Objective:To evaluate deep learning in improving the diagnostic rate of adenomatous and non-adenomatous polyps.Methods:Non-magnifying narrow band imaging (NBI) polyp images obtained from Endoscopy Center of Renmin Hospital, Wuhan University were divided into three datasets. Dataset 1 (2 699 adenomatous and 1 846 non-adenomatous non-magnifying NBI polyp images from January 2018 to October 2020) was used for model training and validation of the diagnosis system. Dataset 2 (288 adenomatous and 210 non-adenomatous non-magnifying NBI polyp images from January 2018 to October 2020) was used to compare the accuracy of polyp classification between the system and endoscopists. At the same time, the accuracy of 4 trainees in polyp classification with and without the assistance of this system was compared. Dataset 3 (203 adenomatous and 141 non-adenomatous non-magnifying NBI polyp images from November 2020 to January 2021) was used to prospectively test the system.Results:The accuracy of the system in polyp classification was 90.16% (449/498) in dataset 2, superior to that of endoscopists. With the assistance of the system, the accuracy of colorectal polyp diagnosis was significantly improved. In the prospective study, the accuracy of the system was 89.53% (308/344).Conclusion:The colorectal polyp classification system based on deep learning can significantly improve the accuracy of trainees in polyp classification.

OBJECTIVE To establish a method for simultaneously determining the contents of camphor ，menthol，borneol and methyl salicylate in Compound shexiang xuelian liuzhi plaster . METHODS The test solution was prepared by reflux extraction with ethyl acetate ，and was determined by gas chromatography （GC）. A Shimadzu SH -Rtx-Wax capillary column was used as the chromatographic column ，and a flame ionization detector was used as the detector . The detector temperature and the injector temperature were both set at 200 ℃. The flow rate of carrier gas （nitrogen）was 2.0 mL/min，the separation ratio was 20∶1，and the sample size was 1.0 μL. RESULTS The linear ranges of camphor ，menthol，borneol（calculated by the sum of isoborneol and borneol）and methyl salicylate were 11.5-230.4，10.6-211.6，11.3-225.5，11.0-219.1 μg/mL（r＞0.999）. RSDs of the precision ， repeatability and stability （48 h）tests were all less than 4%. The average recoveries of the four components were 100.7%，99.7%， 98.9% and 100.7%（RSDs were 4.3%，2.9%，2.2%，3.7%，n＝9）. The contents of camphor ，menthol，borneol and methyl salicylate in two specifications of Compound shexiang xuelian liuzhi plaster were 16.8-19.5，4.6-6.0，9.8-11.9，6.9-8.2 mg/piece（7 cm×10 cm/piece），and 8.3-8.6，2.2-2.4，4.7-4.8，3.2-3.6 mg/piece （5 cm×7 cm/piece）. CONCLUSIONS The method is successfully established for simultaneous determination of four volatile components in Compound shexiang xuelian liuzhi plaster .

Objective:To investigate the effects of Bifidobacterium animalis subsp. lactis BB-12 on hippocampal neuroinflammation and cognitive function of mice after whole brain radiotherapy. Methods:A total of sixty male C57BL/6J mice aged 7-8 weeks were randomly divided into 5 groups with 12 mice in each group: control group (Con group), probiotic group (BB-12 group), irradiation group (IR group), irradiation and Memantine group (IR+ Memantine group), irradiation and probiotic group (IR+ BB-12 group). The model of radiation-induced brain injury of mice was established by 10 Gy whole brain radiotherapy with a medical linear accelerator. Y-maze test was used to evaluate the cognitive function. The activation of microglia and astrocytes was observed by immunofluorescence staining. The expressions of inflammatory cytokines interleukin-1β (IL-1β), IL-6 and tumor necrosis factor-α (TNF-α) were detected by quantitative real-time reverse transcription polymerase chain reaction (QRT-PCR) and Western blot.Results:Y-maze test showed that, compared with Con group, the percentage of the times of reaching the novel arm in the total times of the three arms decreased significantly in the IR group ( t=5.04, P<0.05). BB-12 mitigated radiation-induced cognitive dysfunction ( t=4.72, P<0.05). Compared with Con group, the number ( t=3.05, 7.18, P<0.05) and circularity index ( t=6.23, 2.52, P<0.05) of Iba1 and GFAP positive cells were increased, the microglia and astrocytes were activated in the hippocampus of IR group, but these alterations were eliminated by BB-12. After whole brain IR, the mRNA and protein expression levels of inflammatory cytokines IL-1β, IL-6 and TNF-α in the hippocampus of mice were significantly increased compared with Con group ( tmRNA =4.10, 3.04, 4.18, P<0.05; tprotein=11.49, 7.04, 8.42, P<0.05), which were also significantly reduced by BB-12 compared with IR group ( tmRNA=4.20, 3.40, 2.84, P<0.05; tprotein=6.36, 4.03, 3.75, P<0.05). Conclusions:Bifidobacterium animalis BB-12 can suppress neuroinflammation mediated by microglia and astrocytes in the hippocampus of mice after radiotherapy and alleviates IR-induced cognitive dysfunction. Therefore, BB-12 has potential application in alleviating radiation induced brain injury.

