Objective To develop and validate a deep learning-based segmentation model for low-dose cervical spine X-ray,aiming to address the insufficient segmentation accuracy in low-dose protocols while balancing radiation protection and diagnostic accuracy.Methods A total of 1 363 patients cervical spine X-ray images data were collected.A dose-attenuation mathematical simulation sys-tem was constructed to generate 14 122 dynamic low-dose cervical spine images incorporating quantum noise,contrast degradation,and blur artifacts.A neural network model was developed for automated segmentation of low-dose cervical spine X-ray using this dataset.Results Within the dose range of 50%to 7.5%,the average reults of automatic segmentation by the neural network model and manual segmentation for each group were as follows:50%dose group,intersection over union(IoU)=0.98 vs 0.93(P=0.707)and Dice coefficient(Dice)=0.99 vs 0.96(P=0.749);10%dose group,IoU=0.97 vs 0.87(P=0.201)and Dice=0.99 vs 0.93(P=0.219);7.5%dose group,IoU=0.97 vs 0.67(P<0.01)and Dice=0.98 vs 0.80(P<0.01).Conclusion The developed deep learning model achieved robust cervical spine segmentation(IoU>0.96,Dice>0.98)below diagnostic dose thresholds[peak signal-to-noise ratio(PSNR)<38 dB,structural similarity index(SSIM)<0.65].Under ultra-low-dose conditions(PSNR=27.710 dB,SSIM=0.274),it demonstrated a 44.78%IoU improvement and 22.5%Dice improvement over manual segmentation.This model enables minimal radia-tion exposure while preserving diagnostic performance,confirming its theoretical feasibility for low-dose X-ray image analysis and clinical research potential.

Objective To develop and validate a deep learning-based segmentation model for low-dose cervical spine X-ray,aiming to address the insufficient segmentation accuracy in low-dose protocols while balancing radiation protection and diagnostic accuracy.Methods A total of 1 363 patients cervical spine X-ray images data were collected.A dose-attenuation mathematical simulation sys-tem was constructed to generate 14 122 dynamic low-dose cervical spine images incorporating quantum noise,contrast degradation,and blur artifacts.A neural network model was developed for automated segmentation of low-dose cervical spine X-ray using this dataset.Results Within the dose range of 50%to 7.5%,the average reults of automatic segmentation by the neural network model and manual segmentation for each group were as follows:50%dose group,intersection over union(IoU)=0.98 vs 0.93(P=0.707)and Dice coefficient(Dice)=0.99 vs 0.96(P=0.749);10%dose group,IoU=0.97 vs 0.87(P=0.201)and Dice=0.99 vs 0.93(P=0.219);7.5%dose group,IoU=0.97 vs 0.67(P<0.01)and Dice=0.98 vs 0.80(P<0.01).Conclusion The developed deep learning model achieved robust cervical spine segmentation(IoU>0.96,Dice>0.98)below diagnostic dose thresholds[peak signal-to-noise ratio(PSNR)<38 dB,structural similarity index(SSIM)<0.65].Under ultra-low-dose conditions(PSNR=27.710 dB,SSIM=0.274),it demonstrated a 44.78%IoU improvement and 22.5%Dice improvement over manual segmentation.This model enables minimal radia-tion exposure while preserving diagnostic performance,confirming its theoretical feasibility for low-dose X-ray image analysis and clinical research potential.

Objective To observe value of echocardiographic evaluation on infants with pulmonary atresia and intact ventricular septum(PA/IVS)for surgical decision and post operation right ventricle(RV)development.Methods Forty-six PA/IVS infants who underwent pulmonary valve(PV)annuloplasty(group A,n=25),PV annuloplasty and RV outflow tract reconstruction with/without additional systemic-to-pulmonary artery shunt(group B,n=15),and systemic-to-pulmonary artery shunt and atrial septal enlargement(group C,n=6)were retrospectively enrolled.Status of RV developments were compared among groups before operation as well as 1 and 6 months after operation.Results The presentation age in group B was younger than,while in group C was older than that in group A(both P＜0.05).Before operation,tricuspid valve(TV)annulus diameter,TV annulus Z-score and TV/mitral valve(MV)annulus ratio in groups B and C were both smaller than those in group A(all P＜0.05),whereas RV/left ventricle(LV)longitudinal diameter ratio in group B was larger and PV annulus Z-score in group C was smaller than those in group A(both P＜0.05).Meanwhile,preoperative PV annulus Z-score and RV/LV longitudinal diameter ratio in group B were both larger than those in group C(both P＜0.05).One month after operations,TV annulus diameter,TV annulus Z-score and TV/MV annulus ratio in group B and C,as well as PV annulus diameter,PV annulus Z-score and RV/LV longitudinal diameter ratio in group C were all smaller than those in group A(all P＜0.05),while PV annulus diameter,PV annulus Z-score and RV/LV longitudinal diameter ratio in group C were all smaller than those in group B(all P＜0.05).Six months after operations,no significant difference of TV annulus diameter,PV annulus diameter,PV annulus Z-score,TV/MV annulus ratio nor RV/LV longitudinal diameter ratio was found between group A and B(all P＞0.05),but the above indexes in group C were all lower than those in group A and B(all P＜0.05).Besides,no significant difference of TV annulus Z-score was found between group A and B(P＞0.05),which were lower in group C than in group A(P＜0.05).Conclusion Echocardiographic evaluation on PA/IVS infants was helpful to establishment of forward blood flow from RV to pulmonary arteries in time,hence promoting RV development.

