Objective:To assess the diagnostic efficacy of upper gastrointestinal endoscopic image assisted diagnosis system (ENDOANGEL-LD) based on artificial intelligence (AI) for detecting gastric lesions and neoplastic lesions under white light endoscopy.Methods:The diagnostic efficacy of ENDOANGEL-LD was tested using image testing dataset and video testing dataset, respectively. The image testing dataset included 300 images of gastric neoplastic lesions, 505 images of non-neoplastic lesions and 990 images of normal stomach of 191 patients in Renmin Hospital of Wuhan University from June 2019 to September 2019. Video testing dataset was from 83 videos (38 gastric neoplastic lesions and 45 non-neoplastic lesions) of 78 patients in Renmin Hospital of Wuhan University from November 2020 to April 2021. The accuracy, the sensitivity and the specificity of ENDOANGEL-LD for image testing dataset were calculated. The accuracy, the sensitivity and the specificity of ENDOANGEL-LD in video testing dataset for gastric neoplastic lesions were compared with those of four senior endoscopists.Results:In the image testing dataset, the accuracy, the sensitivity, the specificity of ENDOANGEL-LD for gastric lesions were 93.9% (1 685/1 795), 98.0% (789/805) and 90.5% (896/990) respectively; while the accuracy, the sensitivity and the specificity of ENDOANGEL-LD for gastric neoplastic lesions were 88.7% (714/805), 91.0% (273/300) and 87.3% (441/505) respectively. In the video testing dataset, the sensitivity [100.0% (38/38) VS 85.5% (130/152), χ2=6.220, P=0.013] of ENDOANGEL-LD was higher than that of four senior endoscopists. The accuracy [81.9% (68/83) VS 72.0% (239/332), χ2=3.408, P=0.065] and the specificity [ 66.7% (30/45) VS 60.6% (109/180), χ2=0.569, P=0.451] of ENDOANGEL-LD were comparable with those of four senior endoscopists. Conclusion:The ENDOANGEL-LD can accurately detect gastric lesions and further diagnose neoplastic lesions to help endoscopists in clinical work.

Objective:To construct a real-time artificial intelligence (AI)-assisted endoscepic diagnosis system based on YOLO v3 algorithm, and to evaluate its ability of detecting focal gastric lesions in gastroscopy.Methods:A total of 5 488 white light gastroscopic images (2 733 images with gastric focal lesions and 2 755 images without gastric focal lesions) from June to November 2019 and videos of 92 cases (288 168 clear stomach frames) from May to June 2020 at the Digestive Endoscopy Center of Renmin Hospital of Wuhan University were retrospectively collected for AI System test. A total of 3 997 prospective consecutive patients undergoing gastroscopy at the Digestive Endoscopy Center of Renmin Hospital of Wuhan University from July 6, 2020 to November 27, 2020 and May 6, 2021 to August 2, 2021 were enrolled to assess the clinical applicability of AI System. When AI System recognized an abnormal lesion, it marked the lesion with a blue box as a warning. The ability to identify focal gastric lesions and the frequency and causes of false positives and false negatives of AI System were statistically analyzed.Results:In the image test set, the accuracy, the sensitivity, the specificity, the positive predictive value and the negative predictive value of AI System were 92.3% (5 064/5 488), 95.0% (2 597/2 733), 89.5% (2 467/ 2 755), 90.0% (2 597/2 885) and 94.8% (2 467/2 603), respectively. In the video test set, the accuracy, the sensitivity, the specificity, the positive predictive value and the negative predictive value of AI System were 95.4% (274 792/288 168), 95.2% (109 727/115 287), 95.5% (165 065/172 881), 93.4% (109 727/117 543) and 96.7% (165 065/170 625), respectively. In clinical application, the detection rate of local gastric lesions by AI System was 93.0% (6 830/7 344). A total of 514 focal gastric lesions were missed by AI System. The main reasons were punctate erosions (48.8%, 251/514), diminutive xanthomas (22.8%, 117/514) and diminutive polyps (21.4%, 110/514). The mean number of false positives per gastroscopy was 2 (1, 4), most of which were due to normal mucosa folds (50.2%, 5 635/11 225), bubbles and mucus (35.0%, 3 928/11 225), and liquid deposited in the fundus (9.1%, 1 021/11 225).Conclusion:The application of AI System can increase the detection rate of focal gastric lesions.