Objective:To construct a real-time monitoring system based on computer vision for monitoring withdrawal speed of colonoscopy and to validate its feasibility and performance.Methods:A total of 35 938 images and 63 videos of colonoscopy were collected in endoscopic database of Renmin Hospital of Wuhan University from May to October 2018. The images were divided into two datasets, one dataset included in vitro, in vivo and unqualified colonoscopy images, and another dataset included ileocecal and non-cecal area images. And then 3 594 and 2 000 images were selected respectively from the two datasets for testing the deep learning model, and the remaining images were used to train the model. Three colonoscopy videos were selected to evaluate the feasibility of real-time monitoring system, and 60 colonoscopy videos were used to evaluate its performance.Results:The accuracy rate of the deep learning model for classification for in vitro, in vivo, and unqualified colonoscopy images was 90.79% (897/988), 99.92% (1 300/1 301), and 99.08% (1 293/1 305), respectively, and the overall accuracy rate was 97.11% (3 490/3 594). The accuracy rate of identifying ileocecal and non-cecal area was 96.70% (967/1 000) and 94.90% (949/1 000), respectively, and the overall accuracy rate was 95.80% (1 916/2 000). In terms of feasibility evaluation, 3 colonoscopy videos data showed a linear relationship between the retraction speed and the image processing interval, which indicated that the real-time monitoring system automatically monitored the retraction speed during the colonoscopy withdrawal process. In terms of performance evaluation, the real-time monitoring system correctly predicted entry time and withdrawal time of all 60 examinations, and the results showed that the withdrawal speed and withdrawal time was significantly negative-related ( R=-0.661, P<0.001). The 95% confidence interval of withdrawal speed for the colonoscopy with withdrawal time of less than 5 min, 5-6 min, and more than 6 min was 43.90-49.74, 40.19-45.43, and 34.89-39.11 respectively. Therefore, 39.11 was set as the safe withdrawal speed and 45.43 as the alarm withdrawal speed. Conclusion:The real-time monitoring system we constructed can be used to monitor real-time withdrawal speed of colonoscopy and improve the quality of endoscopy.

Objective:To construct an artificial intelligence-assisted diagnosis system to detect gastric ulcer lesions and identify benign and malignant gastric ulcers automatically.Methods:A total of 1 885 endoscopy images were collected from November 2016 to April 2019 in the Digestive Endoscopy Center of Renmin Hospital of Wuhan University. Among them, 636 were normal images, 630 were with benign gastric ulcers, and 619 were with malignant gastric ulcers. A total of 1 735 images belonged to training data set and 150 images were used for validation. These images were input into the Res-net50 model based on the fastai framework, the Res-net50 model based on the Keras framework, and the VGG-16 model based on the Keras framework respectively. Three separate binary classification models of normal gastric mucosa and benign ulcers, normal gastric mucosa and malignant ulcers, and benign and malignant ulcers were constructed.Results:The VGG-16 model showed the best ability of classification. The accuracy of the validation set was 98.0%, 98.0% and 85.0%, respectively, for distinguishing normal gastric mucosa from benign ulcers, normal gastric mucosa from malignant ulcers, and benign ulcers from malignant ulcers.Conclusion:The artificial intelligence-assisted diagnosis system obtained in this study shows noteworthy ability of detection of ulcerous lesions, and is expected to be used in clinical to assist doctors to detect ulcer and identify benign and malignant ulcers.

