|
1
|
Li Q, Xie W, Wang Y, Qin K, Huang M, Liu T, Chen Z, Chen L, Teng L, Fang Y, Ye L, Chen Z, Zhang J, Li A, Yang W, Liu S. A Deep Learning Application of Capsule Endoscopic Gastric Structure Recognition Based on a Transformer Model. J Clin Gastroenterol 2024; 58:937-943. [PMID: 38457410 DOI: 10.1097/mcg.0000000000001972] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/28/2023] [Accepted: 12/26/2023] [Indexed: 03/10/2024]
Abstract
BACKGROUND Gastric structure recognition systems have become increasingly necessary for the accurate diagnosis of gastric lesions in capsule endoscopy. Deep learning, especially using transformer models, has shown great potential in the recognition of gastrointestinal (GI) images according to self-attention. This study aims to establish an identification model of capsule endoscopy gastric structures to improve the clinical applicability of deep learning to endoscopic image recognition. METHODS A total of 3343 wireless capsule endoscopy videos collected at Nanfang Hospital between 2011 and 2021 were used for unsupervised pretraining, while 2433 were for training and 118 were for validation. Fifteen upper GI structures were selected for quantifying the examination quality. We also conducted a comparison of the classification performance between the artificial intelligence model and endoscopists by the accuracy, sensitivity, specificity, and positive and negative predictive values. RESULTS The transformer-based AI model reached a relatively high level of diagnostic accuracy in gastric structure recognition. Regarding the performance of identifying 15 upper GI structures, the AI model achieved a macroaverage accuracy of 99.6% (95% CI: 99.5-99.7), a macroaverage sensitivity of 96.4% (95% CI: 95.3-97.5), and a macroaverage specificity of 99.8% (95% CI: 99.7-99.9) and achieved a high level of interobserver agreement with endoscopists. CONCLUSIONS The transformer-based AI model can accurately evaluate the gastric structure information of capsule endoscopy with the same performance as that of endoscopists, which will provide tremendous help for doctors in making a diagnosis from a large number of images and improve the efficiency of examination.
Collapse
Affiliation(s)
- Qingyuan Li
- Guangdong Provincial Key Laboratory of Gastroenterology, Department of Gastroenterology, Nanfang Hospital
| | - Weijie Xie
- School of Biomedical Engineering
- Department of Information, Guangzhou First People's Hospital, School of Medicine, South China University of Technology
| | - Yusi Wang
- Guangdong Provincial Key Laboratory of Gastroenterology, Department of Gastroenterology, Nanfang Hospital
| | - Kaiwen Qin
- Guangdong Provincial Key Laboratory of Gastroenterology, Department of Gastroenterology, Nanfang Hospital
| | - Mei Huang
- Guangdong Provincial Key Laboratory of Gastroenterology, Department of Gastroenterology, Nanfang Hospital
| | | | | | - Lu Chen
- Guangdong Provincial Key Laboratory of Gastroenterology, Department of Gastroenterology, Nanfang Hospital
| | - Lan Teng
- Guangdong Provincial Key Laboratory of Gastroenterology, Department of Gastroenterology, Nanfang Hospital
| | - Yuxin Fang
- Guangdong Provincial Key Laboratory of Gastroenterology, Department of Gastroenterology, Nanfang Hospital
| | - Liuhua Ye
- Nanfang Hospital, The First School of Clinical Medicine, Southern Medical University
| | - Zhenyu Chen
- Guangdong Provincial Key Laboratory of Gastroenterology, Department of Gastroenterology, Nanfang Hospital
| | - Jie Zhang
- Guangdong Provincial Key Laboratory of Gastroenterology, Department of Gastroenterology, Nanfang Hospital
| | - Aimin Li
- Guangdong Provincial Key Laboratory of Gastroenterology, Department of Gastroenterology, Nanfang Hospital
| | - Wei Yang
- School of Biomedical Engineering
- Pazhou Lab, Guangzhou, Guangdong
| | - Side Liu
- Guangdong Provincial Key Laboratory of Gastroenterology, Department of Gastroenterology, Nanfang Hospital
- Pazhou Lab, Guangzhou, Guangdong
- Department of Gastroenterology, Zhuhai People's Hospital, Zhuhai Hospital Affiliated with Jinan University, Zhuhai, China
| |
Collapse
|
|
2
|
Sumioka A, Tsuboi A, Oka S, Kato Y, Matsubara Y, Hirata I, Takigawa H, Yuge R, Shimamoto F, Tada T, Tanaka S. Disease surveillance evaluation of primary small-bowel follicular lymphoma using capsule endoscopy images based on a deep convolutional neural network (with video). Gastrointest Endosc 2023; 98:968-976.e3. [PMID: 37482106 DOI: 10.1016/j.gie.2023.07.024] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/31/2023] [Revised: 07/01/2023] [Accepted: 07/09/2023] [Indexed: 07/25/2023]
Abstract
BACKGROUND AND AIMS Capsule endoscopy (CE) is useful in evaluating disease surveillance for primary small-bowel follicular lymphoma (FL), but some cases are difficult to evaluate objectively. This study evaluated the usefulness of a deep convolutional neural network (CNN) system using CE images for disease surveillance of primary small-bowel FL. METHODS We enrolled 26 consecutive patients with primary small-bowel FL diagnosed between January 2011 and January 2021 who underwent CE before and after a watch-and-wait strategy or chemotherapy. Disease surveillance by the CNN system was evaluated by the percentage of FL-detected images among all CE images of the small-bowel mucosa. RESULTS Eighteen cases (69%) were managed with a watch-and-wait approach, and 8 cases (31%) were treated with chemotherapy. Among the 18 cases managed with the watch-and-wait approach, the outcome of lesion evaluation by the CNN system was almost the same in 13 cases (72%), aggravation in 4 (22%), and improvement in 1 (6%). Among the 8 cases treated with chemotherapy, the outcome of lesion evaluation by the CNN system was improvement in 5 cases (63%), almost the same in 2 (25%), and aggravation in 1 (12%). The physician and CNN system reported similar results regarding disease surveillance evaluation in 23 of 26 cases (88%), whereas a discrepancy between the 2 was found in the remaining 3 cases (12%), attributed to poor small-bowel cleansing level. CONCLUSIONS Disease surveillance evaluation of primary small-bowel FL using CE images by the developed CNN system was useful under the condition of excellent small-bowel cleansing level.
Collapse
Affiliation(s)
- Akihiko Sumioka
- Department of Gastroenterology, Hiroshima University Hospital, Hiroshima, Japan
| | - Akiyoshi Tsuboi
- Department of Endoscopy, Hiroshima University Hospital, Hiroshima, Japan
| | - Shiro Oka
- Department of Gastroenterology, Hiroshima University Hospital, Hiroshima, Japan
| | | | - Yuka Matsubara
- Department of Gastroenterology, Hiroshima University Hospital, Hiroshima, Japan
| | - Issei Hirata
- Department of Gastroenterology, Hiroshima University Hospital, Hiroshima, Japan
| | - Hidehiko Takigawa
- Department of Endoscopy, Hiroshima University Hospital, Hiroshima, Japan
| | - Ryo Yuge
- Department of Endoscopy, Hiroshima University Hospital, Hiroshima, Japan
| | - Fumio Shimamoto
- Faculty of Health Sciences, Hiroshima Shudo University, Hiroshima, Japan
| | - Tomohiro Tada
- AI Medical Service Inc, Tokyo, Japan; Department of Surgical Oncology, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan; Tada Tomohiro Institute of Gastroenterology and Proctology, Saitama, Japan
| | - Shinji Tanaka
- Department of Endoscopy, Hiroshima University Hospital, Hiroshima, Japan
| |
Collapse
|
|
3
|
Zhu S, Gao J, Liu L, Yin M, Lin J, Xu C, Xu C, Zhu J. Public Imaging Datasets of Gastrointestinal Endoscopy for Artificial Intelligence: a Review. J Digit Imaging 2023; 36:2578-2601. [PMID: 37735308 PMCID: PMC10584770 DOI: 10.1007/s10278-023-00844-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/27/2023] [Revised: 05/03/2023] [Accepted: 05/03/2023] [Indexed: 09/23/2023] Open
Abstract
With the advances in endoscopic technologies and artificial intelligence, a large number of endoscopic imaging datasets have been made public to researchers around the world. This study aims to review and introduce these datasets. An extensive literature search was conducted to identify appropriate datasets in PubMed, and other targeted searches were conducted in GitHub, Kaggle, and Simula to identify datasets directly. We provided a brief introduction to each dataset and evaluated the characteristics of the datasets included. Moreover, two national datasets in progress were discussed. A total of 40 datasets of endoscopic images were included, of which 34 were accessible for use. Basic and detailed information on each dataset was reported. Of all the datasets, 16 focus on polyps, and 6 focus on small bowel lesions. Most datasets (n = 16) were constructed by colonoscopy only, followed by normal gastrointestinal endoscopy and capsule endoscopy (n = 9). This review may facilitate the usage of public dataset resources in endoscopic research.
Collapse
Affiliation(s)
- Shiqi Zhu
- Department of Gastroenterology, The First Affiliated Hospital of Soochow University, 188 Shizi Street, Suzhou , Jiangsu, 215000, China
- Suzhou Clinical Center of Digestive Diseases, Suzhou, 215000, China
| | - Jingwen Gao
- Department of Gastroenterology, The First Affiliated Hospital of Soochow University, 188 Shizi Street, Suzhou , Jiangsu, 215000, China
- Suzhou Clinical Center of Digestive Diseases, Suzhou, 215000, China
| | - Lu Liu
- Department of Gastroenterology, The First Affiliated Hospital of Soochow University, 188 Shizi Street, Suzhou , Jiangsu, 215000, China
- Suzhou Clinical Center of Digestive Diseases, Suzhou, 215000, China
| | - Minyue Yin
- Department of Gastroenterology, The First Affiliated Hospital of Soochow University, 188 Shizi Street, Suzhou , Jiangsu, 215000, China
- Suzhou Clinical Center of Digestive Diseases, Suzhou, 215000, China
| | - Jiaxi Lin
- Department of Gastroenterology, The First Affiliated Hospital of Soochow University, 188 Shizi Street, Suzhou , Jiangsu, 215000, China
- Suzhou Clinical Center of Digestive Diseases, Suzhou, 215000, China
| | - Chang Xu
- Department of Gastroenterology, The First Affiliated Hospital of Soochow University, 188 Shizi Street, Suzhou , Jiangsu, 215000, China
- Suzhou Clinical Center of Digestive Diseases, Suzhou, 215000, China
| | - Chunfang Xu
- Department of Gastroenterology, The First Affiliated Hospital of Soochow University, 188 Shizi Street, Suzhou , Jiangsu, 215000, China.
- Suzhou Clinical Center of Digestive Diseases, Suzhou, 215000, China.
| | - Jinzhou Zhu
- Department of Gastroenterology, The First Affiliated Hospital of Soochow University, 188 Shizi Street, Suzhou , Jiangsu, 215000, China.