Establish a production line with controllable process and high intelligence, contribute to improve the quality and production efficiency of aconite processed by microwave, and promote the transformation and application of aconite processed by microwave. According to the principle of aconite detoxification and the characteristics of industrial microwave equipment, an industrial production line of aconite processed by microwave was established with diester alkaloids and monoester alkaloids as indicators, and pilot production was carried out. At the same time, the content of active constituents and efficacy were compared with that of the main processed products, such as Shengfupian, Baifupian and Heishunpian. The results showed that the industrial production of aconite processed by microwave can be divided into two stages: "Liquid seal to detoxification - drying and puffing". The content of monoester alkaloids in 10 batches of aconite processed by microwave was 0.071%-0.166% and the content of diester alkaloids was 0.004%-0.016%, which met the relevant requirements of the Chinese Pharmacopoeia in 2020. Compared with Heishunpian and Baifupian, the retention rate of the effective components of aconite processed by microwave was higher. Pharmacological experiments showed that aconite processed by microwave not only retained the anti-inflammatory and analgesic activities of Heishunpian and Baifupian, but also significantly increased the levels of leukocytes and lymphocytes in mice with liver cancer chemotherapy, enhanced the CD4/CD8 ratio in spleen cells of mice (P < 0.05), thus regulating the body's immunity. However, this effect of Baifupian was weak, while Heishunpian and Shengfupian had no such effect. Through the above research, this study established microwave processing line with controllable process and high intelligence, as well produced the aconite processed by microwave with low toxicity and stable quality. It laid a foundation for the industrialized continuous production and clinical positioning of aconite by microwave processed, and provided scientific support for the development and application of microwave technology in the field of traditional Chinese medicine. All animal experiments in this study were reviewed and approved by the Experimental Animal Ethics Committee of Chengdu University of Traditional Chinese Medicine before being carried out (Approval No. 2020-28).

Objective:To explore the effects of the γ-aminobutyric acid(GABA) neurons and melanin-concentrating hormone (MCH) neurons of the nucleus accumbens (NAc)-lateral hypothalamic area (LHA) neural pathway on the rewarding feeding(palatable food sweat condensed milk) in the obesity rats.Methods:Total 142 male Wistar rats of SPF grade were divided into normal diet (ND) group ( n=68) and high-fat diet induced obesity (DIO) group ( n=74) according to the principle of body mass matching. The rats in the two groups were given normal diet and high-fat diet for 8 weeks. Eight weeks later, 6 DIO rats were randomly selected to observe the nerve projection from GABA neurons in NAc to MCH neurons in LHA by fluorogold retrograde tracing combined fluorescence immunohistochemistry. And the expressions of c-Fos and MCH in LHA after ingestion of sweet condensed milk(rewarding feeding) were observed by fluorescence immunohistochemistry (6 rats in each group). GABA receptor agonist Musimol or GABA receptor antagonist Bicuculine was microinjected into the nucleus of LHA to observe the effect of GABA on rewarding food intake in ND and DIO rats ( n=8 in each group), and the changes of rewarding food intake after blocking MCH signal ( n=8 in each group). SPSS 17.0 was used for statistical analysis, two-way ANOVA and post hoc Bonferroni test were used for comparison among multiple groups, and t-test was used for comparison between two groups. Results:After 8 weeks of high-fat diet modeling, the intake of delicious food in DIO rats was significantly higher than that in ND rats((12.52±2.29) mL, (7.45±1.23) mL, t=4.778, P<0.01) after satiety.The results of fluorogold retrograde tracing combined with fluorescence immunohistochemistry showed that GABA neurons in NAc projected nerve fibers to neurons in LHA, and GABA A receptors in some neurons in LHA coexisted with MCH.The results of NAc-LHA pathway on delicious food intake showed that the interaction between rat group and drug intervention was significant( F=9.869, P<0.01). Simple effect analysis showed that the intake of delicious food after microinjection of Musimol into LHA nucleus of ND rats was significantly lower than that of microinjection normal saline ((4.25±1.38) mL, (7.29±1.49) mL, P<0.01), while the intake of delicious food after injection of Bicuculine was significantly higher than that of microinjection normal