Objective:To establish a deep convolutional neural network (DCNN) model based on YOLO and ResNet algorithm for automatic detection of colorectal polyps and to test its function.Methods:Colonoscopy images and videos collected from the database of Digestive Endoscopy Center of Renmin Hospital of Wuhan University from January 2018 to March 2019 were divided into three databases (database 1, 3, 4). The public database CVC-ClinicDB (composed of 612 polyp images extracted from 29 colonoscopy videos provided by Barcelona Hospital, Spain) was used as the database 2. Database 1 (4 700 colonoscopy images from January 2018 to November 2018, including 3 700 intestinal polyp images and 1 000 non-polyp images) was used for establishing training and verifying the DCNN model. Database 2 (CVC-ClinicDB) and database 3 (720 colonoscopy images from January 2019 to March 2019, including 320 intestinal polyp images and 400 non-polyp images) were used for testing the DCNN model on image detection. Database 4 (15 colonoscopy videos in December 2019, containing 33 polyps) was used for testing the DCNN model on video detection. The sensitivity, specificity, accuracy and false positive rate of the DCNN model for detecting intestinal polyps were calculated.Results:The sensitivity of the DCNN model for detecting intestinal polyps in database 2 was 93.19% (602/646). In database 3, the DCNN model showed the accuracy of 95.00% (684/720), sensitivity of 98.13% (314/320), specificity of 92.50% (370/400), and false positive rate of 7.50% (30/400) for detecting intestinal polyps. In database 4, the DCNN model achieved a per-polyp-sensitivity of 100.00% (33/33), a per-image-accuracy of 96.29% (133 840/138 998), a per-image-sensitivity of 90.24% (4 066/4 506), a per-image-specificity of 96.49% (129 774/134 492), and a per-image-false positive rate of 3.51% (4 718/134 492).Conclusion:The DCNN model constructed in the study has a high sensitivity and specificity for automatic detection of colorectal polyps both in the colonoscopy images and videos, has a low false positive rate in the videos, and has the potential to assist endoscopists in diagnosis of colorectal polyps.

Objective:To construct an artificial intelligence-assisted diagnosis system to recognize the characteristics of Helicobacter pylori ( HP) infection under endoscopy, and evaluate its performance in real clinical cases. Methods:A total of 1 033 cases who underwent 13C-urea breath test and gastroscopy in the Digestive Endoscopy Center of Renmin Hospital of Wuhan University from January 2020 to March 2021 were collected retrospectively. Patients with positive results of 13C-urea breath test (which were defined as HP infertion) were assigned to the case group ( n=485), and those with negative results to the control group ( n=548). Gastroscopic images of various mucosal features indicating HP positive and negative, as well as the gastroscopic images of HP positive and negative cases were randomly assigned to the training set, validation set and test set with at 8∶1∶1. An artificial intelligence-assisted diagnosis system for identifying HP infection was developed based on convolutional neural network (CNN) and long short-term memory network (LSTM). In the system, CNN can identify and extract mucosal features of endoscopic images of each patient, generate feature vectors, and then LSTM receives feature vectors to comprehensively judge HP infection status. The diagnostic performance of the system was evaluated by sensitivity, specificity, accuracy and area under receiver operating characteristic curve (AUC). Results:The diagnostic accuracy of this system for nodularity, atrophy, intestinal metaplasia, xanthoma, diffuse redness + spotty redness, mucosal swelling + enlarged fold + sticky mucus and HP negative features was 87.5% (14/16), 74.1% (83/112), 90.0% (45/50), 88.0% (22/25), 63.3% (38/60), 80.1% (238/297) and 85.7% (36 /42), respectively. The sensitivity, specificity, accuracy and AUC of the system for predicting HP infection was 89.6% (43/48), 61.8% (34/55), 74.8% (77/103), and 0.757, respectively. The diagnostic accuracy of the system was equivalent to that of endoscopist in diagnosing HP infection under white light (74.8% VS 72.1%, χ2=0.246, P=0.620). Conclusion:The system developed in this study shows noteworthy ability in evaluating HP status, and can be used to assist endoscopists to diagnose HP infection.

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.