检索结果-南通市图书馆

Enhanced segmentation of gastrointestinal polyps from capsule endoscopy images with artifacts using ensemble learning

引用

World Journal of Gastroenterology 2022年第41期28卷 5931-5943页

作者： Jun-Xiao Zhou Zhan Yang Ding-Hao Xi Shou-Jun Dai Zhi-Qiang Feng Jun-Yan Li Wei Xu Hong Wang Department of Gastroenterology and Hepatology Guangzhou First People’s HospitalGuangzhou 510180Guangdong ProvinceChina School of Information Renmin University of ChinaBeijing 100872China

BACKGROUND endoscopy artifacts are widespread in real capsule endoscopy(CE)images but not in high-quality standard datasets.AIM To improve the segmentation performance of polyps from CE images with artifacts based on ensemble learning.METHODS We collected 277 polyp images with CE artifacts from 5760 h of videos from 480 patients at Guangzhou First People’s Hospital from January 2016 to December 2019.Two public high-quality standard external datasets were retrieved and used for the comparison experiments.For each dataset,we randomly segmented the data into training,validation,and testing sets for model training,selection,and testing.We compared the performance of the base models and the ensemble model in segmenting polyps from images with artifacts.RESULTS The performance of the semantic segmentation model was affected by artifacts in the sample images,which also affected the results of polyp detection by CE using a single model.The evaluation based on real datasets with artifacts and standard datasets showed that the ensemble model of all state-of-the-art models performed better than the best corresponding base learner on the real dataset with artifacts.Compared with the corresponding optimal base learners,the intersection over union(IoU)and dice of the ensemble learning model increased to different degrees,ranging from 0.08%to 7.01%and 0.61%to 4.93%,respectively.Moreover,in the standard datasets without artifacts,most of the ensemble models were slightly better than the base learner,as demonstrated by the IoU and dice increases ranging from-0.28%to 1.20%and-0.61%to 0.76%,respectively.CONCLUSION Ensemble learning can improve the segmentation accuracy of polyps from CE images with artifacts.Our results demonstrated an improvement in the detection rate of polyps with interference from artifacts.

关键词： Artifacts capsule endoscopy Polyps Ensemble learning Segmentation Robustness

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Convolutional neural network-based segmentation network applied to image recognition of angiodysplasias lesion under capsule endoscopy

引用

World Journal of Gastroenterology 2023年第5期29卷 879-889页

作者： Ye Chu Fang Huang Min Gao Duo-Wu Zou Jie Zhong Wei Wu Qi Wang Xiao-Nan Shen Ting-Ting Gong Yuan-Yi Li Li-Fu Wang Department of Gastroenterology Shanghai Jiao Tong University School of MedicineRuijin HospitalShanghai 200025China Technology Platform Department Jinshan Science&Technology(Group)Co.Ltd.Chongqing 401120China

BACKGROUND Small intestinal vascular malformations(angiodysplasias)are common causes of small intestinal bleeding.While capsule endoscopy has become the primary diagnostic method for angiodysplasia,manual reading of the entire gastrointestinal tract is time-consuming and requires a heavy workload,which affects the accuracy of diagnosis.AIM To evaluate whether artificial intelligence can assist the diagnosis and increase the detection rate of angiodysplasias in the small intestine,achieve automatic disease detection,and shorten the capsule endoscopy(CE)reading time.METHODS A convolutional neural network semantic segmentation model with a feature fusion method,which automatically recognizes the category of vascular dysplasia under CE and draws the lesion contour,thus improving the efficiency and accuracy of identifying small intestinal vascular malformation lesions,was ***-50 was used as the skeleton network to design the fusion mechanism,fuse the shallow and depth features,and classify the images at the pixel level to achieve the segmentation and recognition of vascular dysplasia.The training set and test set were constructed and compared with PSPNet,Deeplab3+,and UperNet.RESULTS The test set constructed in the study achieved satisfactory results,where pixel accuracy was 99%,mean intersection over union was 0.69,negative predictive value was 98.74%,and positive predictive value was 94.27%.The model parameter was 46.38 M,the float calculation was 467.2 G,and the time length to segment and recognize a picture was 0.6 s.CONCLUSION Constructing a segmentation network based on deep learning to segment and recognize angiodysplasias lesions is an effective and feasible method for diagnosing angiodysplasias lesions.

