Magnetic resonance imaging diagnosis of acute Guillain-Barré syndrome in children

The present study examined 24 children with acute Guillain-Barre syndrome using magnetic resonance imaging （MRI） plain scans and fat-suppressed enhanced Tl-weighted imaging （T1WI） scans. Axial MRI plain scans centering on the medullary conus were positive in nine patients （38%）. These displayed variable thickening involving the cauda equina with isointensity on T1WI and isointensity or slight hyperintensity on T2WI. False negatives were obtained in patients with cervical and cranial nerve symptoms. Contrast enhancement of T1WI with fat suppression was positive in all patients in the cauda equina with varied thickening and enhancement centering on the medullary conus. Five patients （36%） were positive in the cervical nerves and 3 patients （50%） were positive in the cranial nerves. These patients had corresponding cervical and cranial nerve symptoms, respectively. Patients with serious clinical symptoms in the lower limbs exhibited obvious involvement of the cauda equina by MRI. Statistical analysis revealed a positive correlation between the extent of enlargement of the cauda equina, centering on the medullary conus, and cerebrospinal fluid protein concentration.

MRI investigation for low-grade glioma after gamma knife radiosurgery

Objective： To evaluate the therapeutic efficacy of low-grade glioma （WHO grades Ⅰ-Ⅱ） patients treated with gamma knife radiosurgery and study on the efficacy evaluation method and radiobiological effect. Methods： 140 MRI data of 52 patients after gamma knife radiosurgery were analyzed in tumor size, necrosis or cyst formation, radiation-induced edema and MRI contrast enhancement and circumsciption change for therapeutic efficacy was evaluated. Results： The efficiency rate was 84.3%. The salient efficiency rates were 54.3% for total and 30%, 36.4%, 50%, 68%, 69.2%, and 73.1% for segmenting, respectively. Aggrandizement of tumor related to MRI contrast enhancement and necrosis or cyst formation. Radiation-induced oedema occurred for 32.7%. The MRI contrast enhancement occurred for 57.7% and showed special lace-like ring while some piece-like. Conclusion： Evaluation by MRI has showed gamma knife radiosurgery is efficient for low-grade glioma. The segmenting salient efficiency rate that increase with time is better for evaluation than the efficiency rate especially for long-term MRI follow-up. Radiobiological effect affect the efficacy evaluation. MRI contrast enhancement appears after therapy and shows special as lace-like ring and partly minificates or vanishes subsequently.

A Correlative Study of CT, MR and Pathology in Rabbit Liver after Embolization by a China-Formulated Lipiodol Emulsion

OBJECTIVE To explore the MR characteristics following lipiodol retention in rabbit liver and to evaluate the sensitivity of CT （CT value 〉400 HU） and MR in displaying the hepatic degeneration and necrosis following embolization. METHODS Thirty-two rabbits were randomly divided into 3 groups. In the control group （n=8）, 2 ml of normal saline was injected into the right branch of the portal vein. In the first experimental group（n= 12）, 4 ml of lipiodol emulsion was injected into the main portal vein. In the second experimental group （n= 12）, 2 ml of lipiodol emulsion was injected into the right branch of the portal vein. CT and MR images were obtained before and after surgery in each group. The histopathologic condition was determined for all liver tissue specimens. RESULTS In the control group, CT and MR did not show any significant changes in the livers after surgery. After the operations in the experimental groups, the regional CT attenuation was 601±101 HU in the largest slice, which had no abnormal signals on T1Wl and T2Wl. In the first group, histologic examinations showed there were concentrated lipiodol droplets around the portal areas. In the second group, serious degeneration and necrosis in the right hepatic lobe occurred in 9 rabbits. T1Wl displayed homogenous or non-homogenous low signals and T2Wl mainly displayed a high signal. However, these pathologic changes did not appear on CT scanning due to high attenuation of the lipiodol. CONCLUSION There were no remarkable hepatic changes on MR in rabbits following good retention of the formulated lipiodol emulsion mixture of lipiodol and urografin（CT value 〉 400 HU）. MR displayed serious degeneration and necrosis of the liver following embolization.

Belimumab shows promise in neuropsychiatric lupus:Another challenge to find the offender

Introduction:Agents that can be used for the treatment of neuropsychiatric lupus(NPSLE)are lacking in the therapeutic armamentarium.Belimumab is a monoclonal antibody targeting the B-cell activating factor(BAFF)and is approved by the US Food and Drug Administration as an additional treatment for systemic lupus erythematosus patients with persistent disease activity and lupus nephritis(LN);however,severe active central nervous system manifestations were excluded.Case Report:We report on a treatment-naïve LN patient with refractory NPSLE complicated with progressive posterior reversible encephalopathy syndrome(PRES)who was successfully treated via the combination of mycophenolate and belimumab,resulting in reversal of persistent headache and neuroradiologic manifestations.Conclusion:Research on this topic could be relevant for identifying a possible correlation between BAFF and psychiatric NPSLE manifestations.