Lung cancer is the most threatening tumor disease to human health. Early detection is crucial to improve the survival rate and recovery rate of lung cancer patients. Existing methods use the two-dimensional multi-view framework to learn lung nodules features and simply integrate multi-view features to achieve the classification of benign and malignant lung nodules. However, these methods suffer from the problems of not capturing the spatial features effectively and ignoring the variability of multi-views. Therefore, this paper proposes a three-dimensional (3D) multi-view convolutional neural network (MVCNN) framework. To further solve the problem of different views in the multi-view model, a 3D multi-view squeeze-and-excitation convolution neural network (MVSECNN) model is constructed by introducing the squeeze-and-excitation (SE) module in the feature fusion stage. Finally, statistical methods are used to analyze model predictions and doctor annotations. In the independent test set, the classification accuracy and sensitivity of the model were 96.04% and 98.59% respectively, which were higher than other state-of-the-art methods. The consistency score between the predictions of the model and the pathological diagnosis results was 0.948, which is significantly higher than that between the doctor annotations and the pathological diagnosis results. The methods presented in this paper can effectively learn the spatial heterogeneity of lung nodules and solve the problem of multi-view differences. At the same time, the classification of benign and malignant lung nodules can be achieved, which is of great significance for assisting doctors in clinical diagnosis.
Humans ; Lung/pathology* ; Lung Neoplasms/pathology* ; Neural Networks, Computer ; Tomography, X-Ray Computed/methods*

Objective:To develop a neural network model for the evaluation of glomerular filtration rate (GFR) based on multilayer perceptual neural network, and to compare with the improved Chinese based creatinine GFR evaluation formula (C-GFR cr) and the evaluation formula (EPI-GFR cr) of the American Chronic Kidney Disease Epidemiology Collaboration (CKD-EPI) for the clinical applicability of multilayer perceptual neural network model in evaluating GFR. Methods:A total of 684 chronic kidney disease (CKD) patients used for developing a modified version of China′s based creatinine GFR evaluation formula were taken as the research object. The data of 454 patients were randomly selected as the development group and the data of the other 230 patients were as the verification group. The multilayer perceptual neural network GFR evaluation model (M-GFR cr) was established. With the double plasma GFR as the reference value (rGFR), the correlation, mean difference, mean absolute difference, precision and accuracy of C-GFR cr, EPI-GFR cr and M-GFR cr were compared. Results:Among the 684 CKD patients, there were 352 males and 332 females, with age of (49.9±15.8) years. The correlation between M-GFR cr and rGFR was the highest (Pearson correlation =0.93, P<0.001). The mean difference of M-GFR cr was lower than that of C-GFR cr ( Z=9.929, P<0.001) and EPI-GFR cr ( Z=10.573, P<0.001). The mean absolute difference of M-GFR cr was also lower than that of C-GFR cr ( Z=3.953, P<0.001) and EPI-GFR cr ( Z=4.210, P<0.001). The accuracy of ±15% of M-GFR cr was higher than that of C-GFR cr ( χ2=26.068, P<0.001) and EPI-GFR cr ( χ2=23.154, P<0.001). The accuracy of ±30% of M-GFR cr was also higher than that of C-GFR cr ( χ2=8.264, P=0.001) and EPI-GFR cr ( χ2=11.963, P=0.001). The results of different stages of CKD showed that in the early stage of CKD (CKD 1-2), the mean difference of M-GFR cr was lower than that of C-GFR cr ( Z=7.401, P<0.001) and EPI-GFR cr ( Z=8.096, P<0.001); the mean absolute difference of M-GFR cr was also lower than that of C-GFR cr ( Z=4.723, P<0.001) and EPI-GFR cr ( Z=4.946, P<0.001); the accuracy of ±15% of M-GFR cr was higher than that of C-GFR cr ( χ2=23.547, P<0.001) and EPI-GFR cr ( χ2=26.421, P<0.001); the accuracy of ±30% of M-GFR cr was also higher than that of C-GFR cr ( χ2=12.089, P=0.001) and EPI-GFR cr ( χ2=16.168, P<0.001). But there was no significant difference in the applicability among C-GFR cr, EPI-GFR cr and M-GFR cr in the advanced stages of CKD (CKD 3-5). Conclusion:Compared with the improved Chinese based creatinine GFR evaluation formula C-GFR cr and CKD-EPI evaluation formula EPI-GFR cr, the accuracy of multilayer perceptual neural network model to evaluate GFR in CKD patients has been significantly improved, especially in CKD 1-2 stage.