关键词： Artificial intelligence Image segmentation capsule endoscopy Angiodysplasias

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

First prospective European study for the feasibility and safety of magnetically controlled capsule endoscopy in gastric mucosal abnormalities

引用

World Journal of Gastroenterology 2022年第20期28卷 2227-2242页

作者： Milán Szalai Krisztina Helle Barbara Dorottya Lovász Ádám Finta András Rosztóczy László Oczella László Madácsy Department of Gastroenterology Endo-Kapszula Health Centre and Endoscopy UnitSzékesfehérvár 8000Hungary Department of Internal Medicine University of SzegedSzeged 6725Hungar

BACKGROUND While capsule endoscopy(CE)is the gold standard diagnostic method of detecting small bowel(SB)diseases and disorders,a novel magnetically controlled capsule endoscopy(MCCE)system provides non-invasive evaluation of the gastric mucosal surface,which can be performed without sedation or discomfort.During standard SBCE,passive movement of the CE may cause areas of the complex anatomy of the gastric mucosa to remain unexplored,whereas the precision of MCCE capsule movements inside the stomach promises better visualization of the entire mucosa.AIM To evaluate the Ankon MCCE system’s feasibility,safety,and diagnostic yield in patients with gastric or SB disorders.METHODS Of outpatients who were referred for SBCE,284(male/female:149/135)were prospectively enrolled and evaluated by MCCE.The stomach was examined in the supine,left,and right lateral decubitus positions without sedation.Next,all patients underwent a complete SBCE study protocol.The gastric mucosa was explored with the Ankon MCCE system with active magnetic control of the capsule endoscope in the stomach,applying three standardized pre-programmed computerized algorithms in combination with manual control of the magnetic movements.RESULTS The urea breath test revealed Helicobacter pylori positivity in 32.7%of patients.The mean gastric and SB transit times with MCCE were 0 h 47 min 40 s and 3 h 46 min 22 s,respectively.The average total time of upper gastrointestinal MCCE examination was 5 h 48 min 35 s.Active magnetic movement of the Ankon capsule through the pylorus was successful in 41.9%of patients.Overall diagnostic yield for detecting abnormalities in the stomach and SB was 81.9%(68.6%minor;13.3%major pathologies);25.8%of abnormalities were in the SB;74.2%were in the stomach.The diagnostic yield for stomach/SB was 55.9%/12.7%for minor and 4.9%/8.4%for major pathologies.CONCLUSION MCCE is a feasible,safe diagnostic method for evaluating gastric mucosal lesions and is a promising non-invasive screening tool to decrease morbidity and mortality in

关键词： Bowel diseases capsule endoscopy Diagnostic techniques Gastrointestinal diseases Gastric mucosa Helicobacter pylori

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

capsule endoscopy and push enteroscopy in the diagnosis of obscure gastrointestinal bleeding

引用

Chinese Medical Journal 2004年第7期117卷 1045-1049页

作者：戈之铮胡运彪萧树东 Department of Gastroenterology

Background In obscure gastrointestinal (GI) bleeding, it is often difficult to detect the bleeding sites located in the small bowel with conventional radiological, scintigraphic or angiographic techniques. Push enteroscopy and capsule endoscopy are currently considered to be the most effective diagnostic procedures. The aim of this study was to compare the detection rates between capsule endoscopy and push enteroscopy. Methods From May 2002 through January 2003, we prospectively examined by capsule endoscopy 39 patients with suspected small bowel diseases, in particular GI bleeding of unknown origin in Renji Hospital. Among them, 32 complained of obscure recurrent GI bleeding. Between January 1993 and October 1996, we used push enteroscopy on 36 patients who suffered from unexplained GI bleeding. All patients had prior normal results on gastroscopy, colonoscopy, small bowel barium radiography, scintigraphy and/or angiography. Results M2A capsule endoscopy disclosed abnormal small bowel findings in 26 (82%) out of 32 patients. Twenty-one of them had significant pathological findings explaining their clinical disorders. Diagnostic yield was therefore 66% (21 of 32 patients). Definite bleeding sites diagnosed by capsule endoscopy in 21 patients included angiodysplasia (8), inflammatory small-bowel (5), small-bowel polyps (4), gastrointestinal stromal tumour (2), carcinoid tumour and lipoma (1), and hemorrhagic gastritis (1). Push enteroscopy detected the definite sources of bleeding in 9 (25%) of the 36 patients. Patients with definite bleeding sources included angiodysplasias (2), leiomyosarcoma (2), leiomyoma (1), lymphoma (1), Crohn’s disease (1), small-bowel polyps (1) and adenocarcinoma of ampulla (1). Suspected bleeding sources were shown by push enteroscopy in two additional patients (6%), and in other five patients (16%) by capsule endoscopy. Conclusions The present study of patients with obscure GI bleeding showed that capsule endoscopy significantly superior to push enteroscopy in detecting G