saline((10.72±2.11) mL, (7.29±1.49) mL, P<0.05). The intake of delicious food after microinjection of Musimol into LHA nucleus in DIO group was significantly lower than that of microinjection normal saline((3.51±1.77)mL, (13.68±2.95) mL, P<0.01), but there was no significant difference between microinjection Bicuculine and microinjection normal saline ((14.83±3.44) mL, (13.68±2.95) mL, P>0.05). The results of blocking MCH signal on delicious food intake showed that the interaction effect between SNAP-94847 and Bicuculine intervention was not significant ( F=1.468, P>0.05). The main effect of SNAP-94847 intervention was significant ( F=15.880, P<0.01)and the main effect of Bicuculine intervention was significant ( F=6.930, P<0.05). After intracerebroventricular injection of MCH receptor blocker SNAP-94847, the delicious food intake of ND rats was significantly less than that of injection normal saline((4.78±1.72) mL, (7.63±2.77) mL, P<0.05), and it was not affected by pre injection of Bicuculine in LHA ((6.24±2.18) mL, (4.78±1.72) mL, P>0.05). In the DIO rats, the interaction effect between SNAP-94847 and Bicuculine intervention was not significant( F=0.006, P>0.05). The main effect of SNAP-94847 intervention was significant ( F=18.46, P<0.01) and the main effect of Bicuculine intervention was not significant ( F=2.059, P>0.05). After intracerebroventricular injection of MCH receptor blocker SNAP-94847, the delicious food intake of DIO rats was significantly lower than that of injection normal saline((6.89±2.11) mL, (12.19±4.36) mL, P<0.05), and it was not affected by pre injection of Bicuculine in LHA ((8.72±2.26) mL, (6.89±2.11) mL, P>0.05). Conclusion:GABAergic signal in NAc can regulate the expression of MCH in neurons of LHA. In the DIO rats, the sensitivity of MCH neurons in LHA to satiety signal decreases and the hedonic feeding increases.

Objective:To compare the ability of deep convolutional neural network-crop (DCNN-C) and deep convolutional neural network-whole (DCNN-W), 2 artificial intelligence systems based on different training methods to dignose early gastric cancer (EGC) diagnosis under magnifying image-enhanced endoscopy (M-IEE).Methods:The images and video clips of EGC and non-cancerous lesions under M-IEE under narrow band imaging or blue laser imaging mode were retrospectively collected in the Endoscopy Center of Renmin Hospital of Wuhan University, for the training set and test set for DCNN-C and DCNN-W. The ability of DCNN-C and DCNN-W in EGC identity in image test set were compared. The ability of DCNN-C, DCNN-W and 3 senior endoscopists (average performance) in EGC identity in video test set were also compared. Paired Chi-squared test and Chi-squared test were used for statistical analysis. Inter-observer agreement was expressed as Cohen′s Kappa statistical coefficient (Kappa value).Results:In the image test set, the accuracy, sensitivity, specificity and positive predictive value of DCNN-C in EGC diagnosis were 94.97%(1 133/1 193), 97.12% (202/208), 94.52% (931/985), and 78.91%(202/256), respectively, which were higher than those of DCNN-W(86.84%, 1 036/1 193; 92.79%, 193/208; 85.58%, 843/985 and 57.61%, 193/335), and the differences were statistically significant ( χ2=4.82, 4.63, 61.04 and 29.69, P=0.028, =0.035, <0.001 and <0.001). In the video test set, the accuracy, specificity and positive predictive value of senior endoscopists in EGC diagnosis were 67.67%, 60.42%, and 53.37%, respectively, which were lower than those of DCNN-C (93.00%, 92.19% and 87.18%), and the differences were statistically significant ( χ2=20.83, 16.41 and 11.61, P<0.001, <0.001 and =0.001). The accuracy, specificity and positive predictive value of DCNN-C in EGC diagnosis were higher than those of DCNN-W (79.00%, 70.31% and 64.15%, respectively), and the differences were statistically significant ( χ2=7.04, 8.45 and 6.18, P=0.007, 0.003 and 0.013). There were no significant differences in accuracy, specificity and positive predictive value between senior endoscopists and DCNN-W in EGC diagnosis (all P>0.05). The sensitivity of senior endoscopists, DCNN-W and DCNN-C in EGC diagnosis were 80.56%, 94.44%, and 94.44%, respectively, and the differences were not statistically significant (all P>0.05). The results of the agreement analysis showed that the agreement between senior endoscopists and the gold standard was fair to moderate (Kappa=0.259, 0.532, 0.329), the agreement between DCNN-W and the gold standard was moderate (Kappa=0.587), and the agreement between DCNN-C and the gold standard was very high (Kappa=0.851). Conclusion:When the training set is the same, the ability of DCNN-C in EGC diagnosis is better than that of DCNN-W and senior endoscopists, and the diagnostic level of DCNN-W is equivalent to that of senior endoscopists.