Objective To investigate the effect of somatostatin on pancreatic blood flow and pancreatic function on the patients with acute pancreatitis.Methods 120 patients with acute pancreatitis from March 2015 to March 2017 were collected, and were randomly divided into the observation group and the control group.The control group were given routine treatment, at the basis of this, the observation group were given somatostatin.octreotide 0.6 mg was dripped into intravenous continuously, and was reducted to 0.3 mg, continuous treatment for 7 d.The changes of blood flow and the curative effect of pancreas were compared between the two groups before and after treatment.Results The total effective rate was 96.67%(58/60)in the treatment group and 80.00%(48/60)in the control group.The total effective rate in the observation group was significantly higher than that in the control group, the difference was statistically significant (P<0.05).There was no significant difference in blood flow(BF), blood volume(BV)and capillary surface permeability(PS)between the two groups before treatment.1 and 7 days after treatment, BF, BV in the observation group were higher than those in the control group, the levels of PS were significantly lower than that in the control group, the differences were statistically significant(P<0.05).Before treatment, the differences of(CP), insulin(INS), glucagon(GLU), serum lipase(LIP), amylase(AMY)and trypsinogen-2(TPS)were measured in the two groups were not statistically significant.1 and 7 days after treatment, CP and INS in the observation group were significantly higher than those in the control group, and GLU, LIP, AMY and TPS-2 were significantly lower than those in the control group, the differences between the two groups was statistically significant (P<0.05).Conclusion It has a protective effect on pancreatic blood flow and function which somatostatin was used in the treatment of the patients with acute pancreatitis, it can improve the overall state of pancreas, and has significant therapeutic effect.

Objective To study the prevalence and socio-demographic correlates of mental disorders in Beijing residents. Methods The multi-stage stratified cluster random sampling method was used,19 874 residents aged 18 or above who had lived for more than six months in Beijing were selected. Face-to-face assessment was conducted by trained investigators by using the Chinese version of the Structured Clinical Interview for DSM-ⅣAxisⅠDisorders-Patient Edition(SCID-Ⅰ/P)to find any mental disorders, and the Mini-Mental State Examination (MMSE) to screen for dementia and mental retardation. Those who were positive on MMSE(MMSE≤17 for those who completed elementary education or less,≤23 for those who completed middle school or above) were further assessed to confirm dementia and mental retardation by using the SCID. Results 16 032 (80.7%) out of 19 874 eligible residents completed the face-to-face assessment. Adjusted by age and gender, the lifetime prevalence of all mental disorders was 120.8‰ (1 937/16 032, 115.8‰-125.9‰), and the top three most common ones were major depressive disorder (527,32.9‰), alcohol dependence and abuse (311, 19.4‰), and anxiety disorder, NOS (270, 16.8‰). The point prevalence of all mental disorders was 75.3‰ (1 207/16 032,71.2‰-79.4‰), the top three were specific phobias (187, 11.7‰),anxiety disorder, NOS (186, 11.6‰), and major depressive disorder (162, 10.1‰).The prevalence of mental disorders was significantly higher in the elderly(OR=1.014),female(OR=1.428),unemployed(OR=1.096),people having poor rapports with family(OR=1.686) or others(OR=1.901), smoking(OR=1.129)or drinking(OR=1.262). The prevalence of mental disorders was significantly lower in the urban residents(OR=0.840), people in a higher level of education(OR=0.813), people who had got married/remarried or who had partner(OR=0.689), people who had no family history of any mental disorders(OR=0.405). Conclusions Approximately 12% of Beijing residents may meet at least one diagnosis of mental disorder in their lifetime; The prevalence of mental disorders is associated with older age,female gender,lower level of education,rural dwelling,positive family history of mental disorders,and poor social support system.