- Suzhou Clinical Center of Digestive Diseases, Suzhou, 215000, China.
| |
Collapse
|
|
4
|
Popa SL, Stancu B, Ismaiel A, Turtoi DC, Brata VD, Duse TA, Bolchis R, Padureanu AM, Dita MO, Bashimov A, Incze V, Pinna E, Grad S, Pop AV, Dumitrascu DI, Munteanu MA, Surdea-Blaga T, Mihaileanu FV. Enteroscopy versus Video Capsule Endoscopy for Automatic Diagnosis of Small Bowel Disorders-A Comparative Analysis of Artificial Intelligence Applications. Biomedicines 2023; 11:2991. [PMID: 38001991 PMCID: PMC10669430 DOI: 10.3390/biomedicines11112991] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/04/2023] [Revised: 10/26/2023] [Accepted: 11/05/2023] [Indexed: 11/26/2023] Open
Abstract
BACKGROUND Small bowel disorders present a diagnostic challenge due to the limited accessibility of the small intestine. Accurate diagnosis is made with the aid of specific procedures, like capsule endoscopy or double-ballon enteroscopy, but they are not usually solicited and not widely accessible. This study aims to assess and compare the diagnostic effectiveness of enteroscopy and video capsule endoscopy (VCE) when combined with artificial intelligence (AI) algorithms for the automatic detection of small bowel diseases. MATERIALS AND METHODS We performed an extensive literature search for relevant studies about AI applications capable of identifying small bowel disorders using enteroscopy and VCE, published between 2012 and 2023, employing PubMed, Cochrane Library, Google Scholar, Embase, Scopus, and ClinicalTrials.gov databases. RESULTS Our investigation discovered a total of 27 publications, out of which 21 studies assessed the application of VCE, while the remaining 6 articles analyzed the enteroscopy procedure. The included studies portrayed that both investigations, enhanced by AI, exhibited a high level of diagnostic accuracy. Enteroscopy demonstrated superior diagnostic capability, providing precise identification of small bowel pathologies with the added advantage of enabling immediate therapeutic intervention. The choice between these modalities should be guided by clinical context, patient preference, and resource availability. Studies with larger sample sizes and prospective designs are warranted to validate these results and optimize the integration of AI in small bowel diagnostics. CONCLUSIONS The current analysis demonstrates that both enteroscopy and VCE with AI augmentation exhibit comparable diagnostic performance for the automatic detection of small bowel disorders.
Collapse
Affiliation(s)
- Stefan Lucian Popa
- 2nd Medical Department, “Iuliu Hatieganu” University of Medicine and Pharmacy, 400000 Cluj-Napoca, Romania; (S.L.P.); (A.I.); (S.G.); (A.-V.P.); (T.S.-B.)
| | - Bogdan Stancu
- 2nd Surgical Department, “Iuliu Hatieganu” University of Medicine and Pharmacy, 400347 Cluj-Napoca, Romania;
| | - Abdulrahman Ismaiel
- 2nd Medical Department, “Iuliu Hatieganu” University of Medicine and Pharmacy, 400000 Cluj-Napoca, Romania; (S.L.P.); (A.I.); (S.G.); (A.-V.P.); (T.S.-B.)
| | - Daria Claudia Turtoi
- Faculty of Medicine, “Iuliu Hatieganu“ University of Medicine and Pharmacy, 400000 Cluj-Napoca, Romania; (D.C.T.); (V.D.B.); (T.A.D.); (R.B.); (A.M.P.); (M.O.D.); (A.B.); (V.I.); (E.P.)
| | - Vlad Dumitru Brata
- Faculty of Medicine, “Iuliu Hatieganu“ University of Medicine and Pharmacy, 400000 Cluj-Napoca, Romania; (D.C.T.); (V.D.B.); (T.A.D.); (R.B.); (A.M.P.); (M.O.D.); (A.B.); (V.I.); (E.P.)
| | - Traian Adrian Duse
- Faculty of Medicine, “Iuliu Hatieganu“ University of Medicine and Pharmacy, 400000 Cluj-Napoca, Romania; (D.C.T.); (V.D.B.); (T.A.D.); (R.B.); (A.M.P.); (M.O.D.); (A.B.); (V.I.); (E.P.)
| | - Roxana Bolchis
- Faculty of Medicine, “Iuliu Hatieganu“ University of Medicine and Pharmacy, 400000 Cluj-Napoca, Romania; (D.C.T.); (V.D.B.); (T.A.D.); (R.B.); (A.M.P.); (M.O.D.); (A.B.); (V.I.); (E.P.)
| | - Alexandru Marius Padureanu
- Faculty of Medicine, “Iuliu Hatieganu“ University of Medicine and Pharmacy, 400000 Cluj-Napoca, Romania; (D.C.T.); (V.D.B.); (T.A.D.); (R.B.); (A.M.P.); (M.O.D.); (A.B.); (V.I.); (E.P.)
| | - Miruna Oana Dita
- Faculty of Medicine, “Iuliu Hatieganu“ University of Medicine and Pharmacy, 400000 Cluj-Napoca, Romania; (D.C.T.); (V.D.B.); (T.A.D.); (R.B.); (A.M.P.); (M.O.D.); (A.B.); (V.I.); (E.P.)
| | - Atamyrat Bashimov
- Faculty of Medicine, “Iuliu Hatieganu“ University of Medicine and Pharmacy, 400000 Cluj-Napoca, Romania; (D.C.T.); (V.D.B.); (T.A.D.); (R.B.); (A.M.P.); (M.O.D.); (A.B.); (V.I.); (E.P.)
| | - Victor Incze
- Faculty of Medicine, “Iuliu Hatieganu“ University of Medicine and Pharmacy, 400000 Cluj-Napoca, Romania; (D.C.T.); (V.D.B.); (T.A.D.); (R.B.); (A.M.P.); (M.O.D.); (A.B.); (V.I.); (E.P.)
| | - Edoardo Pinna
- Faculty of Medicine, “Iuliu Hatieganu“ University of Medicine and Pharmacy, 400000 Cluj-Napoca, Romania; (D.C.T.); (V.D.B.); (T.A.D.); (R.B.); (A.M.P.); (M.O.D.); (A.B.); (V.I.); (E.P.)
| | - Simona Grad
- 2nd Medical Department, “Iuliu Hatieganu” University of Medicine and Pharmacy, 400000 Cluj-Napoca, Romania; (S.L.P.); (A.I.); (S.G.); (A.-V.P.); (T.S.-B.)
| | - Andrei-Vasile Pop
- 2nd Medical Department, “Iuliu Hatieganu” University of Medicine and Pharmacy, 400000 Cluj-Napoca, Romania; (S.L.P.); (A.I.); (S.G.); (A.-V.P.); (T.S.-B.)
| | - Dinu Iuliu Dumitrascu
- Department of Anatomy, “Iuliu Hatieganu“ University of Medicine and Pharmacy, 400006 Cluj-Napoca, Romania;
| | - Mihai Alexandru Munteanu
- Department of Medical Disciplines, Faculty of Medicine and Pharmacy, University of Oradea, 410087 Oradea, Romania;
| | - Teodora Surdea-Blaga
- 2nd Medical Department, “Iuliu Hatieganu” University of Medicine and Pharmacy, 400000 Cluj-Napoca, Romania; (S.L.P.); (A.I.); (S.G.); (A.-V.P.); (T.S.-B.)
| | - Florin Vasile Mihaileanu
- 2nd Surgical Department, “Iuliu Hatieganu” University of Medicine and Pharmacy, 400347 Cluj-Napoca, Romania;
| |
Collapse
|
|
5
|
Thurm T, Gluck N, Barak O, Deutsch L. Octa-nonagenarians can perform video capsule endoscopy safely and with a higher diagnostic yield than 65-79-year-old patients. J Am Geriatr Soc 2022; 70:2958-2966. [PMID: 35788980 PMCID: PMC9796662 DOI: 10.1111/jgs.17953] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/22/2022] [Revised: 05/31/2022] [Accepted: 06/08/2022] [Indexed: 01/07/2023]
Abstract
BACKGROUND Video capsule endoscopy (VCE) is an effective, noninvasive modality for small bowel (SB) investigation. Its usage in the older adults is rising. However, data in octa-nonagenarians regarding diagnostic yield and motility are lacking. Our aim was to evaluate and compare safety and efficacy of VCE between age subgroups of older adult patients. METHODS This was a retrospective study of prospectively documented data. All consecutive VCEs of patients ≥65 years (01/2010-12/2017) were included. Patients unable to swallow the capsule or videos with significant recording technical malfunction were excluded. The cohort was divided into the younger group aged 65-79 years old and octa-nonagenarians aged ≥80 years old. Indications for referral, diagnostic yield and transit times were compared between groups. RESULTS A total of 535 VCEs were performed in 499 older adult patients (51.2% males); 82.8% were 65-79 years old and 17.2% were ≥80 years old. The ≥80-year-old group had higher rates of clinically significant findings (52.7% vs. 40.0%, p = 0.025), active bleeding (12.5% vs. 6.5%, p = 0.053) and angioectasia (36.0% vs. 23.4%, p = 0.014). Crohn's disease was newly diagnosed in approximately 8% of the entire cohort and 12% of the ≥80 years old. Anemia was the most common indication in both groups, followed by overt bleeding in the ≥80-year-old group (25% vs. 9.9% in 65-79-year-old group, p < 0.001) and Crohn's disease in the 65-79 years old (17.2% vs. 5.4% in ≥80 years old, p = 0.004). Groups were comparable in transit time and cecal documentation rates. CONCLUSIONS In octa-nonagenarians, VCE is as safe as in younger older-adults with a higher diagnostic yield of significant and treatable conditions.
Collapse
Affiliation(s)
- Tamar Thurm
- Department of Gastroenterology and Liver DiseasesTel‐Aviv Sourasky Medical CenterTel‐AvivIsrael,Sackler School of MedicineTel‐Aviv UniversityTel‐AvivIsrael
| | - Nathan Gluck
- Department of Gastroenterology and Liver DiseasesTel‐Aviv Sourasky Medical CenterTel‐AvivIsrael,Sackler School of MedicineTel‐Aviv UniversityTel‐AvivIsrael
| | - Orly Barak
- Sackler School of MedicineTel‐Aviv UniversityTel‐AvivIsrael,Geriatric DivisionTel‐Aviv Sourasky Medical CenterTel‐AvivIsrael
| | - Liat Deutsch
- Department of Gastroenterology and Liver DiseasesTel‐Aviv Sourasky Medical CenterTel‐AvivIsrael,Sackler School of MedicineTel‐Aviv UniversityTel‐AvivIsrael
| |
Collapse
|
|
6
|
Minchenberg SB, Walradt T, Glissen Brown JR. Scoping out the future: The application of artificial intelligence to gastrointestinal endoscopy. World J Gastrointest Oncol 2022; 14:989-1001. [PMID: 35646286 PMCID: PMC9124983 DOI: 10.4251/wjgo.v14.i5.989] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/26/2021] [Revised: 06/21/2021] [Accepted: 04/21/2022] [Indexed: 02/06/2023] Open
Abstract
Artificial intelligence (AI) is a quickly expanding field in gastrointestinal endoscopy. Although there are a myriad of applications of AI ranging from identification of bleeding to predicting outcomes in patients with inflammatory bowel disease, a great deal of research has focused on the identification and classification of gastrointestinal malignancies. Several of the initial randomized, prospective trials utilizing AI in clinical medicine have centered on polyp detection during screening colonoscopy. In addition to work focused on colorectal cancer, AI systems have also been applied to gastric, esophageal, pancreatic, and liver cancers. Despite promising results in initial studies, the generalizability of most of these AI systems have not yet been evaluated. In this article we review recent developments in the field of AI applied to gastrointestinal oncology.
