Skull segmentation in magnetic resonance image(MRI)provides realistic skull models for MEG and EEG positive problems.An MRI skull segmentation method based on bi-stream pyramid decoder and deep supervision(BiNETR)is proposed to solve the problem of difficult segmentation due to the blurred and complex structure of MRI skull imaging.The method uses a bi-stream pyramid decoder as the main decoder in the network structure of encoding-decoding,including serial dual decoders for edge information oriented and precise feature merging.Specifically,edge information oriented pyramid decoder effectively enhances the edge information based on feature sharpening to improve the edge segmentation accuracy,and the precise feature merging pyramid decoder further refines and reuses the edge-enhanced features to promote the fusion of deep and shallow features.In addition,deep supervised computation of intermediate feature loss is introduced to implant the gradient into the deep network for enhancing network training.The segmentation algorithm is validated on the skull dataset,achieving a Dice similarity coefficient of 0.880±0.039 and an average symmetric surface distance of(0.931±0.286)mm,outperforming other state-of-the-art methods.The experimental results demonstrate the effectiveness and accuracy of the proposed algorithm in MRI skull segmentation.

A self-supervised super-resolution reconstruction method based on scale adaptive and coordinate encoding is proposed to realize super-resolution reconstruction of anisotropic brain magnetic resonance images with different slice thicknesses even in the absence of paired isotropic brain magnetic resonance images.Firstly,an image encoding module that integrates super-resolution scale information is used to learn the specific features of images with different slice thicknesses.Subsequently,a coordinate encoding module is employed to facilitate the deep fusion of coordinate information and image features.Finally,an overall loss function comprising reconstruction loss and brain tissue edge perception loss is adopted to optimize the recovery of edge high-frequency information,while global residual learning is introduced to enhance network training.Experimental results on the HCP-1200 and OASIS-1 datasets demonstrate that the proposed method outperforms other self-supervised super-resolution reconstruction methods.

A self-supervised super-resolution reconstruction method based on scale adaptive and coordinate encoding is proposed to realize super-resolution reconstruction of anisotropic brain magnetic resonance images with different slice thicknesses even in the absence of paired isotropic brain magnetic resonance images.Firstly,an image encoding module that integrates super-resolution scale information is used to learn the specific features of images with different slice thicknesses.Subsequently,a coordinate encoding module is employed to facilitate the deep fusion of coordinate information and image features.Finally,an overall loss function comprising reconstruction loss and brain tissue edge perception loss is adopted to optimize the recovery of edge high-frequency information,while global residual learning is introduced to enhance network training.Experimental results on the HCP-1200 and OASIS-1 datasets demonstrate that the proposed method outperforms other self-supervised super-resolution reconstruction methods.

Skull segmentation in magnetic resonance image(MRI)provides realistic skull models for MEG and EEG positive problems.An MRI skull segmentation method based on bi-stream pyramid decoder and deep supervision(BiNETR)is proposed to solve the problem of difficult segmentation due to the blurred and complex structure of MRI skull imaging.The method uses a bi-stream pyramid decoder as the main decoder in the network structure of encoding-decoding,including serial dual decoders for edge information oriented and precise feature merging.Specifically,edge information oriented pyramid decoder effectively enhances the edge information based on feature sharpening to improve the edge segmentation accuracy,and the precise feature merging pyramid decoder further refines and reuses the edge-enhanced features to promote the fusion of deep and shallow features.In addition,deep supervised computation of intermediate feature loss is introduced to implant the gradient into the deep network for enhancing network training.The segmentation algorithm is validated on the skull dataset,achieving a Dice similarity coefficient of 0.880±0.039 and an average symmetric surface distance of(0.931±0.286)mm,outperforming other state-of-the-art methods.The experimental results demonstrate the effectiveness and accuracy of the proposed algorithm in MRI skull segmentation.

Objective:To explore the relationship between childhood trauma and anxiety in vocational school students, and to analyze the mediating role of emotion dysregulation.Methods:A cross-sectional survey was conducted in one vocational school in Ganzhou, all students completed a series of questionnaires, including the childhood trauma questionnaire (CTQ), difficulties in emotion regulation scale (DERS), and generalized anxiety disorder scale (GAD-7).The cut-off score for anxiety symptom was set GAD-7≥5.The data were analyzed using SPSS 23.0 and SPSS macro program PROCESS V4.0.Results:(1) The rate of anxiety in vocational school students was 42.96%, and girls were 27.1% higher than boys ( OR=1.271, 95% CI=1.095-1.474).(2) The CTQ (44(38, 51)) and DERS (98(89, 111)) in students with anxiety were both significantly higher than those in students without anxiety (39(34, 45), 81(73, 90), Z=-17.910, -33.859, both P<0.001).(3) Regression analysis showed that girls ( β=0.240, OR=1.271, 95% CI=1.095~1.474), childhood trauma ( β=0.028, OR=1.028, 95% CI=1.019~1.037), and emotion dysregulation ( β=0.076, OR=1.080, 95% CI=1.073-1.086) were significant predictors for anxiety.(4) Path analysis and mediating effect showed that childhood trauma positively predicted anxiety ( β=0.059, 95% CI=0.048-0.071) and emotion dysregulation ( β=0.802, 95% CI=0.749-0.854), and emotion dysregulation positively predicted anxiety ( β=0.139, 95% CI=0.132-0.145).Emotion dysregulation had a significant mediating effect (effect value=0.112, 95% CI=0.101-0.121) in the relationship between childhood trauma and anxiety, with the indirect effect accounting for 65.50% of the total effect. Conclusion:The incidence of anxiety symptoms is high among vocational school students, and childhood trauma not only directly affects anxiety symptoms, but also indirectly affects anxiety symptoms through emotion dysregulation.