Objective To study the prevalence and socio-demographic correlates of mental disorders in Beijing residents. Methods The multi-stage stratified cluster random sampling method was used,19 874 residents aged 18 or above who had lived for more than six months in Beijing were selected. Face-to-face assessment was conducted by trained investigators by using the Chinese version of the Structured Clinical Interview for DSM-ⅣAxisⅠDisorders-Patient Edition(SCID-Ⅰ/P)to find any mental disorders, and the Mini-Mental State Examination (MMSE) to screen for dementia and mental retardation. Those who were positive on MMSE(MMSE≤17 for those who completed elementary education or less,≤23 for those who completed middle school or above) were further assessed to confirm dementia and mental retardation by using the SCID. Results 16 032 (80.7%) out of 19 874 eligible residents completed the face-to-face assessment. Adjusted by age and gender, the lifetime prevalence of all mental disorders was 120.8‰ (1 937/16 032, 115.8‰-125.9‰), and the top three most common ones were major depressive disorder (527,32.9‰), alcohol dependence and abuse (311, 19.4‰), and anxiety disorder, NOS (270, 16.8‰). The point prevalence of all mental disorders was 75.3‰ (1 207/16 032,71.2‰-79.4‰), the top three were specific phobias (187, 11.7‰),anxiety disorder, NOS (186, 11.6‰), and major depressive disorder (162, 10.1‰).The prevalence of mental disorders was significantly higher in the elderly(OR=1.014),female(OR=1.428),unemployed(OR=1.096),people having poor rapports with family(OR=1.686) or others(OR=1.901), smoking(OR=1.129)or drinking(OR=1.262). The prevalence of mental disorders was significantly lower in the urban residents(OR=0.840), people in a higher level of education(OR=0.813), people who had got married/remarried or who had partner(OR=0.689), people who had no family history of any mental disorders(OR=0.405). Conclusions Approximately 12% of Beijing residents may meet at least one diagnosis of mental disorder in their lifetime; The prevalence of mental disorders is associated with older age,female gender,lower level of education,rural dwelling,positive family history of mental disorders,and poor social support system.

Objective To investigate the MRI findings of perihip heterotopic ossification (HO) in the early, mid and late stages. Meth-ods The MRI of 44 inpatients with HO from February, 2011 to September, 2013 were reviewed, in which 20 cases (28 joints) were in early stage, 18 cases (24 joints) in mid stage and 6 cases (8 joints) in late stage. For the enhanced T1WI, 9 cases (11 joints) were in early stage, 6 cases (7 joints) in mid stage, and 3 cases (4 joints) in late stage. Theχ2 trend test was used to evaluate the MRI signal change with the HO maturity. Results With the maturity of hip HO, the signal intensity of T2WI reduced (χ2=16.773, P<0.001), fat signal on T1WI increased, the enhancement reduced (χ2=16.048, P=0.007). Conclusion The MRI findings of perihip HO are characteristic in MRI in all the stages. MRI is useful for the diagnosis of perihip HO, especially for the early HO.

BACKGROUND:Vascularuzed fibular graft is one of the effective methods for repair of large segmental bone defects in the extremities OBJECTIVE:To explore the clinical effects of vascularized fibular graft for repairing large segmental bone defects in the extremities. METHODS:Twenty-eight non-malignant patients who received vascularized fibular graft for repairing large segmental bone defects in the extremities and were folowed up for more than 20 months were enroled. After lesion removal, vascularized fibula bone graft was used to repair the bone defects. If cases combined with soft tissue defects, fibula flap or anterolateral thigh flap was adopted. RESULTS AND CONCLUSION: Al patients were folowed up for 20 months to 6 years. The grafted bones were healed with the surrounding bone at 3-8 months after fibula bone grafting. The grafted bone was enlarged near to the diameter of recipient bone at 10-22 months after grafting. Based on the Enneking system, the average score of large segmental tibia bone defects was 24.2 points with 81% limb function recovered and 94.1% patient satisfaction; the average score of large segmental femur bone defects was 26.3 points with 87.7% limb function recovered and 100% patient satisfaction; the average score of large segmental bone defects of the distal radius and ulna was 21.75 points with 72.5% limb function recovered and 100% patient satisfaction. These findings reveal that vascularized fibular graft for repairing large segmental bone defects in extremities can effectively promote bone healing and reduce disability, infection, amputation rate; moreover, patients are satisfied with the postoperative recovery of limb function.