关键词： capsule endoscopy push enteroscopy obscure gastrointestinal bleeding

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Artificial intelligence in detection of small bowel lesions and their bleeding risk:A new step forward

引用

World Journal of Gastroenterology 2024年第18期30卷 2482-2484页

作者： Silvia Cocca Giuseppina Pontillo Giuseppe Grande Rita Conigliaro Gastroenterology and endoscopy Unit Azienda Ospedaliero Universitaria Policlinico di ModenaModena 41121Italy Gastroenterology and endoscopy Unit Presidio Ospedaliero San Giuseppe Moscati(AversaCE)-ASL CasertaCaserta 81100Italy Department of Gastroenterology and Digestive endoscopy Azienda Ospedaliero Universitaria di ModenaModena 41121Italy

The present letter to the editor is related to the study with the title“Automatic detection of small bowel(SB)lesions with different bleeding risk based on deep learning models”.capsule endoscopy(CE)is the main tool to assess SB diseases but it is a time-consuming procedure with a significant error rate.The development of artificial intelligence(AI)in CE could simplify physicians’tasks.The novel deep learning model by Zhang et al seems to be able to identify various SB lesions and their bleeding risk,and it could pave the way to next perspective studies to better enhance the diagnostic support of AI in the detection of different types of SB lesions in clinical practice.

关键词： capsule endoscopy Small bowel Artificial intelligence Bleeding risk Vascular lesions

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Automatic detection of small bowel lesions with different bleeding risks based on deep learning models

引用

World Journal of Gastroenterology 2024年第2期30卷 170-183页

作者： Rui-Ya Zhang Peng-Peng Qiang Ling-Jun Cai Tao Li Yan Qin Yu Zhang Yi-Qing Zhao Jun-Ping Wang Department of Gastroenterology The Fifth Clinical Medical College of Shanxi Medical UniversityTaiyuan 030012Shanxi ProvinceChina School of Computer and Information Technology Shanxi UniversityTaiyuan 030006Shanxi ProvinceChina School of Life Sciences and Technology Mudanjiang Normal UniversityMudanjiang 157011Heilongjiang ProvinceChina

BACKGROUND Deep learning provides an efficient automatic image recognition method for small bowel(SB)capsule endoscopy(CE)that can assist physicians in diagnosis.However,the existing deep learning models present some unresolved challenges.AIM To propose a novel and effective classification and detection model to automatically identify various SB lesions and their bleeding risks,and label the lesions accurately so as to enhance the diagnostic efficiency of physicians and the ability to identify high-risk bleeding groups.METHODS The proposed model represents a two-stage method that combined image classification with object detection.First,we utilized the improved ResNet-50 classification model to classify endoscopic images into SB lesion images,normal SB mucosa images,and invalid images.Then,the improved YOLO-V5 detection model was utilized to detect the type of lesion and its risk of bleeding,and the location of the lesion was marked.We constructed training and testing sets and compared model-assisted reading with physician reading.RESULTS The accuracy of the model constructed in this study reached 98.96%,which was higher than the accuracy of other systems using only a single module.The sensitivity,specificity,and accuracy of the model-assisted reading detection of all images were 99.17%,99.92%,and 99.86%,which were significantly higher than those of the endoscopists’diagnoses.The image processing time of the model was 48 ms/image,and the image processing time of the physicians was 0.40±0.24 s/image(P<0.001).CONCLUSION The deep learning model of image classification combined with object detection exhibits a satisfactory diagnostic effect on a variety of SB lesions and their bleeding risks in CE images,which enhances the diagnostic efficiency of physicians and improves the ability of physicians to identify high-risk bleeding groups.