Aiming at the limitations of clinical diagnosis of Parkinson's disease (PD) with rapid eye movement sleep behavior disorder (RBD), in order to improve the accuracy of diagnosis, an intelligent-aided diagnosis method based on few-channel electroencephalogram (EEG) and time-frequency deep network is proposed for PD with RBD. Firstly, in order to improve the speed of the operation and robustness of the algorithm, the 6-channel scalp EEG of each subject were segmented with the same time-window. Secondly, the model of time-frequency deep network was constructed and trained with time-window EEG data to obtain the segmentation-based classification result. Finally, the output of time-frequency deep network was postprocessed to obtain the subject-based diagnosis result. Polysomnography (PSG) of 60 patients, including 30 idiopathic PD and 30 PD with RBD, were collected by Nanjing Brain Hospital Affiliated to Nanjing Medical University and the doctor's detection results of PSG were taken as the gold standard in our study. The accuracy of the segmentation-based classification was 0.902 4 in the validation set. The accuracy of the subject-based classification was 0.933 3 in the test set. Compared with the RBD screening questionnaire (RBDSQ), the novel approach has clinical application value.
Electroencephalography ; Humans ; Intelligence ; Parkinson Disease/diagnosis* ; Polysomnography ; REM Sleep Behavior Disorder/diagnosis*

Objective: To investigate the abnormalities of the blood system in landfill workers. Methods: A cohort study was conducted for 224 landfill workers who were followed up for 6 consecutive years with abnormal routine blood test results and a low platelet count as the outcome events. The life-table method was used to analyze the incidence rates of these two outcome events, and the incidence rates were compared between first-and second-line workers. Results: A total of 71 workers had abnormal routine blood test results, among whom 29 had abnormal leukocyte count, 14 had abnormal erythrocyte count, 40 had abnormal platelet count, 17 had abnormal hemoglobin, and 29 had a reduction in platelet count. For these landfill workers, the 6-year abnormal rate of routine blood test results was 43.2%, and the incidence rate of low platelet count within 6 years was 13.5%. The first-line workers had a significantly lower abnormal rate of routine blood test results than the second-line workers (P=0.020) , and the relative risk of abnormal routine blood test results in the first-and second-line workers was 0.592. There was no significant difference in the incidence rate of low platelet count between the two groups of workers (P≥0.05) . Conclusion The landfill has an adverse effect on the blood system of landfill workers, and the second-line workers have greater impairment than the first-line workers.

This study provides the candidate sequences in the identification of Radix et Rhizoma Clematidis and its adulterants using DNA barcoding. We amplified and sequenced the region psbA-trnH, with the data of 284 sequences from GenBank, the differential intra- and inter-specific divergences, genetic distance, barcoding gap were used to evaluate five barcodes, and the identification efficiency was assessed using BLAST1 and Nearest Distance methods. The results showed that psbA-trnH barcodes performed high identification efficiency and inter-specific divergences among the five different DNA barcodes. Analysis of the barcoding gap and NJ tree showed psbA-trnH was superior to other barcodes. Based on the identification and PCR amplification efficiency, psbA-trnH can be the ideal barcode to identify Radix et Rhizoma Clematidis and its adulterants accurately.

To establish a new method for identifying genus of Lilium by DNA barcoding technology, ITS, ITS2, psbA-trnH, matK and rbcL sequences were analyzed in term of variation of inter- and intra-species, barcoding gap, neighbor-joining tree to distinguish genus of Lilium based on 978 sequences from experimental and GenBank database, and identification efficiency was evaluated by Nearest distance and BLAST1 methods. The results showed that DNA barcoding could identify different species in genus of Lilium. ITS sequence performed higher identification efficiency, and had significant difference between intra- and inter-species. And NJ tree could also divide species into different clades. Results indicate that DNA barcoding can identify genus of Lilium accurately. ITS sequence can be the optimal barcode to identify species of Lilium.

Objective To study the effect of electrical stimulation breath training on lung function of patients following pulmonary lobectomy. Methods 62 patients following pulmonary lobectomy were randomly allocated into experimental group (n=30 )and control group (n=32). The experimental group received a 4-week supervised electrical stimulation breath training program using an electric stimulus feedback trainer (20mins per time, 3 times per week);The control group received postoperative routine nursing. Cadiopulmonary function evaluation of 2 groups were tested before and after the experiment. The evaluation included the 6-min walking test (6MWD), FVC, FEV1,W,AT and VO2max/kg. Results After 4 week training, the value of 6MWD,W,FVC,FEV1 all improved, compared to the baseline value (P < 0.05) and the value of 6MWD,W,FVC,FEV1 were more obvious in experimental group, compared to control group(P<0.05). The AT value and the VO2max/kg value increased than the baseline value (P<0.05)and the improvement degree was more remarkable in experimental group than that in control group (P<0.05). Conclusion Electrical stimulation breath training can improve cardiopulmonary function of the patients following pulmonary lobectomy.