Collapse
Affiliation(s)
- Scott B Minchenberg
- Department of Internal Medicine, Beth Israel Deaconess Medical Center, Boston, MA 02130, United States
| | - Trent Walradt
- Department of Internal Medicine, Beth Israel Deaconess Medical Center, Boston, MA 02130, United States
| | - Jeremy R Glissen Brown
- Division of Gastroenterology, Beth Israel Deaconess Medical Center, Boston, MA 02130, United States
| |
Collapse
|
|
7
|
Kim HJ, Gong EJ, Bang CS, Lee JJ, Suk KT, Baik GH. Computer-Aided Diagnosis of Gastrointestinal Protruded Lesions Using Wireless Capsule Endoscopy: A Systematic Review and Diagnostic Test Accuracy Meta-Analysis. J Pers Med 2022; 12:jpm12040644. [PMID: 35455760 PMCID: PMC9029411 DOI: 10.3390/jpm12040644] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/06/2022] [Revised: 04/14/2022] [Accepted: 04/14/2022] [Indexed: 12/13/2022] Open
Abstract
Background: Wireless capsule endoscopy allows the identification of small intestinal protruded lesions, such as polyps, tumors, or venous structures. However, reading wireless capsule endoscopy images or movies is time-consuming, and minute lesions are easy to miss. Computer-aided diagnosis (CAD) has been applied to improve the efficacy of the reading process of wireless capsule endoscopy images or movies. However, there are no studies that systematically determine the performance of CAD models in diagnosing gastrointestinal protruded lesions. Objective: The aim of this study was to evaluate the diagnostic performance of CAD models for gastrointestinal protruded lesions using wireless capsule endoscopic images. Methods: Core databases were searched for studies based on CAD models for the diagnosis of gastrointestinal protruded lesions using wireless capsule endoscopy, and data on diagnostic performance were presented. A systematic review and diagnostic test accuracy meta-analysis were performed. Results: Twelve studies were included. The pooled area under the curve, sensitivity, specificity, and diagnostic odds ratio of CAD models for the diagnosis of protruded lesions were 0.95 (95% confidence interval, 0.93–0.97), 0.89 (0.84–0.92), 0.91 (0.86–0.94), and 74 (43–126), respectively. Subgroup analyses showed robust results. Meta-regression found no source of heterogeneity. Publication bias was not detected. Conclusion: CAD models showed high performance for the optical diagnosis of gastrointestinal protruded lesions based on wireless capsule endoscopy.
Collapse
Affiliation(s)
- Hye Jin Kim
- Department of Internal Medicine, Hallym University College of Medicine, Chuncheon 24253, Korea; (H.J.K.); (E.J.G.); (K.T.S.); (G.H.B.)
- Institute for Liver and Digestive Diseases, Hallym University, Chuncheon 24253, Korea
- Institute of New Frontier Research, Hallym University College of Medicine, Chuncheon 24253, Korea;
| | - Eun Jeong Gong
- Department of Internal Medicine, Hallym University College of Medicine, Chuncheon 24253, Korea; (H.J.K.); (E.J.G.); (K.T.S.); (G.H.B.)
- Institute for Liver and Digestive Diseases, Hallym University, Chuncheon 24253, Korea
| | - Chang Seok Bang
- Department of Internal Medicine, Hallym University College of Medicine, Chuncheon 24253, Korea; (H.J.K.); (E.J.G.); (K.T.S.); (G.H.B.)
- Institute for Liver and Digestive Diseases, Hallym University, Chuncheon 24253, Korea
- Institute of New Frontier Research, Hallym University College of Medicine, Chuncheon 24253, Korea;
- Division of Big Data and Artificial Intelligence, Chuncheon Sacred Heart Hospital, Chuncheon 24253, Korea
- Correspondence: ; Tel.: +82-33-240-5821; Fax: +82-33-241-8064
| | - Jae Jun Lee
- Institute of New Frontier Research, Hallym University College of Medicine, Chuncheon 24253, Korea;
- Division of Big Data and Artificial Intelligence, Chuncheon Sacred Heart Hospital, Chuncheon 24253, Korea
- Department of Anesthesiology and Pain Medicine, Hallym University College of Medicine, Chuncheon 24253, Korea
| | - Ki Tae Suk
- Department of Internal Medicine, Hallym University College of Medicine, Chuncheon 24253, Korea; (H.J.K.); (E.J.G.); (K.T.S.); (G.H.B.)
- Institute for Liver and Digestive Diseases, Hallym University, Chuncheon 24253, Korea
| | - Gwang Ho Baik
- Department of Internal Medicine, Hallym University College of Medicine, Chuncheon 24253, Korea; (H.J.K.); (E.J.G.); (K.T.S.); (G.H.B.)
- Institute for Liver and Digestive Diseases, Hallym University, Chuncheon 24253, Korea
| |
Collapse
|
|
8
|
Bang CS, Lee JJ, Baik GH. Computer-Aided Diagnosis of Gastrointestinal Ulcer and Hemorrhage Using Wireless Capsule Endoscopy: Systematic Review and Diagnostic Test Accuracy Meta-analysis. J Med Internet Res 2021; 23:e33267. [PMID: 34904949 PMCID: PMC8715364 DOI: 10.2196/33267] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/30/2021] [Revised: 10/10/2021] [Accepted: 10/13/2021] [Indexed: 12/13/2022] Open
Abstract
BACKGROUND Interpretation of capsule endoscopy images or movies is operator-dependent and time-consuming. As a result, computer-aided diagnosis (CAD) has been applied to enhance the efficacy and accuracy of the review process. Two previous meta-analyses reported the diagnostic performance of CAD models for gastrointestinal ulcers or hemorrhage in capsule endoscopy. However, insufficient systematic reviews have been conducted, which cannot determine the real diagnostic validity of CAD models. OBJECTIVE To evaluate the diagnostic test accuracy of CAD models for gastrointestinal ulcers or hemorrhage using wireless capsule endoscopic images. METHODS We conducted core databases searching for studies based on CAD models for the diagnosis of ulcers or hemorrhage using capsule endoscopy and presenting data on diagnostic performance. Systematic review and diagnostic test accuracy meta-analysis were performed. RESULTS Overall, 39 studies were included. The pooled area under the curve, sensitivity, specificity, and diagnostic odds ratio of CAD models for the diagnosis of ulcers (or erosions) were .97 (95% confidence interval, .95-.98), .93 (.89-.95), .92 (.89-.94), and 138 (79-243), respectively. The pooled area under the curve, sensitivity, specificity, and diagnostic odds ratio of CAD models for the diagnosis of hemorrhage (or angioectasia) were .99 (.98-.99), .96 (.94-0.97), .97 (.95-.99), and 888 (343-2303), respectively. Subgroup analyses showed robust results. Meta-regression showed that published year, number of training images, and target disease (ulcers vs erosions, hemorrhage vs angioectasia) was found to be the source of heterogeneity. No publication bias was detected. CONCLUSIONS CAD models showed high performance for the optical diagnosis of gastrointestinal ulcer and hemorrhage in wireless capsule endoscopy.
Collapse
Affiliation(s)
- Chang Seok Bang
- Department of Internal Medicine, Hallym University College of Medicine, Chuncheon, Republic of Korea.,Institute for Liver and Digestive Diseases, Hallym University, Chuncheon, Republic of Korea.,Institute of New Frontier Research, Hallym University College of Medicine, Chuncheon, Republic of Korea.,Division of Big Data and Artificial Intelligence, Chuncheon Sacred Heart Hospital, Chuncheon, Republic of Korea
| | - Jae Jun Lee
- Institute of New Frontier Research, Hallym University College of Medicine, Chuncheon, Republic of Korea.,Division of Big Data and Artificial Intelligence, Chuncheon Sacred Heart Hospital, Chuncheon, Republic of Korea.,Department of Anesthesiology and Pain Medicine, Hallym University College of Medicine, Chuncheon, Republic of Korea
| | - Gwang Ho Baik
- Department of Internal Medicine, Hallym University College of Medicine, Chuncheon, Republic of Korea.,Institute for Liver and Digestive Diseases, Hallym University, Chuncheon, Republic of Korea
| |
Collapse
|
|
9
|
Oka A, Ishimura N, Ishihara S. A New Dawn for the Use of Artificial Intelligence in Gastroenterology, Hepatology and Pancreatology. Diagnostics (Basel) 2021; 11:1719. [PMID: 34574060 PMCID: PMC8468082 DOI: 10.3390/diagnostics11091719] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/31/2021] [Revised: 09/17/2021] [Accepted: 09/17/2021] [Indexed: 12/15/2022] Open
Abstract
Artificial intelligence (AI) is rapidly becoming an essential tool in the medical field as well as in daily life. Recent developments in deep learning, a subfield of AI, have brought remarkable advances in image recognition, which facilitates improvement in the early detection of cancer by endoscopy, ultrasonography, and computed tomography. In addition, AI-assisted big data analysis represents a great step forward for precision medicine. This review provides an overview of AI technology, particularly for gastroenterology, hepatology, and pancreatology, to help clinicians utilize AI in the near future.
Collapse
Affiliation(s)
- Akihiko Oka
- Department of Internal Medicine II, Faculty of Medicine, Shimane University, Izumo 693-8501, Shimane, Japan; (N.I.); (S.I.)
| | | | | |
Collapse
|
|
10
|
Convolution neural network for the diagnosis of wireless capsule endoscopy: a systematic review and meta-analysis. Surg Endosc 2021; 36:16-31. [PMID: 34426876 PMCID: PMC8741689 DOI: 10.1007/s00464-021-08689-3] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/05/2021] [Accepted: 08/07/2021] [Indexed: 02/07/2023]
Abstract
Background Wireless capsule endoscopy (WCE) is considered to be a powerful instrument for the diagnosis of intestine diseases. Convolution neural network (CNN) is a type of artificial intelligence that has the potential to assist the detection of WCE images. We aimed to perform a systematic review of the current research progress to the CNN application in WCE. Methods A search in PubMed, SinoMed, and Web of Science was conducted to collect all original publications about CNN implementation in WCE. Assessment of the risk of bias was performed by Quality Assessment of Diagnostic Accuracy Studies-2 risk list. Pooled sensitivity and specificity were calculated by an exact binominal rendition of the bivariate mixed-effects regression model. I2 was used for the evaluation of heterogeneity. Results 16 articles with 23 independent studies were included. CNN application to WCE was divided into detection on erosion/ulcer, gastrointestinal bleeding (GI bleeding), and polyps/cancer. The pooled sensitivity of CNN for erosion/ulcer is 0.96 [95% CI 0.91, 0.98], for GI bleeding is 0.97 (95% CI 0.93–0.99), and for polyps/cancer is 0.97 (95% CI 0.82–0.99). The corresponding specificity of CNN for erosion/ulcer is 0.97 (95% CI 0.93–0.99), for GI bleeding is 1.00 (95% CI 0.99–1.00), and for polyps/cancer is 0.98 (95% CI 0.92–0.99). Conclusion Based on our meta-analysis, CNN-dependent diagnosis of erosion/ulcer, GI bleeding, and polyps/cancer approached a high-level performance because of its high sensitivity and specificity. Therefore, future perspective, CNN has the potential to become an important assistant for the diagnosis of WCE. Supplementary Information The online version contains supplementary material available at 10.1007/s00464-021-08689-3.