Objective:To assess the influence of an artificial intelligence (AI) -assisted diagnosis system on the performance of endoscopists in diagnosing gastric cancer by magnifying narrow banding imaging (M-NBI).Methods:M-NBI images of early gastric cancer (EGC) and non-gastric cancer from Renmin Hospital of Wuhan University from March 2017 to January 2020 and public datasets were collected, among which 4 667 images (1 950 images of EGC and 2 717 of non-gastric cancer)were included in the training set and 1 539 images (483 images of EGC and 1 056 of non-gastric cancer) composed a test set. The model was trained using deep learning technique. One hundred M-NBI videos from Beijing Cancer Hospital and Renmin Hospital of Wuhan University between 9 June 2020 and 17 November 2020 were prospectively collected as a video test set, 38 of gastric cancer and 62 of non-gastric cancer. Four endoscopists from four other hospitals participated in the study, diagnosing the video test twice, with and without AI. The influence of the system on endoscopists′ performance was assessed.Results:Without AI assistance, accuracy, sensitivity, and specificity of endoscopists′ diagnosis of gastric cancer were 81.00%±4.30%, 71.05%±9.67%, and 87.10%±10.88%, respectively. With AI assistance, accuracy, sensitivity and specificity of diagnosis were 86.50%±2.06%, 84.87%±11.07%, and 87.50%±4.47%, respectively. Diagnostic accuracy ( P=0.302) and sensitivity ( P=0.180) of endoscopists with AI assistance were improved compared with those without. Accuracy, sensitivity and specificity of AI in identifying gastric cancer in the video test set were 88.00% (88/100), 97.37% (37/38), and 82.26% (51/62), respectively. Sensitivity of AI was higher than that of the average of endoscopists ( P=0.002). Conclusion:AI-assisted diagnosis system is an effective tool to assist diagnosis of gastric cancer in M-NBI, which can improve the diagnostic ability of endoscopists. It can also remind endoscopists of high-risk areas in real time to reduce the probability of missed diagnosis.

Objective:To develop early gastric cancer (EGC) detection system of magnifying blue laser imaging (ME-BLI) model and magnifying narrow-band imaging (ME-NBI) model based on deep convolutional neural network, to compare the performance differences of the two models and to explore the effects of training methods on the accuracy.Methods:The images of benign gastric lesions and EGC under ME-BLI and ME-NBI were respectively collected. A total of five data sets and three test sets were collected. Data set 1 included 2 024 noncancerous lesions and 452 EGC images under ME-BLI. Data set 2 included 2 024 noncancerous lesions and 452 EGC images under ME-NBI. Data set 3 was the combination of data set 1 and 2 (a total of 4 048 noncancerous lesions and 904 EGC images under ME-BLI and ME-NBI). Data set 4: on the basis of data set 2, another 62 noncancerous lesions and 2 305 EGC images under ME-NBI were added (2 086 noncancerous lesions and 2 757 EGC images under ME-NBI). Data set 5: on the basis of data set 3, another 62 noncancerous lesions and 2 305 EGC images under ME-NBI were added(4 110 noncancerous lesions and 3 209 EGC images under ME-NBI and ME-BLI). Test set A included 422 noncancerous lesions and 197 EGC images under ME-BLI. Test set B included 422 noncancerous lesions and 197 EGC images under ME-NBI. Test set C was the combination of test set A and B (844 noncancerous and 394 EGC images under ME-BLI and ME-NBI). Five models were constructed according to these five data sets respectively and their performance was evaluated in the three test sets. Per-lesion video was collected and used to compare the performance of deep convolutional neural network models under ME-BLI and ME-NBI for the detection of EGC in clinical environment, and compared with four senior endoscopy doctors. The primary endpoint was the diagnostic accuracy of EGG, sensitivity and specificity. Chi-square test was used for statistical analysis.Results:The performance of model 1 was the best in test set A with the accuracy, sensitivity and specificity of 76.90% (476/619), 63.96% (126/197) and 82.94% (350/422), respectively. The performance of model 2 was the best in test set B with the accuracy, sensitivity and specificity of 86.75% (537/619), 