BACKGROUND A convolutional neural network(CNN) is a deep learning algorithm based on the principle of human brain visual cortex processing and image recognition.AIM To automatically identify the invasion depth and ori...BACKGROUND A convolutional neural network(CNN) is a deep learning algorithm based on the principle of human brain visual cortex processing and image recognition.AIM To automatically identify the invasion depth and origin of esophageal lesions based on a CNN.METHODS A total of 1670 white-light images were used to train and validate the CNN system.The method proposed in this paper included the following two parts:(1)Location module,an object detection network,locating the classified main image feature regions of the image for subsequent classification tasks;and(2) Classification module,a traditional classification CNN,classifying the images cut out by the object detection network.RESULTS The CNN system proposed in this study achieved an overall accuracy of 82.49%,sensitivity of 80.23%,and specificity of 90.56%.In this study,after follow-up pathology,726 patients were compared for endoscopic pathology.The misdiagnosis rate of endoscopic diagnosis in the lesion invasion range was approximately 9.5%;41 patients showed no lesion invasion to the muscularis propria,but 36 of them pathologically showed invasion to the superficial muscularis propria.The patients with invasion of the tunica adventitia were all treated by surgery with an accuracy rate of 100%.For the examination of submucosal lesions,the accuracy of endoscopic ultrasonography(EUS) was approximately 99.3%.Results of this study showed that EUS had a high accuracy rate for the origin of submucosal lesions,whereas the misdiagnosis rate was slightly high in the evaluation of the invasion scope of lesions.Misdiagnosis could be due to different operating and diagnostic levels of endoscopists,unclear ultrasound probes,and unclear lesions.CONCLUSION This study is the first to recognize esophageal EUS images through deep learning,which can automatically identify the invasion depth and lesion origin of submucosal tumors and classify such tumors,thereby achieving good accuracy.In future studies,this method can provide guidance and help to clinical endoscopists.展开更多
BACKGROUND Acute esophageal mucosal lesions(AEMLs)are an underrecognized and largely unexplored disease.Endoscopic findings are similar,and a higher percentage of AEML could be misdiagnosed as reflux esophagitis Los A...BACKGROUND Acute esophageal mucosal lesions(AEMLs)are an underrecognized and largely unexplored disease.Endoscopic findings are similar,and a higher percentage of AEML could be misdiagnosed as reflux esophagitis Los Angeles classification grade D(RE-D).These diseases could have different pathologies and require different treatments.AIM To compare AEML and RE-D to confirm that the two diseases are different from each other and to clarify the clinical features of AEML.METHODS We selected emergency endoscopic cases of upper gastrointestinal bleeding with circumferential esophageal mucosal injury and classified them into AEML and RE-D groups according to the mucosal injury’s shape on the oral side.We examined patient background,blood sampling data,comorbidities at onset,endoscopic characteristics,and outcomes in each group.RESULTS Among the emergency cases,the AEML and RE-D groups had 105(3.1%)and 48(1.4%)cases,respectively.Multiple variables exhibited significantly different results,indicating that these two diseases are distinct.The clinical features of AEML consisted of more comorbidities[risk ratio(RR):3.10;95%confidence interval(CI):1.68–5.71;P<0.001]and less endoscopic hemostasis compared with RE-D(RR:0.25;95%CI:0.10–0.63;P<0.001).Mortality during hospitalization was higher in the AEML group(RR:3.43;95%CI:0.82–14.40;P=0.094),and stenosis developed only in the AEML group.CONCLUSION AEML and RE-D were clearly distinct diseases with different clinical features.AEML may be more common than assumed,and the potential for its presence should be taken into account in cases of upper gastrointestinal bleeding with comorbidities.展开更多
BACKGROUND Helicobacter pylori(H. pylori) is a Gram-negative bacterium found in the upper digestive tract. Although H. pylori infection is an identified risk factor for gastric cancer, its role in esophageal squamous ...BACKGROUND Helicobacter pylori(H. pylori) is a Gram-negative bacterium found in the upper digestive tract. Although H. pylori infection is an identified risk factor for gastric cancer, its role in esophageal squamous cell carcinoma(ESCC) remains a topic of much debate.AIM To evaluate the association between H. pylori infection and the risk of precancerous lesions of ESCC, and further explore the association between dietary factors and the risk of H. pylori infection.METHODS Two hundred patients with esophageal precancerous