Collapse
|
|
11
|
Abstract
Video capsule endoscopy has been proven to be a beneficial tool to inspect the gastrointestinal lumen but its true impact may lie in utilization outside of traditional gastroenterology settings such as in the emergency room, the intensive care unit, and outpatient settings. Some advantages of video capsule endoscopy are that its administration does not require special training, patients do not require anesthesia, and videos can be shared with off-site consultants.
Collapse
|
|
12
|
Phillips F, Beg S. Video capsule endoscopy: pushing the boundaries with software technology. Transl Gastroenterol Hepatol 2021; 6:17. [PMID: 33409411 DOI: 10.21037/tgh.2020.02.01] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/29/2019] [Accepted: 12/11/2019] [Indexed: 12/14/2022] Open
Abstract
Video capsule endoscopy (VCE) has transformed imaging of the small bowel as it is a non-invasive and well tolerated modality with excellent diagnostic capabilities. The way we read VCE has not changed much since its introduction nearly two decades ago. Reading is still very time intensive and prone to reader error. This review outlines the evidence regarding software enhancements which aim to address these challenges. These include the suspected blood indicator (SBI), automated fast viewing modes including QuickView, lesion characterization tools such Fuji Intelligent Color Enhancement, and three-dimensional (3D) representation tools. We also outline the exciting new evidence of artificial intelligence (AI) and deep learning (DL), which promises to revolutionize capsule reading. DL algorithms have been developed for identifying organs of origin, intestinal motility events, active bleeding, coeliac disease, polyp detection, hookworms and angioectasias, all with impressively high sensitivity and accuracy. More recently, an algorithm has been created to detect multiple abnormalities with a sensitivity of 99.9% and reading time of only 5.9 minutes. These algorithms will need to be validated robustly. However, it will not be long before we see this in clinical practice, aiding the clinician in rapid and accurate diagnosis.
Collapse
Affiliation(s)
- Frank Phillips
- Department of Gastroenterology, NIHR Nottingham Digestive Diseases Biomedical Research Centre, Queens Medical Centre Campus, Nottingham University Hospitals NHS Trust, Nottingham, UK
| | - Sabina Beg
- Department of Gastroenterology, NIHR Nottingham Digestive Diseases Biomedical Research Centre, Queens Medical Centre Campus, Nottingham University Hospitals NHS Trust, Nottingham, UK
| |
Collapse
|
|
13
|
Trasolini R, Byrne MF. Artificial intelligence and deep learning for small bowel capsule endoscopy. Dig Endosc 2021; 33:290-297. [PMID: 33211357 DOI: 10.1111/den.13896] [Citation(s) in RCA: 15] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/30/2020] [Accepted: 11/16/2020] [Indexed: 12/20/2022]
Abstract
Capsule endoscopy is ideally suited to artificial intelligence-based interpretation given its reliance on pattern recognition in still images. Time saving viewing modes and lesion detection features currently available rely on machine learning algorithms, a form of artificial intelligence. Current software necessitates close human supervision given poor sensitivity relative to an expert reader. However, with the advent of deep learning, artificial intelligence is becoming increasingly reliable and will be increasingly relied upon. We review the major advances in artificial intelligence for capsule endoscopy in recent publications and briefly review artificial intelligence development for historical understanding. Importantly, recent advancements in artificial intelligence have not yet been incorporated into practice and it is immature to judge the potential of this technology based on current platforms. Remaining regulatory and standardization hurdles are being overcome and artificial intelligence-based clinical applications are likely to proliferate rapidly.
Collapse
Affiliation(s)
- Roberto Trasolini
- Department of Medicine, The University of British Columbia, Vancouver, Canada
| | - Michael F Byrne
- Department of Medicine, The University of British Columbia, Vancouver, Canada
| |
Collapse
|
|
14
|
Sinonquel P, Bisschops R. Striving for quality improvement: can artificial intelligence help? Best Pract Res Clin Gastroenterol 2020; 52-53:101722. [PMID: 34172249 DOI: 10.1016/j.bpg.2020.101722] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/10/2020] [Accepted: 12/22/2020] [Indexed: 02/06/2023]
Abstract
Artificial intelligence (AI) is of keen interest for global health development as potential support for current human shortcomings. Gastrointestinal (GI) endoscopy is an excellent substrate for AI, since it holds the genuine potential to improve quality in GI endoscopy and overall patient care by improving detection and diagnosis guiding the endoscopists in performing endoscopy to the highest quality standards. The possibility of large data acquisitioning to refine algorithms makes implementation of AI into daily practice a potential reality. With the start of a new era adopting deep learning, large amounts of data can easily be processed, resulting in better diagnostic performances. In the upper gastrointestinal tract, research currently focusses on the detection and characterization of neoplasia, including Barrett's, squamous cell and gastric carcinoma, with an increasing amount of AI studies demonstrating the potential and benefit of AI-augmented endoscopy. Deep learning applied to small bowel video capsule endoscopy also appears to enhance pathology detection and reduce capsule reading time. In the colon, multiple prospective trials including five randomized trials, showed a consistent improvement in polyp and adenoma detection rates, one of the main quality indicators in endoscopy. There are however potential additional roles for AI to assist in quality improvement of endoscopic procedures, training and therapeutic decision making. Further large-scale, multicenter validation trials are required before AI-augmented diagnostic gastrointestinal endoscopy can be integrated into our routine clinical practice.
Collapse
Affiliation(s)
- P Sinonquel
- Department of Gastroenterology and Hepatology, University Hospitals Leuven, Herestraat 49, 3000, Leuven, Belgium; Department of Translational Research in Gastrointestinal Diseases (TARGID), Catholic University Leuven, Herestraat 49, 3000, Leuven, Belgium.
| | - R Bisschops
- Department of Gastroenterology and Hepatology, University Hospitals Leuven, Herestraat 49, 3000, Leuven, Belgium; Department of Translational Research in Gastrointestinal Diseases (TARGID), Catholic University Leuven, Herestraat 49, 3000, Leuven, Belgium.
| |
Collapse
|
|
15
|
Oh DJ, Kim KS, Lim YJ. A New Active Locomotion Capsule Endoscopy under Magnetic Control and Automated Reading Program. Clin Endosc 2020; 53:395-401. [PMID: 32746536 PMCID: PMC7403023 DOI: 10.5946/ce.2020.127] [Citation(s) in RCA: 11] [Impact Index Per Article: 2.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/08/2020] [Accepted: 05/28/2020] [Indexed: 02/06/2023] Open
Abstract
Capsule endoscopy (CE) is the first-line diagnostic modality for detecting small bowel lesions. CE is non-invasive and does not require sedation, but its movements cannot be controlled, it requires a long time for interpretation, and it has lower image quality compared to wired endoscopy. With the rapid advancement of technology, several methods to solve these problems have been developed. This article describes the ongoing developments regarding external CE locomotion using magnetic force, artificial intelligence-based interpretation, and image-enhancing technologies with the CE system.
Collapse
Affiliation(s)
- Dong Jun Oh
- Department of Internal Medicine, Dongguk University Ilsan Hospital, Dongguk University College of Medicine, Goyang, Korea
| | - Kwang Seop Kim
- Chief Research Engineer, Research and Development team, IntroMedic Co., Ltd., Seoul, Korea
| | - Yun Jeong Lim
- Department of Internal Medicine, Dongguk University Ilsan Hospital, Dongguk University College of Medicine, Goyang, Korea
| |
Collapse
|
|
16
|
Yang YJ. The Future of Capsule Endoscopy: The Role of Artificial Intelligence and Other Technical Advancements. Clin Endosc 2020; 53:387-394. [PMID: 32668529 PMCID: PMC7403015 DOI: 10.5946/ce.2020.133] [Citation(s) in RCA: 19] [Impact Index Per Article: 4.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/15/2020] [Accepted: 05/24/2020] [Indexed: 12/13/2022] Open
Abstract
Capsule endoscopy has revolutionized the management of small-bowel diseases owing to its convenience and noninvasiveness. Capsule endoscopy is a common method for the evaluation of obscure gastrointestinal bleeding, Crohn’s disease, small-bowel tumors, and polyposis syndrome. However, the laborious reading process, oversight of small-bowel lesions, and lack of locomotion are major obstacles to expanding its application. Along with recent advances in artificial intelligence, several studies have reported the promising performance of convolutional neural network systems for the diagnosis of various small-bowel lesions including erosion/ulcers, angioectasias, polyps, and bleeding lesions, which have reduced the time needed for capsule endoscopy interpretation. Furthermore, colon capsule endoscopy and capsule endoscopy locomotion driven by magnetic force have been investigated for clinical application, and various capsule endoscopy prototypes for active locomotion, biopsy, or therapeutic approaches have been introduced. In this review, we will discuss the recent advancements in artificial intelligence in the field of capsule endoscopy, as well as studies on other technological improvements in capsule endoscopy.
Collapse
Affiliation(s)
- Young Joo Yang
- Department of Internal Medicine, Hallym University College of Medicine, Chuncheon, Korea.,Institute for Liver and Digestive Diseases, Hallym University, Chuncheon, Korea
| |
Collapse
|
|
17
|
Saito H, Aoki T, Aoyama K, Kato Y, Tsuboi A, Yamada A, Fujishiro M, Oka S, Ishihara S, Matsuda T, Nakahori M, Tanaka S, Koike K, Tada T. Automatic detection and classification of protruding lesions in wireless capsule endoscopy images based on a deep convolutional neural network. Gastrointest Endosc 2020; 92:144-151.e1. [PMID: 32084410 DOI: 10.1016/j.gie.2020.01.054] [Citation(s) in RCA: 94] [Impact Index Per Article: 23.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 10/31/2019] [Accepted: 01/31/2020] [Indexed: 02/08/2023]
Abstract
BACKGROUND AND AIMS Protruding lesions of the small bowel vary in wireless capsule endoscopy (WCE) images, and their automatic detection may be difficult. We aimed to develop and test a deep learning-based system to automatically detect protruding lesions of various types in WCE images. METHODS We trained a deep convolutional neural network (CNN), using 30,584 WCE images of protruding lesions from 292 patients. We evaluated CNN performance by calculating the area under the receiver operating characteristic curve (AUC), sensitivity, and specificity, using an independent set of 17,507 test images from 93 patients, including 7507 images of protruding lesions from 73 patients. RESULTS The developed CNN analyzed 17,507 images in 530.462 seconds. The AUC for detection of protruding lesions was 0.911 (95% confidence interval [Cl], 0.9069-0.9155). The sensitivity and specificity of the CNN were 90.7% (95% CI, 90.0%-91.4%) and 79.8% (95% CI, 79.0%-80.6%), respectively, at the optimal cut-off value of 0.317 for probability score. In a subgroup analysis of the category of protruding lesions, the sensitivities were 86.5%, 92.0%, 95.8%, 77.0%, and 94.4% for the detection of polyps, nodules, epithelial tumors, submucosal tumors, and venous structures, respectively. In individual patient analyses (n = 73), the detection rate of protruding lesions was 98.6%. CONCLUSION We developed and tested a new computer-aided system based on a CNN to automatically detect various protruding lesions in WCE images. Patient-level analyses with larger cohorts and efforts to achieve better diagnostic performance are necessary in further studies.