关键词： Artificial intelligence Deep learning capsule endoscopy Image classification Object detection Bleeding risk

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Intermittent melena and refractory anemia due to jejunal cavernous lymphangioma:A case report

引用

World Journal of Gastrointestinal Surgery 2024年第4期16卷 1208-1214页

作者： Kai-Rui Liu Sheng Zhang Wei-Run Chen You-Xing Huang Xu-Guang Li Department of Abdominal Surgery The Second Affiliated Hospital of Guangzhou University of Chinese MedicineGuangzhou 510000Guangdong ProvinceChina Department of General Surgery The Affiliated Brain Hospital of Guangzhou Medical UniversityGuangzhou 510000Guangdong ProvinceChina Key Laboratory of Neurogenetics and Channelopathies of Guangdong Province and The Ministry of Education of China Guangzhou Medical UniversityGuangzhou 510000Guangdong ProvinceChina

BACKGROUND Lymphangiomas in the gastrointestinal tract are extremely rare in adults.As a benign lesion,small intestine lymphangiomas often remain asymptomatic and pose challenges for definitive diagnosis.However,lymphangiomas can give rise to complications such as abdominal pain,bleeding,volvulus,and intussusception.Here,we report a case of jejunal cavernous lymphangioma that presented with intermittent melena and refractory anemia in a male adult.CASE SUMMARY A 66-year-old man presented with intermittent melena,fatigue and refractory anemia nine months prior.Esophagogastroduodenoscopy and colonoscopy were performed many times and revealed no apparent bleeding.Conservative management,including transfusion,hemostasis,gastric acid secretion inhibition and symptomatic treatment,was performed,but the lesions tended to recur shortly after surgery.Ultimately,the patient underwent capsule endoscopy,which revealed a more than 10 cm lesion accompanied by active bleeding.After singleballoon enteroscopy and biopsy,a diagnosis of jejunal cavernous lymphangioma was confirmed,and the patient underwent surgical resection.No complications or recurrences were observed postoperatively.CONCLUSION Jejunal cavernous lymphangioma should be considered a cause of obscure gastrointestinal bleeding.capsule endoscopy and single-balloon enteroscopy can facilitate diagnosis.Surgical resection is an effective management method.

关键词： Intermittent melena Refractory anemia capsule endoscopy Single-balloon enteroscopy Jejunal cavernous lymphangioma Enterectomy Case report

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Single-center retrospective study of the diagnostic value of doubleballoon enteroscopy in Meckel’s diverticulum with bleeding

引用

World Journal of Gastrointestinal Surgery 2024年第4期16卷 1043-1054页

作者： Tian He Chao Yang Jing Wang Ji-Sheng Zhong Ai-Hua Li Ya-Jing Yin Li-Ling Luo Chun-Mei Rao Nian-Fen Mao Qiang Guo Zan Zuo Wen Zhang Ping Wan Yunnan Digestive endoscopy Clinical Medical Center Department of GastroenterologyThe First People’s Hospital of Yunnan ProvinceThe Affiliated Hospital of Kunming University of Science and TechnologyKunming 650032Yunnan ProvinceChina Department of Medicine Kunming University of Science and TechnologyKunming 650093Yunnan ProvinceChina School of Medicine Yunnan University of Traditional Chinese MedicineKunming 650011Yunnan ProvinceChina Department of Gastroenterology Qujing Hospital of Traditional Chinese MedicineQujing 655000Yunnan ProvinceChina Department of Gastroenterology Yunnan University of Traditional Chinese MedicineKunming 650011Yunnan ProvinceChina

BACKGROUND The study aimed to analyze the characteristic clinical manifestations of patients with intestinal disease Meckel’s diverticulum(MD)complicated by digestive tract hemorrhage.Moreover,we aimed to evaluate the value of double-balloon enteroscopy(DBE)in MD diagnosis and the prognosis after laparoscopic diverticula resection.AIM To evaluate the value of DBE in the diagnosis and the prognosis after laparoscopic diverticula resection for MD with bleeding.METHODS The study retrospectively analyzed relevant data from 84 MD patients treated between January 2015 and March 2022 and recorded their clinical manifestations,auxiliary examination,and follow-up after laparoscopic resection of diverticula.RESULTS(1)Among 84 MD patients complicated with hemorrhage,77 were male,and 7 were female with an average age of 31.31±10.75 years.The incidence was higher in men than in women of different ages;(2)Among the 84 MD patients,65(78.40%)had defecated dark red stools,and 50(58.80%)had no accompanying symptoms during bleeding,indicating that most MD bleeding appeared a dark red stool without accompanying symptoms;(3)The shock index of 71 patients(85.20%)was30%;(4)The DBE-positive rate was 100%(54/54),99mTcpertechnetate-positive scanning rate was 78%(35/45)compared with capsule endoscopy(36%)and small intestine computed tomography(19%).These results suggest that DBE and 99mTc-pertechnetate scans had significant advantages in diagnosing MD and bleeding,especially DBE was a highly precise examination method in MD diagnosis;(5)A total of 54 MD patients with hemorrhage underwent DBE examination before surgery.DBE endoscopy revealed many mucosal manifestations including normal appearance,inflammatory changes,ulcerative changes,diverticulum inversion,and nodular hyperplasia,with ulcerative changes being the most common(53.70%).This suggests that diverticular mucosal ulcer was the main cause of MD and bleeding;and(6