lesions(EPL) aged 63.01 ± 6.08 years and 200 healthy controls aged 62.85 ± 6.03 years were included in this case-control study. Epidemiological data and qualitative food frequency data were investigated. Enzyme-linked immunosorbent assay measuring serum immunoglobulin G antibodies was used to determine H. pylori seropositivity. An unconditional logistic regression model was used to assess the association between H. pylori infection and EPL risk dichotomized by gender, age, and the use of tobacco and alcohol, as well as the association between dietary factors and the risk of H. pylori infection.RESULTS A total of 47(23.5%) EPL cases and 58(29.0%) healthy controls had positive H. pylori infection. An inverse relation between H. pylori infection and the risk of EPL was found in the group of drinkers after adjustment for covariates [odds ratio(OR) = 0.32, 95% confidence interval(95%CI): 0.11-0.95]. Additionally, peanut intake was significantly associated with a decreased risk of H. pylori infection(OR = 0.39, 95%CI: 0.20-0.74).CONCLUSION Our study suggested that H. pylori infection may decrease the risk of EPL for drinkers in a rural adult Chinese population, and the consumption of peanut may reduce the risk of H. pylori infection. These findings should be framed as preliminary evidence, and further studies are required to address whether the mechanisms are related to the localization of lesions and alcohol consumption.展开更多
Several features of drug-induced mucosal alterations have been observed in the upper gastrointestinal tract,i.e.,the esophagus,stomach,and duodenum.These include pill-induced esophagitis,desquamative esophagitis,worse...Several features of drug-induced mucosal alterations have been observed in the upper gastrointestinal tract,i.e.,the esophagus,stomach,and duodenum.These include pill-induced esophagitis,desquamative esophagitis,worsening of gastroesophageal reflux,chemotherapy-induced esophagitis,proton pump inhibitor-induced gastric mucosal changes,medication-induced gastric erosions and ulcers,pseudomelanosis of the stomach,olmesartan-related gastric mucosal inflammation,lanthanum deposition in the stomach,zinc acetate hydrate tabletinduced gastric ulcer,immune-related adverse event gastritis,olmesartan-associated sprue-like enteropathy,pseudomelanosis of the duodenum,and lanthanum deposition in the duodenum.For endoscopists,acquiring accurate knowledge regarding these diverse drug-induced mucosal alterations is crucial not only for the correct diagnosis of these lesions but also for differential diag-nosis of other conditions.This minireview aims to provide essential information on druginduced mucosal alterations observed on esophagogastroduodenoscopy,along with representative endoscopic images.展开更多
基金Supported by the Natural Science Foundation of Jiangsu,No.BK20171508.
文摘BACKGROUND A convolutional neural network(CNN) is a deep learning algorithm based on the principle of human brain visual cortex processing and image recognition.AIM To automatically identify the invasion depth and origin of esophageal lesions based on a CNN.METHODS A total of 1670 white-light images were used to train and validate the CNN system.The method proposed in this paper included the following two parts:(1)Location module,an object detection network,locating the classified main image feature regions of the image for subsequent classification tasks;and(2) Classification module,a traditional classification CNN,classifying the images cut out by the object detection network.RESULTS The CNN system proposed in this study achieved an overall accuracy of 82.49%,sensitivity of 80.23%,and specificity of 90.56%.In this study,after follow-up pathology,726 patients were compared for endoscopic pathology.The misdiagnosis rate of endoscopic diagnosis in the lesion invasion range was approximately 9.5%;41 patients showed no lesion invasion to the muscularis propria,but 36 of them pathologically showed invasion to the superficial muscularis propria.The patients with invasion of the tunica adventitia were all treated by surgery with an accuracy rate of 100%.For the examination of submucosal lesions,the accuracy of endoscopic ultrasonography(EUS) was approximately 99.3%.Results of this study showed that EUS had a high accuracy rate for the origin of submucosal lesions,whereas the misdiagnosis rate was slightly high in the evaluation of the invasion scope of lesions.Misdiagnosis could be due to different operating and diagnostic levels of endoscopists,unclear ultrasound probes,and unclear lesions.CONCLUSION This study is the first to recognize esophageal EUS images through deep learning,which can automatically identify the invasion depth and lesion origin of submucosal tumors and classify such tumors,thereby achieving good accuracy.In future studies,this method can provide guidance and help to clinical endoscopists.