Collapse
Affiliation(s)
- Hiroaki Saito
- Department of Gastroenterology, Sendai Kousei Hospital, Miyagi, Japan.
| | - Tomonori Aoki
- Department of Gastroenterology, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan
| | | | | | - Akiyoshi Tsuboi
- Department of Endoscopy, Hiroshima University Hospital, Hiroshima, Japan
| | - Atsuo Yamada
- Department of Gastroenterology, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan
| | - Mitsuhiro Fujishiro
- Department of Gastroenterology and Hepatology, Nagoya University Graduate School of Medicine, Aichi, Japan
| | - Shiro Oka
- Department of Endoscopy, Hiroshima University Hospital, Hiroshima, Japan
| | - Soichiro Ishihara
- Department of Surgical Oncology, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan; Tada Tomohiro Institute of Gastroenterology and Proctology, Saitama, Japan
| | - Tomoki Matsuda
- Department of Gastroenterology, Sendai Kousei Hospital, Miyagi, Japan
| | - Masato Nakahori
- Department of Gastroenterology, Sendai Kousei Hospital, Miyagi, Japan
| | - Shinji Tanaka
- Department of Endoscopy, Hiroshima University Hospital, Hiroshima, Japan
| | - Kazuhiko Koike
- Department of Gastroenterology, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan
| | - Tomohiro Tada
- AI Medical Service Inc., Tokyo, Japan; Department of Surgical Oncology, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan; Tada Tomohiro Institute of Gastroenterology and Proctology, Saitama, Japan
| |
Collapse
|
|
18
|
Gan T, Liu S, Yang J, Zeng B, Yang L. A pilot trial of Convolution Neural Network for automatic retention-monitoring of capsule endoscopes in the stomach and duodenal bulb. Sci Rep 2020; 10:4103. [PMID: 32139758 PMCID: PMC7057987 DOI: 10.1038/s41598-020-60969-5] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/06/2019] [Accepted: 02/12/2020] [Indexed: 02/05/2023] Open
Abstract
The retention of a capsule endoscope (CE) in the stomach and the duodenal bulb during the examination is a troublesome problem, which can make the medical staff spend several hours observing whether the CE enters the descending segment of the duodenum (DSD). This paper investigated and evaluated the Convolution Neural Network (CNN) for automatic retention-monitoring of the CE in the stomach or the duodenal bulb. A trained CNN system based on 180,000 CE images of the DSD, stomach, and duodenal bulb was used to assess its recognition of the accuracy by calculating the area under the receiver operating characteristic curve (ROC-AUC), sensitivity and specificity. The AUC for distinguishing the DSD was 0.984. The sensitivity, specificity, positive predictive value, and negative predictive value of the CNN were 97.8%, 96.0%, 96.1% and 97.8%, respectively, at a cut-off value of 0.42 for the probability score. The deviated rate of the time into the DSD marked by the CNN at less than ±8 min was 95.7% (P < 0.01). These results indicate that the CNN for automatic retention-monitoring of the CE in the stomach or the duodenal bulb can be used as an efficient auxiliary measure in the clinical practice.
Collapse
Affiliation(s)
- Tao Gan
- Department of Gastroenterology and Hepatology, West China Hospital, Sichuan University, Chengdu, 610041, Sichuan, China
| | - Shuaicheng Liu
- School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, 611731, Sichuan, China
| | - Jinlin Yang
- Department of Gastroenterology and Hepatology, West China Hospital, Sichuan University, Chengdu, 610041, Sichuan, China
| | - Bing Zeng
- School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, 611731, Sichuan, China
| | - Li Yang
- Department of Gastroenterology and Hepatology, West China Hospital, Sichuan University, Chengdu, 610041, Sichuan, China.
| |
Collapse
|
|
19
|
Leenhardt R, Li C, Le Mouel JP, Rahmi G, Saurin JC, Cholet F, Boureille A, Amiot X, Delvaux M, Duburque C, Leandri C, Gérard R, Lecleire S, Mesli F, Nion-Larmurier I, Romain O, Sacher-Huvelin S, Simon-Shane C, Vanbiervliet G, Marteau P, Histace A, Dray X. CAD-CAP: a 25,000-image database serving the development of artificial intelligence for capsule endoscopy. Endosc Int Open 2020; 8:E415-E420. [PMID: 32118115 PMCID: PMC7035135 DOI: 10.1055/a-1035-9088] [Citation(s) in RCA: 27] [Impact Index Per Article: 6.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/05/2019] [Accepted: 09/16/2019] [Indexed: 02/06/2023] Open
Abstract
Background and study aims Capsule endoscopy (CE) is the preferred method for small bowel (SB) exploration. With a mean number of 50,000 SB frames per video, SBCE reading is time-consuming and tedious (30 to 60 minutes per video). We describe a large, multicenter database named CAD-CAP (Computer-Assisted Diagnosis for CAPsule Endoscopy, CAD-CAP). This database aims to serve the development of CAD tools for CE reading. Materials and methods Twelve French endoscopy centers were involved. All available third-generation SB-CE videos (Pillcam, Medtronic) were retrospectively selected from these centers and deidentified. Any pathological frame was extracted and included in the database. Manual segmentation of findings within these frames was performed by two pre-med students trained and supervised by an expert reader. All frames were then classified by type and clinical relevance by a panel of three expert readers. An automated extraction process was also developed to create a dataset of normal, proofread, control images from normal, complete, SB-CE videos. Results Four-thousand-one-hundred-and-seventy-four SB-CE were included. Of them, 1,480 videos (35 %) containing at least one pathological finding were selected. Findings from 5,184 frames (with their short video sequences) were extracted and delimited: 718 frames with fresh blood, 3,097 frames with vascular lesions, and 1,369 frames with inflammatory and ulcerative lesions. Twenty-thousand normal frames were extracted from 206 SB-CE normal videos. CAD-CAP has already been used for development of automated tools for angiectasia detection and also for two international challenges on medical computerized analysis.
Collapse
Affiliation(s)
| | - Cynthia Li
- Drexel University, College of Arts & Sciences, Philadelphia, Pennsylvania, United States
| | - Jean-Philippe Le Mouel
- Gastroenterology, Amiens University Hospital, Université de Picardie Jules Verne, Amiens, France
| | - Gabriel Rahmi
- Georges Pompidou European Hospital, APHP, Department of Gastroenterology and Endoscopy, Paris, France
| | - Jean Christophe Saurin
- Department of Endoscopy and Gastroenterology, Pavillon L, Hôpital Edouard Herriot, Lyon, France
| | - Franck Cholet
- Digestive Endoscopy Unit, University Hospital, Brest, France
| | - Arnaud Boureille
- Department of Hepato-Gastroenterology, Institut des Maladies de l'Appareil Digestif, Nantes, France
| | - Xavier Amiot
- Tenon Hospital, Gastroenterology Department, Paris, France
| | - Michel Delvaux
- CHU Strasbourg, Gastroenterology Department, Strasbourg, France
| | | | - Chloé Leandri
- Cochin Hospital Gastroenterology Department, Paris, France
| | - Romain Gérard
- CHRU Lille, Gastroenterology Department, Lille, France
| | | | - Farida Mesli
- CHU Henri Mondor, Gastroenterology Department, Creteil, France
| | | | - Olivier Romain
- ETIS, Université de Cergy-Pontoise, ENSEA, CNRS, Cergy-Pontoise Cedex, France
| | - Sylvie Sacher-Huvelin
- Department of Hepato-Gastroenterology, Institut des Maladies de l'Appareil Digestif, Nantes, France
| | - Camille Simon-Shane
- ETIS, Université de Cergy-Pontoise, ENSEA, CNRS, Cergy-Pontoise Cedex, France
| | | | | | - Aymeric Histace
- ETIS, Université de Cergy-Pontoise, ENSEA, CNRS, Cergy-Pontoise Cedex, France
| | - Xavier Dray
- Sorbonne University, Endoscopy Unit,ETIS, Université de Cergy-Pontoise, ENSEA, CNRS, Cergy-Pontoise Cedex, France,Corresponding author Pr Xavier Dray Hopital Saint-Antoine – Endoscopy Unit184 Rue du Faubourg Saint-AntoineParis 75012France
| |
Collapse
|
|
20
|
Tsuboi A, Oka S, Aoyama K, Saito H, Aoki T, Yamada A, Matsuda T, Fujishiro M, Ishihara S, Nakahori M, Koike K, Tanaka S, Tada T. Artificial intelligence using a convolutional neural network for automatic detection of small-bowel angioectasia in capsule endoscopy images. Dig Endosc 2020; 32:382-390. [PMID: 31392767 DOI: 10.1111/den.13507] [Citation(s) in RCA: 91] [Impact Index Per Article: 22.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 06/14/2019] [Accepted: 08/04/2019] [Indexed: 12/12/2022]
Abstract
BACKGROUND AND AIM Although small-bowel angioectasia is reported as the most common cause of bleeding in patients and frequently diagnosed by capsule endoscopy (CE) in patients with obscure gastrointestinal bleeding, a computer-aided detection method has not been established. We developed an artificial intelligence system with deep learning that can automatically detect small-bowel angioectasia in CE images. METHODS We trained a deep convolutional neural network (CNN) system based on Single Shot Multibox Detector using 2237 CE images of angioectasia. We assessed its diagnostic accuracy by calculating the area under the receiver operating characteristic curve (ROC-AUC), sensitivity, specificity, positive predictive value, and negative predictive value using an independent test set of 10 488 small-bowel images, including 488 images of small-bowel angioectasia. RESULTS The AUC to detect angioectasia was 0.998. Sensitivity, specificity, positive predictive value, and negative predictive value of CNN were 98.8%, 98.4%, 75.4%, and 99.9%, respectively, at a cut-off value of 0.36 for the probability score. CONCLUSIONS We developed and validated a new system based on CNN to automatically detect angioectasia in CE images. This may be well applicable to daily clinical practice to reduce the burden of physicians as well as to reduce oversight.