92.89% (183/197) and 83.89% (354/422), respectively. The performance of model 3 was the best in test set B with the accuracy, sensitivity and specificity of 86.91% (538/619), 84.26% (166/197) and 88.15% (372/422), respectively. The performance of model 4 was the best in test set B with the accuracy, sensitivity and specificity of 85.46% (529/619), 95.43% (188/197) and 80.81% (341/422), respectively. The performance of model 5 was the best in test set B, with the accuracy, sensitivity and specificity of 83.52% (517/619), 96.95% (191/197) and 77.25% (326/422), respectively. In terms of image recognition of EGC, the accuracy of models 2 to 5 was higher than that of model 1, and the differences were statistically significant ( χ2=147.90, 149.67, 134.20 and 115.30, all P<0.01). The sensitivity and specificity of models 2 and 3 were higher than those of model 1, the specificity of model 2 was lower than that of model 3, and the differences were statistically significant ( χ2=131.65, 64.15, 207.60, 262.03 and 96.73, all P < 0.01). The sensitivity of models 4 and 5 was higher than those of models 1 to 3, and the specificity of models 4 and 5 was lower than those of models 1 to 3, and the differences were statistically significant ( χ2=151.16, 165.49, 71.35, 112.47, 132.62, 153.14, 176.93, 74.62, 14.09, 15.47, 6.02 and 5.80, all P<0.05). The results of video test based on lesion showed that the average accuracy of doctors 1 to 4 was 68.16%. And the accuracy of models 1 to 5 was 69.47% (66/95), 69.47% (66/95), 70.53% (67/95), 76.84% (73/95) and 80.00% (76/95), respectively. There were no significant differences in the accuracy among models 1 to 5 and between models 1 to 5 and doctors 1 to 4 (all P>0.05). Conclusions:ME-BLI EGC recognition model based on deep learning has good accuracy, but the diagnostic effecacy is sligntly worse than that of ME-NBI model. The effects of EGC recognition model of ME-NBI combined with ME-BLI is better than that of a single model. A more sensitive ME-NBI model can be obtained by increasing the number of ME-NBI images, especially the images of EGG, but the specificity is worse.

OBJECTIVE: To investigate the prevalence and risk factors of multi-site work-related musculoskeletal disorders(WMSDs) among workers in the industry of electronic equipment manufacturing. METHODS: A total of 815 workers in three factories of electronic equipment manufacturing in Guangdong Province were selected as study subjects by convenience sampling. The prevalence of multi-site WMSDs in the past year was investigated using Musculoskeletal Disorders Investigating Questionnaire and the influencing factors were analyzed. RESULTS: The total prevalence of WMSDs was 69.4%(566/815). The prevalence of multi-site WMSDs was 54.5%(444/815), and the prevalence of one-site WMSDs was 15.0%(122/815). Multiple logistic regression showed that female workers had higher prevalence of multi-site WMSDs than males [odds radio(OR) and 95% confidence interval(CI): 1.59(1.12-2.26), P<0.05]. The prevalence of multi-site WMSDs in left-handed workers was lower than that of right-handed workers [OR(95% CI): 0.42(0.19-0.91), P<0.05]. The longer service of current position and the more neck forward movement, the higher prevalence of multi-site WMSDs [OR(95% CI) were 1.33(1.09-1.63) and 1.62(1.23-2.15), P<0.01]. The workers who had long-time sitting at work, adopted uncomfortable working posture, could decide when to work on their own, kept head down for a long time, or often bending wrists up/down had higher prevalence of multi-site WMSDs [OR(95% CI) were 1.41(1.16-1.73), 1.82(1.40-2.38), 1.79(1.16-2.75), 1.92(1.38-2.69) and 1.60(1.14-2.24), respectively, P<0.01]. The workers who could take turns with colleagues to finish work or had enough rest time had lower prevalence of multi-site WMSDs [OR(95% CI): 0.57(0.41-0.78) and 0.67(0.48-0.92), P<0.05]. The workers who worked >10 h per day had lower prevalence of multi-site WMSDs than those who worked ≤8 h per day [OR(95% CI): 0.57(0.37-0.87), P<0.05]. CONCLUSION: Multi-site WMSDs were more common than one-site WMSDs among workers in the industry of electronic equipment manufacturing, and the prevalence of multi-site WMSDs was high. The risk factors include personal factors, work organization and adverse ergonomic factors.

