conditions. Phosphorylated Ng reduces the affinity of Ng to bind CaM, which may affect the activities of calmodulin-dependent downstream enzymes, such as nitric oxide synthase (NOS), CaM-dependent protein kinase II (CaMKII) and adenylate cyclase (AC). These protein enzymes have been reported to play key roles in the development of ischemic/hypoxic preconditioning (I/HPC). We previously demonstrated that activation of cPKCbetaII and gamma isoforms may be involved in the early phase of cerebral hypoxic preconditioning. However, as a substrate of PKC, the role of Ng in the onset of cerebral hypoxic preconditioning is unknown. In this study, we examined the effects of repetitive hypoxic exposure on the status of Ng phosphorylation in the cortex and hippocampus of mice. Using Western blot analysis, we found that the levels of Ng phosphorylation in the cortex and hippocampus of the hypoxic group of mice increased significantly from that of the normoxic group (p<0.05). These results suggest that neurogranin protein may be involved in the development of cerebral hypoxic preconditioning.