Collapse
Affiliation(s)
- Akiyoshi Tsuboi
- Department of Endoscopy, Hiroshima University Hospital, Hiroshima, Japan
| | - Shiro Oka
- Department of Endoscopy, Hiroshima University Hospital, Hiroshima, Japan
| | | | - Hiroaki Saito
- Department of Gastroenterology, Sendai Kousei Hospital, Miyagi, Japan
| | | | | | - Tomoki Matsuda
- Department of Gastroenterology, Sendai Kousei Hospital, Miyagi, Japan
| | - Mitsuhiro Fujishiro
- Department of Gastroenterology & Hepatology, Nagoya University Graduate School of Medicine, Aichi, Japan
| | - Soichiro Ishihara
- Department of Surgical Oncology, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan.,Tada Tomohiro Institute of Gastroenterology and Proctology, Saitama, Japan
| | - Masato Nakahori
- Department of Gastroenterology, Sendai Kousei Hospital, Miyagi, Japan
| | | | - Shinji Tanaka
- Department of Endoscopy, Hiroshima University Hospital, Hiroshima, Japan
| | - Tomohiro Tada
- AI Medical Service Inc., Tokyo, Japan.,Department of Surgical Oncology, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan.,Tada Tomohiro Institute of Gastroenterology and Proctology, Saitama, Japan
| |
Collapse
|
|
21
|
Gulati S, Emmanuel A, Patel M, Williams S, Haji A, Hayee B, Neumann H. Artificial intelligence in luminal endoscopy. Ther Adv Gastrointest Endosc 2020; 13:2631774520935220. [PMID: 32637935 PMCID: PMC7315657 DOI: 10.1177/2631774520935220] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/16/2020] [Accepted: 05/22/2020] [Indexed: 12/15/2022] Open
Abstract
Artificial intelligence is a strong focus of interest for global health development. Diagnostic endoscopy is an attractive substrate for artificial intelligence with a real potential to improve patient care through standardisation of endoscopic diagnosis and to serve as an adjunct to enhanced imaging diagnosis. The possibility to amass large data to refine algorithms makes adoption of artificial intelligence into global practice a potential reality. Initial studies in luminal endoscopy involve machine learning and are retrospective. Improvement in diagnostic performance is appreciable through the adoption of deep learning. Research foci in the upper gastrointestinal tract include the diagnosis of neoplasia, including Barrett's, squamous cell and gastric where prospective and real-time artificial intelligence studies have been completed demonstrating a benefit of artificial intelligence-augmented endoscopy. Deep learning applied to small bowel capsule endoscopy also appears to enhance pathology detection and reduce capsule reading time. Prospective evaluation including the first randomised trial has been performed in the colon, demonstrating improved polyp and adenoma detection rates; however, these appear to be relevant to small polyps. There are potential additional roles of artificial intelligence relevant to improving the quality of endoscopic examinations, training and triaging of referrals. Further large-scale, multicentre and cross-platform validation studies are required for the robust incorporation of artificial intelligence-augmented diagnostic luminal endoscopy into our routine clinical practice.
Collapse
Affiliation(s)
- Shraddha Gulati
- King’s Institute of Therapeutic Endoscopy, King’s College Hospital NHS Foundation Trust, London, UK
| | - Andrew Emmanuel
- King’s Institute of Therapeutic Endoscopy, King’s College Hospital NHS Foundation Trust, London, UK
| | - Mehul Patel
- King’s Institute of Therapeutic Endoscopy, King’s College Hospital NHS Foundation Trust, London, UK
| | - Sophie Williams
- King’s Institute of Therapeutic Endoscopy, King’s College Hospital NHS Foundation Trust, London, UK
| | - Amyn Haji
- King’s Institute of Therapeutic Endoscopy, King’s College Hospital NHS Foundation Trust, London, UK
| | - Bu’Hussain Hayee
- King’s Institute of Therapeutic Endoscopy, King’s College Hospital NHS Foundation Trust, London, UK
| | - Helmut Neumann
- Department of Interdisciplinary Endoscopy, University Hospital Mainz, 55131 Mainz, Germany
| |
Collapse
|
|
22
|
Ding Z, Shi H, Zhang H, Meng L, Fan M, Han C, Zhang K, Ming F, Xie X, Liu H, Liu J, Lin R, Hou X. Gastroenterologist-Level Identification of Small-Bowel Diseases and Normal Variants by Capsule Endoscopy Using a Deep-Learning Model. Gastroenterology 2019; 157:1044-1054.e5. [PMID: 31251929 DOI: 10.1053/j.gastro.2019.06.025] [Citation(s) in RCA: 176] [Impact Index Per Article: 35.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/07/2018] [Revised: 06/02/2019] [Accepted: 06/17/2019] [Indexed: 02/06/2023]
Abstract
BACKGROUND & AIMS Capsule endoscopy has revolutionized investigation of the small bowel. However, this technique produces a video that is 8-10 hours long, so analysis is time consuming for gastroenterologists. Deep convolutional neural networks (CNNs) can recognize specific images among a large variety. We aimed to develop a CNN-based algorithm to assist in the evaluation of small bowel capsule endoscopy (SB-CE) images. METHODS We collected 113,426,569 images from 6970 patients who had SB-CE at 77 medical centers from July 2016 through July 2018. A CNN-based auxiliary reading model was trained to differentiate abnormal from normal images using 158,235 SB-CE images from 1970 patients. Images were categorized as normal, inflammation, ulcer, polyps, lymphangiectasia, bleeding, vascular disease, protruding lesion, lymphatic follicular hyperplasia, diverticulum, parasite, and other. The model was further validated in 5000 patients (no patient was overlap with the 1970 patients in the training set); the same patients were evaluated by conventional analysis and CNN-based auxiliary analysis by 20 gastroenterologists. If there was agreement in image categorization between the conventional analysis and CNN model, no further evaluation was performed. If there was disagreement between the conventional analysis and CNN model, the gastroenterologists re-evaluated the image to confirm or reject the CNN categorization. RESULTS In the SB-CE images from the validation set, 4206 abnormalities in 3280 patients were identified after final consensus evaluation. The CNN-based auxiliary model identified abnormalities with 99.88% sensitivity in the per-patient analysis (95% CI, 99.67-99.96) and 99.90% sensitivity in the per-lesion analysis (95% CI, 99.74-99.97). Conventional reading by the gastroenterologists identified abnormalities with 74.57% sensitivity (95% CI, 73.05-76.03) in the per-patient analysis and 76.89% in the per-lesion analysis (95% CI, 75.58-78.15). The mean reading time per patient was 96.6 ± 22.53 minutes by conventional reading and 5.9 ± 2.23 minutes by CNN-based auxiliary reading (P < .001). CONCLUSIONS We validated the ability of a CNN-based algorithm to identify abnormalities in SB-CE images. The CNN-based auxiliary model identified abnormalities with higher levels of sensitivity and significantly shorter reading times than conventional analysis by gastroenterologists. This algorithm provides an important tool to help gastroenterologists analyze SB-CE images more efficiently and more accurately.
Collapse
Affiliation(s)
- Zhen Ding
- Department of Gastroenterology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430022, China
| | - Huiying Shi
- Department of Gastroenterology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430022, China
| | - Hao Zhang
- Ankon Medical Technologies Co, Ltd, Shanghai, China
| | - Lingjun Meng
- Department of Gastroenterology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430022, China
| | - Mengke Fan
- Department of Gastroenterology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430022, China
| | - Chaoqun Han
- Department of Gastroenterology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430022, China
| | - Kun Zhang
- Department of Gastroenterology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430022, China
| | - Fanhua Ming
- Ankon Medical Technologies Co, Ltd, Shanghai, China
| | - Xiaoping Xie
- Department of Gastroenterology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430022, China
| | - Hao Liu
- Ankon Medical Technologies Co, Ltd, Shanghai, China
| | - Jun Liu
- Department of Gastroenterology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430022, China
| | - Rong Lin
- Department of Gastroenterology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430022, China.
| | - Xiaohua Hou
- Department of Gastroenterology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430022, China
| |
Collapse
|
|
23
|
McGoran JJ, McAlindon ME, Iyer PG, Seibel EJ, Haidry R, Lovat LB, Sami SS. Miniature gastrointestinal endoscopy: Now and the future. World J Gastroenterol 2019; 25:4051-4060. [PMID: 31435163 PMCID: PMC6700702 DOI: 10.3748/wjg.v25.i30.4051] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.2] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 03/20/2019] [Revised: 06/22/2019] [Accepted: 07/03/2019] [Indexed: 02/06/2023] Open
Abstract
Since its original application, gastrointestinal (GI) endoscopy has undergone many innovative transformations aimed at expanding the scope, safety, accuracy, acceptability and cost-effectiveness of this area of clinical practice. One method of achieving this has been to reduce the caliber of endoscopic devices. We propose the collective term “Miniature GI Endoscopy”. In this Opinion Review, the innovations in this field are explored and discussed. The progress and clinical use of the three main areas of miniature GI endoscopy (ultrathin endoscopy, wireless endoscopy and scanning fiber endoscopy) are described. The opportunities presented by these technologies are set out in a clinical context, as are their current limitations. Many of the positive aspects of miniature endoscopy are clear, in that smaller devices provide access to potentially all of the alimentary canal, while conferring high patient acceptability. This must be balanced with the costs of new technologies and recognition of device specific challenges. Perspectives on future application are also considered and the efforts being made to bring new innovations to a clinical platform are outlined. Current devices demonstrate that miniature GI endoscopy has a valuable place in investigation of symptoms, therapeutic intervention and screening. Newer technologies give promise that the potential for enhancing the investigation and management of GI complaints is significant.
Collapse
Affiliation(s)
- John J McGoran
- Digestive Diseases Centre, Leicester Royal Infirmary, Leicester LE1 5WW, United Kingdom
| | - Mark E McAlindon
- Department of Gastroenterology, Royal Hallamshire Hospital, Sheffield S10 2JF, United Kingdom
| | - Prasad G Iyer
- Division of Gastroenterology and Hepatology, Mayo Clinic Rochester, MN 55905, United States
| | - Eric J Seibel
- Department of Mechanical Engineering, University of Washington, 4000 Mason St, Seattle, WA 98195, United States
| | - Rehan Haidry
- Division of Surgery and Interventional Science, University College London, London WC1E 6BT, United Kingdom
| | - Laurence B Lovat
- Division of Surgery and Interventional Science, University College London, London WC1E 6BT, United Kingdom
| | - Sarmed S Sami
- Division of Surgery and Interventional Science, University College London, London WC1E 6BT, United Kingdom
| |
Collapse
|
|
24
|
Leenhardt R, Vasseur P, Li C, Saurin JC, Rahmi G, Cholet F, Becq A, Marteau P, Histace A, Dray X, Mesli F, Leandri C, Nion-Larmurier I, Lecleire S, Gerard R, Duburque C, Vanbiervliet G, Amiot X, Philippe Le Mouel J, Delvaux M, Jacob P, Simon-Shane C, Romain O. A neural network algorithm for detection of GI angiectasia during small-bowel capsule endoscopy. Gastrointest Endosc 2019; 89:189-194. [PMID: 30017868 DOI: 10.1016/j.gie.2018.06.036] [Citation(s) in RCA: 130] [Impact Index Per Article: 26.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/07/2018] [Accepted: 06/29/2018] [Indexed: 02/07/2023]
Abstract
BACKGROUND AND AIMS GI angiectasia (GIA) is the most common small-bowel (SB) vascular lesion, with an inherent risk of bleeding. SB capsule endoscopy (SB-CE) is the currently accepted diagnostic procedure. The aim of this study was to develop a computer-assisted diagnosis tool for the detection of GIA. METHODS Deidentified SB-CE still frames featuring annotated typical GIA and normal control still frames were selected from a database. A semantic segmentation images approach associated with a convolutional neural network (CNN) was used for deep-feature extractions and classification. Two datasets of still frames were created and used for machine learning and for algorithm testing. RESULTS The GIA detection algorithm yielded a sensitivity of 100%, a specificity of 96%, a positive predictive value of 96%, and a negative predictive value of 100%. Reproducibility was optimal. The reading process for an entire SB-CE video would take 39 minutes. CONCLUSIONS The developed CNN-based algorithm had high diagnostic performances, allowing detection of GIA in SB-CE still frames. This study paves the way for future automated CNN-based SB-CE reading softwares.