OBJECTIVE: To analyze the characteristics of noise hazard in a nuclear power station. METHODS: The workplaces and working posts which exposed to occupational noise from two 1 000 MW power units in one nuclear power station in Guangdong Province was selected as study subjects using the convenience sampling method. Occupational health survey, noise measurement in the workplace and personal noise dosage measurement were used to monitor noise exposure, and to analyze the characteristics of occupational noise in the nuclear power station. RESULTS: The noise sources of the nuclear power plant were mainly distributed in the nuclear island, conventional island, and peripheral workshops. A total of 237 points of noise intensity were measured in the workplace. The intensity of noise ranged from 66.0 to 99.6 dB(A). The noise intensity in 62.4%(148/237) of points was equal or greater than 80.0 dB(A) and 34.2%(81/237) equal or greater than 85.0 dB(A). The percentage of detection points with noise intensity was equal or greater than 85.0 dB(A) from low to high were nuclear island, conventional island, and peripheral workshops with 22.0%, 37.5% and 53.8% respectively(P<0.01). The personal noise intensity of three positions including inspectors of operation department, preparation and main engine positions of mechanical department exceeded the occupational exposure limit(OEL), and the percentage of positions whose noise intensity exceeded the OEL was 9.7%(3/31). CONCLUSION: High-intensity noise sources of the nuclear power plant are widely distributed in the workshop areas of nuclear island, conventional island, and peripheral workshops. The noise level of some positions exceeded the standards of noise intensity. The prevention and control measures of noise hazards in posts with excessive noise should be strengthened.

OBJECTIVE: To analyze the current status of occupational exposure to power frequency electromagnetic field in converter stations. METHODS: Eight converter stations with voltage levels of ±500 kV and ±800 kV within normal operation were selected as the research subjects using the typical sampling method. Power frequency electric field and power frequency magnetic field strengths were measured and calculated according to the GBZ/T 189.3-2018 Measurement of Physical Agents in Workplace--Part 3: Electric Field and Magnetic Field between 1 Hz and 100 kHz. The GBZ 2.2-2007 Occupational Exposure Limits for Hazardous Factors in the Workplace--Part 2: Physical Factors were used to evaluate whether the power frequency electric field strength exceeds the regulatory limit(the occupational exposure limit of power frequency electric field in 8 hours workplace is 5.000 kV/m). Meanwhile, the test results were evaluated according to the short-term occupational exposure limit of 50 Hz electric field and magnetic field recommended by the International Committee on Nonionizing Radiation Protection in 2010 that are 10.000 kV/m and 1 000.00 μT. RESULTS: The power frequency electric field and magnetic field strengths of 582 working environment detection points were measured. The median and 0-100 th percentile of power frequency electric field and power frequency magnetic field strength were 4.342(0.001-12.003) kV/m and 5.51(0.10-186.90) μT, respectively.The exceeding standard rate of power frequency electric field strength in converter station workplaces was 37.8%(220/582), which concentrated in 500 kV alternating current filter area and 500 kV alternating current field area. Among them, 5 detection points had power frequency electric field strength exceeding 10.000 kV/m. The magnetic flux density of all the detection points did not exceed 1 000.00 μT. The power frequency electric field strength in ultra-high voltage region was higher than that in high voltage region(P<0.01). There was no significant difference in power frequency magnetic field strength(P>0.05). There was no significant difference in power frequency electric field and magnetic field between rectifier stations and inverter stations(P>0.05). The 8 hours time weighted average(TWA) value of power frequency electric field strength of 8 converter station operators was 1.044-2.335 kV/m, which did not exceed the occupational exposure limit. CONCLUSION: The converter station operators might be exposed to excessive power frequency electric fields for a short time, but the 8 hours TWA value of the power frequency electric field meets the requirements of standards, and the power frequency magnetic field exposure strength also meets the requirements of the relevant standards.