文摘BACKGROUND Acute esophageal mucosal lesions(AEMLs)are an underrecognized and largely unexplored disease.Endoscopic findings are similar,and a higher percentage of AEML could be misdiagnosed as reflux esophagitis Los Angeles classification grade D(RE-D).These diseases could have different pathologies and require different treatments.AIM To compare AEML and RE-D to confirm that the two diseases are different from each other and to clarify the clinical features of AEML.METHODS We selected emergency endoscopic cases of upper gastrointestinal bleeding with circumferential esophageal mucosal injury and classified them into AEML and RE-D groups according to the mucosal injury’s shape on the oral side.We examined patient background,blood sampling data,comorbidities at onset,endoscopic characteristics,and outcomes in each group.RESULTS Among the emergency cases,the AEML and RE-D groups had 105(3.1%)and 48(1.4%)cases,respectively.Multiple variables exhibited significantly different results,indicating that these two diseases are distinct.The clinical features of AEML consisted of more comorbidities[risk ratio(RR):3.10;95%confidence interval(CI):1.68–5.71;P<0.001]and less endoscopic hemostasis compared with RE-D(RR:0.25;95%CI:0.10–0.63;P<0.001).Mortality during hospitalization was higher in the AEML group(RR:3.43;95%CI:0.82–14.40;P=0.094),and stenosis developed only in the AEML group.CONCLUSION AEML and RE-D were clearly distinct diseases with different clinical features.AEML may be more common than assumed,and the potential for its presence should be taken into account in cases of upper gastrointestinal bleeding with comorbidities.
基金Supported by the Fellowship of China Postdoctoral Science Foundation,No. 2022M710675the National Natural Science Foundation of China,No. 81673147the Danone Dietary Nutrition Research and Education Foundation,No. DIC2020-08。
文摘BACKGROUND Helicobacter pylori(H. pylori) is a Gram-negative bacterium found in the upper digestive tract. Although H. pylori infection is an identified risk factor for gastric cancer, its role in esophageal squamous cell carcinoma(ESCC) remains a topic of much debate.AIM To evaluate the association between H. pylori infection and the risk of precancerous lesions of ESCC, and further explore the association between dietary factors and the risk of H. pylori infection.METHODS Two hundred patients with esophageal precancerous lesions(EPL) aged 63.01 ± 6.08 years and 200 healthy controls aged 62.85 ± 6.03 years were included in this case-control study. Epidemiological data and qualitative food frequency data were investigated. Enzyme-linked immunosorbent assay measuring serum immunoglobulin G antibodies was used to determine H. pylori seropositivity. An unconditional logistic regression model was used to assess the association between H. pylori infection and EPL risk dichotomized by gender, age, and the use of tobacco and alcohol, as well as the association between dietary factors and the risk of H. pylori infection.RESULTS A total of 47(23.5%) EPL cases and 58(29.0%) healthy controls had positive H. pylori infection. An inverse relation between H. pylori infection and the risk of EPL was found in the group of drinkers after adjustment for covariates [odds ratio(OR) = 0.32, 95% confidence interval(95%CI): 0.11-0.95]. Additionally, peanut intake was significantly associated with a decreased risk of H. pylori infection(OR = 0.39, 95%CI: 0.20-0.74).CONCLUSION Our study suggested that H. pylori infection may decrease the risk of EPL for drinkers in a rural adult Chinese population, and the consumption of peanut may reduce the risk of H. pylori infection. These findings should be framed as preliminary evidence, and further studies are required to address whether the mechanisms are related to the localization of lesions and alcohol consumption.
文摘Several features of drug-induced mucosal alterations have been observed in the upper gastrointestinal tract,i.e.,the esophagus,stomach,and duodenum.These include pill-induced esophagitis,desquamative esophagitis,worsening of gastroesophageal reflux,chemotherapy-induced esophagitis,proton pump inhibitor-induced gastric mucosal changes,medication-induced gastric erosions and ulcers,pseudomelanosis of the stomach,olmesartan-related gastric mucosal inflammation,lanthanum deposition in the stomach,zinc acetate hydrate tabletinduced gastric ulcer,immune-related adverse event gastritis,olmesartan-associated sprue-like enteropathy,pseudomelanosis of the duodenum,and lanthanum deposition in the duodenum.For endoscopists,acquiring accurate knowledge regarding these diverse drug-induced mucosal alterations is crucial not only for the correct diagnosis of these lesions but also for differential diag-nosis of other conditions.This minireview aims to provide essential information on druginduced mucosal alterations observed on esophagogastroduodenoscopy,along with representative endoscopic images.