Long short-term memory deep learning model for predicting the dynamic performance of automotive PEMFC system

As a high efficiency hydrogen-to-power device,proton exchange membrane fuel cell(PEMFC)attracts much attention,especially for the automotive applications.Real-time prediction of output voltage and area specific resistance(ASR)via the on-board model is critical to monitor the health state of the automotive PEMFC stack.In this study,we use a transient PEMFC system model for dynamic process simulation of PEMFC to generate the dataset,and a long short-term memory(LSTM)deep learning model is developed to predict the dynamic per-formance of PEMFC.The results show that the developed LSTM deep learning model has much better perfor-mance than other models.A sensitivity analysis on the input features is performed,and three insensitive features are removed,that could slightly improve the prediction accuracy and significantly reduce the data volume.The neural structure,sequence duration,and sampling frequency are optimized.We find that the optimal sequence data duration for predicting ASR is 5 s or 20 s,and that for predicting output voltage is 40 s.The sampling frequency can be reduced from 10 Hz to 0.5 Hz and 0.25 Hz,which slightly affects the prediction accuracy,but obviously reduces the data volume and computation amount.

A novel feature susceptibility approach for a PEMFC control system based on an improved XGBoost-Boruta algorithm

Data-driven modelling methods are being developed in the quest to achieve more accurate performance prediction of protons exchange membrane fuel cell (PEMFC) systems in response to their complicated physicochemical phenomena. However, there is little research in this field detailing the pre-processing and selection of balance of plants (BOP) features for the input layer of system performance prediction at different current densities. Furthermore, most of the previous research applies neural networks based on simulation data rather than real-time bench or vehicle operation datasets which leads to low robustness and unreliable practical results. This paper details the application of a novel algorithm denoted XGBoost-Boruta, which utilises the combination of an ensemble learning approach and a wrapping approach, to improve the robustness of feature selection and to increase the accuracy and robustness of PEMFC system performance prediction. By introduction of the Z score and shadow features to eliminate the randomness of conventional ensemble learning methods, seven key controllable BOP variables of the hydrogen anode, air cathode and cooling subsystems are selected as the original input variables to determine their dependency on the stack voltage. Two case studies are presented for verification and validation of the proposed algorithm based on the real-time dataset of bench experimental data and data obtained from heavy truck operation at current densities ranging from 100 to 1500 mA/cm2. The feature selection strategy, based on the proposed XGBoost-Boruta algorithm, largely decreases the RMSE by 23.8% and 14.1% and the R^(2) increases by 0.06 and 0.04 of both the bench experimental and the heavy truck validation datasets respectively.

Failure mode investigation of fuel cell for vehicle application

The durability of proton exchange membrane fuel cells （PEMFCs） has been posing a key technical challenge to commercial spread of fuel cell vehicles （FCVs）. To improve the durability, it is necessary to optimize the fuel cell system （FCS） design against failure modes. The fuel cell durability research method at FCS scale was exhibited, and the failure modes of fuel cell were experimentally investigated in this paper. It is found that the fuel cell dry operation, start/stop cycle and gas diffusion layer （GDL） flooding are typical failure modes of fuel cells. After the modifications against the failure modes, the durability of FCSs is improved to over 3000 h step by step.

Data-based flooding fault diagnosis of proton exchange membrane fuel cell systems using LSTM networks

Flooding fault diagnosis is critical to the stable and efficient operation of fuel cells,while the on-board embedded controller has limited computing power and sensors,making it difficult to incorporate the complex gas-liquid two-phase flow models.Then in fuel cell system for cars,the neural network modeling is usually regarded as an appropriate tool for the on-line diagnosis of water status.Traditional neural network classifiers are not good at processing time series data,so in this paper,Long Short-Term Memory(LSTM)network model is developed and applied to the flooding fault diagnosis based on the embedded platform.Moreover,the fuel cell auxiliary system statuses are adopted as the inputs of the diagnosis network,which avoids installing a large number of sensors in the fuel cell system,and contributes to reduce the total system cost.The bench test on the 92 kW vehicle fuel cell system proved that this model can effectively diagnose/pre-diagnose the fuel cell flooding,and thus help optimize the water management under vehicle conditions.