关键词： Meckel’s diverticulum with bleeding Double-balloon colonoscopy 99mTc-pertechnetate scanning capsule endoscopy Ectopic gastric mucosa

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

A novel cleansing score system for capsule endoscopy

引用

World Journal of Gastroenterology 2010年第7期16卷 875-880页

作者： Sung Chul Park Bora Keum Jong Jin Hyun Yeon Seok Seo Yong Sik Kim Yoon Tae Jeen Hoon Jai Chun Soon Ho Um Chang Duck Kim Ho Sang Ryu Division of Gastroenterology and Hepatology Department of Internal MedicineKorea University Anam HospitalInstitute of Digestive Disease and NutritionKorea University College of MedicineSeoul 136-705South Korea

AIM:To suggest a new cleansing score system for small bowel preparation and to evaluate its clinical efficacy.METHODS:Twenty capsule endoscopy cases were reviewed and small bowel preparation was assessed with the new scoring system.For the assessment,two visual parameters were used:proportion of visualized mucosa and degree of obscuration.Representative frames from small bowel images were serially selected and scored at 5-min intervals.Intraclass correlation coefficient(ICC)was obtained to assess the reliability of the new scoring system.For efficacy evaluation and validation,scores of our new scoring system were compared with another previously reported cleansing grading system.RESULTS:Concordance with the previous system,inter-observer agreement,and intra-patient agreement were excellent with ICC values of 0.82,0.80,and 0.76,respectively.The intra-observer agreements at four-week intervals were also excellent.The cutoff value of adequate image quality was found to be 2.25.CONCLUSION:Our new scoring system is simple,efficient,and can be considered to be applicable in clinical practice and research.

关键词： capsule endoscopy Cleansing score system

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

The role of capsule endoscopy combined with double-balloon enteroscopy in diagnosis of small bowel diseases

引用

Chinese Medical Journal 2007年第1期120卷 30-35页

作者： LI Xiao-bo GE Zhi-zheng DAI Jun GAO Yun-jie LIU Wen-zhong HU Yun-biao XIAO Shu-dong Department of Gastroenterology Renji Hospital Medical Collegeof Shanghai Jiaotong University Shanghai Institute of DigestiveDiseases Shanghai 200001 China

Background The diagnosis of small bowel diseases remains relatively inefficient using traditional imaging techniques. capsule endoscopy （CE） and double-balloon enteroscopy （DBE） are two novel methods of enteroscopy for examining the entire small bowel. The aim of this study was to evaluate the detection rate and diagnostic accuracy of CE and DBE in patients with suspected small bowel diseases and to investigate the clinical significance of combined use of these two novel modalities. Methods Two hundred and eighteen patients were evaluated for suspected small bowel disease, including 116 with obscure gastrointestinal bleeding and 102 with obscure abdominal pain or chronic diarrhea. One hundred and sixty-five out of these patients underwent CE first and 53 patients underwent DBE （under anesthesia with propofol） first. DBE was recommended after negative or equivocal evaluation on CE and vise versa. Introduction of the endoscope during DBE was either orally or anally and the patients were referred for a second procedure using the opposite route several days later when no abnormalities were found on the first procedure. The detection rates, diagnostic accuracy, tolerance and frequency of adverse events of these two modalities were then analyzed. Results Failure of the procedure was seen in one patient with CE and in two patients with DBE. Sixty-four DBE procedures were carded out in 51 patients; by the oral route in 34 cases, the anal route in 4 and both routes in 13 cases. The overall detection rate of small bowel diseases using CE （72.0%, 118/164） was superior to that with DBE （41.2%, 21/51）; X2=16.1218, P〈0.0001. The diagnostic rate （51.8%, 85/164） was also higher than that with the latter procedure （39.2%, 20/51）, but was not significantly different （X^2=2.4771, P〉0.05）. Furthermore, the detection rate of small bowel diseases in patients with obscure gastrointestinal bleeding using CE （88.0%, 88/100） was superior to that of DBE （60.0%, 9/15）; X2=7.7457, P=0.0054. Lesions were detected by DBE in 1 out of 4 patients

关键词： capsule endoscopy double-balloon enteroscopy small intestinal disease obscure gastrointestinal bleeding

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：