Collapse
Affiliation(s)
- Romain Leenhardt
- Sorbonne University, Department of Hepato-Gastroenterology, APHP, Saint Antoine Hospital, Paris, France
| | - Pauline Vasseur
- ETIS, Université de Cergy-Pontoise, ENSEA, CNRS, Cergy-Pontoise Cedex, France
| | - Cynthia Li
- Sorbonne University, Department of Hepato-Gastroenterology, APHP, Saint Antoine Hospital, Paris, France; Drexel University, College of Arts & Sciences, Philadelphia, Pennsylvania, USA
| | - Jean Christophe Saurin
- Department of Endoscopy and Gastroenterology, Pavillon L, Hôpital Edouard Herriot, Lyon, France
| | - Gabriel Rahmi
- Georges Pompidou European Hospital, APHP, Department of Gastroenterology and Endoscopy, Paris, France
| | - Franck Cholet
- Digestive Endoscopy Unit, University Hospital, Brest, France
| | - Aymeric Becq
- Sorbonne University, Department of Hepato-Gastroenterology, APHP, Saint Antoine Hospital, Paris, France
| | - Philippe Marteau
- Sorbonne University, Department of Hepato-Gastroenterology, APHP, Saint Antoine Hospital, Paris, France
| | - Aymeric Histace
- ETIS, Université de Cergy-Pontoise, ENSEA, CNRS, Cergy-Pontoise Cedex, France
| | - Xavier Dray
- Sorbonne University, Department of Hepato-Gastroenterology, APHP, Saint Antoine Hospital, Paris, France; ETIS, Université de Cergy-Pontoise, ENSEA, CNRS, Cergy-Pontoise Cedex, France
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
Collapse
|
|
25
|
Beg S, Parra-Blanco A, Ragunath K. Optimising the performance and interpretation of small bowel capsule endoscopy. Frontline Gastroenterol 2018; 9:300-308. [PMID: 30245793 PMCID: PMC6145435 DOI: 10.1136/flgastro-2017-100878] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/18/2017] [Revised: 09/16/2017] [Accepted: 10/18/2017] [Indexed: 02/04/2023] Open
Abstract
Small bowel capsule endoscopy has become a commonly used tool in the investigation of gastrointestinal symptoms and is now widely available in clinical practice. In contrast to conventional endoscopy, there is a lack of clear consensus on when competency is achieved or the way in which capsule endoscopy should be performed in order to maintain quality and clinical accuracy. Here we explore the evidence on the key factors that influence the quality of small bowel capsule endoscopy services.
Collapse
Affiliation(s)
- Sabina Beg
- Department of Gastroenterology, NIHR Nottingham Digestive Diseases Biomedical Research Centre, Queens Medical Centre campus, Nottingham University Hospitals NHS Trust, Nottingham, UK
| | - Adolfo Parra-Blanco
- Department of Gastroenterology, NIHR Nottingham Digestive Diseases Biomedical Research Centre, Queens Medical Centre campus, Nottingham University Hospitals NHS Trust, Nottingham, UK
| | - Krish Ragunath
- Department of Gastroenterology, NIHR Nottingham Digestive Diseases Biomedical Research Centre, Queens Medical Centre campus, Nottingham University Hospitals NHS Trust, Nottingham, UK
| |
Collapse
|
|
26
|
Raju SA, White WL, Lau MS, Mooney PD, Rees MA, Burden M, Ciacci C, Sanders DS. A comparison study between Magniview and high definition white light endoscopy in detecting villous atrophy and coeliac disease: A single centre pilot study. Dig Liver Dis 2018; 50:920-924. [PMID: 29807874 DOI: 10.1016/j.dld.2018.03.037] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/30/2017] [Revised: 03/28/2018] [Accepted: 03/30/2018] [Indexed: 12/11/2022]
Abstract
BACKGROUND AND AIMS Coeliac disease may be missed at gastroscopy. We aimed to assess the sensitivity of Pentax optical zoom technology endoscopes in detecting duodenal villous atrophy and the ease of image interpretation by non-coeliac specialists. METHOD All patients attending for a gastroscopy were assessed for endoscopic villous atrophy in part one and two of the duodenum with high definition white light endoscopy and magnification endoscopy. Endoscopic findings of the duodenum were compared to histology as the reference standard. A short training video of varying degrees of villous atrophy seen by magnification endoscopy was used to train individuals. They were then assessed for the ability to differentiate between normal duodenum and villous atrophy. RESULTS Two hundred and fifty patients were prospectively recruited (145 females, 58%; age range 16-84, median age 50.5). Ninety-six patients had villous atrophy on histology (38.4%) 154 were controls. Magnification endoscopy had a higher sensitivity in detecting villous atrophy compared to high definition white light endoscopy (86.4% versus 78.4%, p = .0005). 9/10 individuals undertaking magnification endoscopy training correctly identified all cases of villous atrophy. CONCLUSION Magnification endoscopy has superior diagnostic sensitivity in detecting villous atrophy compared to high definition white light endoscopy and the potential to be easily adopted by all endoscopists.
Collapse
Affiliation(s)
- Suneil A Raju
- Academic Unit of Gastroenterology, Royal Hallamshire Hospital, Sheffield, United Kingdom.
| | - William L White
- Academic Unit of Gastroenterology, Royal Hallamshire Hospital, Sheffield, United Kingdom
| | - Michelle S Lau
- Academic Unit of Gastroenterology, Royal Hallamshire Hospital, Sheffield, United Kingdom
| | - Peter D Mooney
- Academic Unit of Gastroenterology, Royal Hallamshire Hospital, Sheffield, United Kingdom
| | - Michael A Rees
- Academic Unit of Gastroenterology, Royal Hallamshire Hospital, Sheffield, United Kingdom
| | - Mitchell Burden
- Academic Unit of Gastroenterology, Royal Hallamshire Hospital, Sheffield, United Kingdom
| | - Carolina Ciacci
- Unit of Gastronterology, AOU San Giovannidi Dio e Ruggi D'Aragona, Department of Medicine and Surgery, Scuola Medica Salernitana, University of Salerno, Italy
| | - David S Sanders
- Academic Unit of Gastroenterology, Royal Hallamshire Hospital, Sheffield, United Kingdom
| |
Collapse
|
|
27
|
Kim SH, Yang DH, Kim JS. Current Status of Interpretation of Small Bowel Capsule Endoscopy. Clin Endosc 2018; 51:329-333. [PMID: 30078306 PMCID: PMC6078920 DOI: 10.5946/ce.2018.095] [Citation(s) in RCA: 9] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 06/03/2018] [Accepted: 07/18/2018] [Indexed: 02/06/2023] Open
Abstract
Capsule endoscopy (CE) has revolutionized direct small bowel imaging and is widely used in clinical practice. Remote visualization of bowel images enables painless, well-tolerated endoscopic examinations. Small bowel CE has a high diagnostic yield and the ability to examine the entire small bowel. The diagnostic yield of CE relies on lesion detection and interpretation. In this review, issues related to lesion detection and interpretation of CE have been addressed, and the current status of automated reading software development has been reviewed. Clinical significance of an external real-time image viewer has also been described.
Collapse
Affiliation(s)
- Su Hwan Kim
- Department of Internal Medicine, Seoul Metropolitan Government Seoul National University Boramae Medical Center, Seoul National University College of Medicine, Seoul, Korea
| | - Dong-Hoon Yang
- Department of Gastroenterology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Korea
| | - Jin Su Kim
- Division of Gastroenterology, Department of Internal Medicine, Seoul St. Mary's Hospital, The Catholic University of Korea College of Medicine, Seoul, Korea
| |
Collapse
|
|
28
|
Mitselos IV, Christodoulou DK. What defines quality in small bowel capsule endoscopy. ANNALS OF TRANSLATIONAL MEDICINE 2018; 6:260. [PMID: 30094246 DOI: 10.21037/atm.2018.05.28] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/15/2022]
Abstract
Small bowel capsule endoscopy is considered a first-line diagnostic tool for the investigation of small bowel diseases. Gastroenterological and endoscopic societies have proposed and established measures known as quality indicators, quality measures or performance measures for the majority of endoscopic procedures, in order to ensure competence, healthcare quality and define areas requiring improvement. However, there is a paucity of publications describing small bowel capsule endoscopy quality indicators. Hereby, we attempt to identify and describe a number of pre-procedure, intra-procedure and post-procedure quality indicators, regarding process measures in small bowel capsule endoscopy, after a comprehensive review of the literature.
Collapse
Affiliation(s)
- Ioannis V Mitselos
- Department of Gastroenterology, School of Health Sciences, University Hospital of Ioannina, Faculty of Medicine, University of Ioannina, Ioannina, Greece
| | - Dimitrios K Christodoulou
- Department of Gastroenterology, School of Health Sciences, University Hospital of Ioannina, Faculty of Medicine, University of Ioannina, Ioannina, Greece
| |
Collapse
|
|
29
|
Omori T, Hara T, Sakasai S, Kambayashi H, Murasugi S, Ito A, Nakamura S, Tokushige K. Does the PillCam SB3 capsule endoscopy system improve image reading efficiency irrespective of experience? A pilot study. Endosc Int Open 2018; 6:E669-E675. [PMID: 29868632 PMCID: PMC5979195 DOI: 10.1055/a-0599-5852] [Citation(s) in RCA: 9] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 06/21/2017] [Accepted: 02/20/2018] [Indexed: 12/20/2022] Open
Abstract
BACKGROUND AND STUDY AIMS The aim of this study was tp compare the diagnostic efficiency of the PillCam SB3 capsule endoscopy (CE) system with the older system, PillCam SB2, taking into consideration the experience of the image reader. PATIENTS AND METHODS Small intestinal CE was conducted on 64 patients around May 2014 when the SB3 was introduced in our hospital. Data obtained from 20 patients (SB2: 10 and SB3: 10) based on transit time were assessed by junior (experience: 20 images), intermediate (> 50), and expert readers (> 600). RESULTS Reading time with the CE down to the end of the small intestine was shorter in the SB3 group for each reader (SB2 vs. SB3: junior, 40.2 ± 10.1 vs. 23.7 ± 6.7 [ P = 0.0009]; intermediate, 21.4 ± 4.9 vs. 10.3 ± 2.9 [ P = 0.0003]; expert, 23.2 ± 5.6 vs. 11.1 ± 2.9 min [ P = 0.0002]). Interpretation agreement rates between the findings by junior and intermediate readers and those by the expert reader were 84.6 % and 92.3 %, respectively. For the junior reader, rates of agreement using the SB2 and SB3 systems with those by the expert reader were 85.7 % and 83.3 %, respectively; no significant difference was noted between the two systems. Similarly, for the intermediate reader, the respective agreement rates using the SB2 and SB3 systems were 85.7 % and 100 %, respectively. CONCLUSIONS The PillCam SB3 reduces the time burden on readers irrespective of their experience.
Collapse
Affiliation(s)
- Teppei Omori
- Institute of Gastroenterology, Tokyo Women’s University, Tokyo, Japan,Corresponding author Teppei Omori, MD Institute of GastroenterologyTokyo Women’s Medical University8-1 Kawada-choShinjuku-kuTokyo 162-8666Japan+81-3-5269-7507
| | - Toshifumi Hara
- Institute of Gastroenterology, Tokyo Women’s University, Tokyo, Japan
| | - Sachiyo Sakasai
- Central Clinical Laboratory, Tokyo Women’s Medical University, Tokyo, Japan
| | | | - Shun Murasugi
- Institute of Gastroenterology, Tokyo Women’s University, Tokyo, Japan
| | - Ayumi Ito
- Institute of Gastroenterology, Tokyo Women’s University, Tokyo, Japan
| | - Shinichi Nakamura
- Institute of Gastroenterology, Tokyo Women’s University, Tokyo, Japan
| | | |
Collapse
|
|
30
|
Domperidone prolongs oral to duodenal transit time in video capsule endoscopy. Eur J Clin Pharmacol 2017; 74:521-524. [PMID: 29222714 DOI: 10.1007/s00228-017-2399-8] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/11/2017] [Accepted: 12/05/2017] [Indexed: 01/10/2023]
Abstract
PURPOSE Domperidone is thought to accelerate gastric emptying via D2 receptor antagonism at the gastro-oesophageal and gastro-duodenal junctions. Listed in the BNF as a prokinetic anti-emetic, it has been used in video capsule endoscopy (VCE) to accelerate capsule delivery to the small intestine. We audited VCEs performed at UHCW from 2011, when as standard practice, domperidone was given pre-VCE, to 2012, after its discontinuation due to doubts about its effectiveness. METHODS Thirty-one patients received oral domperidone 20 mg pre-VCE. Thirty-three patients underwent VCE without domperidone pre-treatment. After 2 h, if the capsule remained intra-gastric, gastroscopy-assisted duodenal delivery was performed. Data was analysed using Mann-Whitney testing. RESULTS Median oro-duodenal transit was 13 and 30 min in the untreated and domperidone groups, respectively (p = 0.01). Median oro-caecal transit was 242 and 267 min in the untreated and domperidone groups, respectively (p = 0.02). No difference in duodenal-caecal transit was seen (p = 0.60). Six percent of untreated and 13% of domperidone VCEs required gastroscopy-assisted duodenal capsule delivery (p = 0.65). CONCLUSIONS Unexpectedly domperidone delayed VCE gastric transit. Most studies on domperidone prokinetic effects have been in diabetic gastroparesis, demonstrating that domperidone can achieve good symptomatic relief, but with mixed results for gastric emptying. Our study suggests that any antiemetic effects of domperidone are not mediated through accelerated gastric transit.
Collapse
|
|
31
|
Iwata Y, Nishikawa H, Enomoto H, Yoh K, Ishii A, Yuri Y, Ishii N, Miyamoto Y, Hasegawa K, Nakano C, Takata R, Nishimura T, Aizawa N, Sakai Y, Ikeda N, Takashima T, Iijima H, Nishiguchi S. Efficacy of capsule endoscopy in patients with cirrhosis for the diagnosis of upper gastrointestinal lesions and small bowel abnormalities: a study protocol for prospective interventional study. BMJ Open Gastroenterol 2017; 4:e000168. [PMID: 29177064 PMCID: PMC5689481 DOI: 10.1136/bmjgast-2017-000168] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/02/2017] [Revised: 08/10/2017] [Accepted: 08/14/2017] [Indexed: 11/29/2022] Open
Abstract
INTRODUCTION AND AIMS The role of capsule endoscopy (CE) in patients with liver cirrhosis (LC) has yet to be established; however, it is likely that it will remain a valuable diagnostic modality in several groups of patients with LC. The primary aims of the current prospective interventional study are to examine the prevalence for small bowel lesions and transit time of CE in the gastrointestinal tract in patients with LC with oesophageal varices (EVs) requiring endoscopic therapies. METHODS AND ANALYSIS The current study will be a single-centre prospective interventional study. Our study participants are LC subjects with portal hypertension who were determined to be necessary for prophylactic endoscopic therapies for EVs. From the view point of safety, patients with gastrointestinal obstruction or fistula or those being suspected of having gastrointestinal obstruction or fistula will be excluded from our study. Patients with implanted medical devices will be also excluded. CE will be performed prior to prophylactic endoscopic therapies in the same hospitalisation and relevant images will be analysed after 8 hours by expert endoscopists. This study will continue to recruit until 50 participants. ETHICS AND DISSEMINATION This study has received approval from the Institutional Review Board at Hyogo College of Medicine (approval no. 2680). The study protocol, informed assent form and other submitted files were reviewed and acknowledged. Final data will be publicly scattered regardless of the study results. A report releasing study results will be submitted for publication in a suitable journal after being finished in data collection. TRIAL REGISTRATION NUMBER UMIN000028433 (https://upload.umin.ac.jp/).
Collapse
Affiliation(s)
- Yoshinori Iwata
- Division of Hepatobiliary and Pancreatic disease, Department of Internal Medicine, Hyogo College of Medicine, Nishinomiya, Japan
| | - Hiroki Nishikawa
- Division of Hepatobiliary and Pancreatic disease, Department of Internal Medicine, Hyogo College of Medicine, Nishinomiya, Japan
- Center for Clinical Research and Education, Hyogo College of Medicine, Nishinomiya, Japan
| | - Hirayuki Enomoto
- Division of Hepatobiliary and Pancreatic disease, Department of Internal Medicine, Hyogo College of Medicine, Nishinomiya, Japan
| | - Kazunori Yoh
- Division of Hepatobiliary and Pancreatic disease, Department of Internal Medicine, Hyogo College of Medicine, Nishinomiya, Japan
| | - Akio Ishii
- Division of Hepatobiliary and Pancreatic disease, Department of Internal Medicine, Hyogo College of Medicine, Nishinomiya, Japan
| | - Yukihisa Yuri
- Division of Hepatobiliary and Pancreatic disease, Department of Internal Medicine, Hyogo College of Medicine, Nishinomiya, Japan
| | - Noriko Ishii
- Division of Hepatobiliary and Pancreatic disease, Department of Internal Medicine, Hyogo College of Medicine, Nishinomiya, Japan
| | - Yuho Miyamoto
- Division of Hepatobiliary and Pancreatic disease, Department of Internal Medicine, Hyogo College of Medicine, Nishinomiya, Japan
| | - Kunihiro Hasegawa
- Division of Hepatobiliary and Pancreatic disease, Department of Internal Medicine, Hyogo College of Medicine, Nishinomiya, Japan
| | - Chikage Nakano
- Division of Hepatobiliary and Pancreatic disease, Department of Internal Medicine, Hyogo College of Medicine, Nishinomiya, Japan
| | - Ryo Takata
- Division of Hepatobiliary and Pancreatic disease, Department of Internal Medicine, Hyogo College of Medicine, Nishinomiya, Japan
| | - Takashi Nishimura
- Division of Hepatobiliary and Pancreatic disease, Department of Internal Medicine, Hyogo College of Medicine, Nishinomiya, Japan
| | - Nobuhiro Aizawa
- Division of Hepatobiliary and Pancreatic disease, Department of Internal Medicine, Hyogo College of Medicine, Nishinomiya, Japan
| | - Yoshiyuki Sakai
- Division of Hepatobiliary and Pancreatic disease, Department of Internal Medicine, Hyogo College of Medicine, Nishinomiya, Japan
| | - Naoto Ikeda
- Division of Hepatobiliary and Pancreatic disease, Department of Internal Medicine, Hyogo College of Medicine, Nishinomiya, Japan
| | - Tomoyuki Takashima
- Division of Hepatobiliary and Pancreatic disease, Department of Internal Medicine, Hyogo College of Medicine, Nishinomiya, Japan
| | - Hiroko Iijima
- Division of Hepatobiliary and Pancreatic disease, Department of Internal Medicine, Hyogo College of Medicine, Nishinomiya, Japan
| | - Shuhei Nishiguchi
- Division of Hepatobiliary and Pancreatic disease, Department of Internal Medicine, Hyogo College of Medicine, Nishinomiya, Japan
- Center for Clinical Research and Education, Hyogo College of Medicine, Nishinomiya, Japan
| |
Collapse
|
|
32
|
Toth E, Marthinsen L, Bergström M, Park PO, Månsson P, Nemeth A, Johansson GW, Thorlacius H. Colonic obstruction caused by video capsule entrapment in a metal stent. ANNALS OF TRANSLATIONAL MEDICINE 2017; 5:199. [PMID: 28567379 DOI: 10.21037/atm.2017.03.79] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/22/2022]
Abstract
Video capsule endoscopy (VCE) has become the method of choice for visualizing the small bowel mucosa and is generally considered to be a safe method. Although uncommon, the most feared complication of VCE is capsule retention that can potentially lead to life-threatening bowel obstruction. Herein, we present for the first time a case of capsule retention in a colonic stent. The patient had known Crohn's disease with colonic involvement and underwent an uneventful but incomplete small bowel VCE for assessment of disease activity and extension for optimizing medical treatment. Five months later, the patient presented with intestinal obstruction due to a Crohn's-stricture in the sigmoid colon, which was successfully decompressed with a self-expandable metal stent. Nonetheless, two days later the patient showed signs of bowel obstruction again and abdominal X-ray showed that the capsule was trapped in the metal stent in the sigmoid colon. Subsequently, emergency surgery was performed and the patient fully recovered. Intestinal capsule retention necessitating interventional removal is rare. This report describes a unique case of capsule retention in a colonic metal stent and highlights the potential risk of performing capsule endoscopy examinations in patients with gastrointestinal stents.
Collapse
Affiliation(s)
- Ervin Toth
- Department of Gastroenterology, Skåne University Hospital, Lund University, 20502 Malmö, Sweden
| | - Lars Marthinsen
- Department of Pediatrics, Halmstad Hospital, 30185 Halmstad, Sweden
| | - Maria Bergström
- Department of Surgery, South Älvsborg Hospital, 50182 Borås, Sweden
| | - Per-Ola Park
- Department of Surgery, South Älvsborg Hospital, 50182 Borås, Sweden
| | - Peter Månsson
- Department of Surgery, Halmstad Hospital, 30185 Halmstad, Sweden
| | - Artur Nemeth
- Department of Gastroenterology, Skåne University Hospital, Lund University, 20502 Malmö, Sweden
| | - Gabriele Wurm Johansson
- Department of Gastroenterology, Skåne University Hospital, Lund University, 20502 Malmö, Sweden
| | - Henrik Thorlacius
- Department of Surgery, Skåne University Hospital, Lund University, 20502 Malmö, Sweden
| |
Collapse
|
|
33
|
Abstract
PURPOSE OF REVIEW The breakthrough success of capsule endoscopy and device-assisted enteroscopy has inspired researchers to test and push the boundary of these technologies. The authors herein summarize the latest and most significant studies with clinical impact. RECENT FINDINGS Competing capsule endoscopy models have enriched the platform of this wireless device. The role of capsule endoscopy in Crohn's disease is expanding as we learn more of the significance of disease distribution and response to treatment. The benefit of capsule endoscopy in abdominal pain has previously been sceptical, but may have a role. Device-assisted enteroscopy demonstrates significant benefit in the management of patients with Crohn's disease and Peutz-Jeghers syndrome. On the contrary, long-term data suggest that endotherapy to small bowel angioectasia may not be as beneficial to patients as we once thought. The role of device-assisted enteroscopy in novel territory, including coeliac disease and endoscopic retrograde cholangiopancreatography, continues to be tested. SUMMARY The limit of capsule endoscopy and enteroscopy is yet to be reached. Accumulating long-term data alludes to the benefits of our current practice while spawning novel indications for small bowel endoscopy.
Collapse
|