| 1. |
- Baldaque-Silva, Francisco, et al.
(författare)
-
Endoscopic assessment and grading of Barrett's esophagus using magnification endoscopy and narrow band imaging: Impact of structured learning and experience on the accuracy of the Amsterdam classification system
- 2013
-
Ingår i: Scandinavian Journal of Gastroenterology. - : Informa UK Limited. - 1502-7708 .- 0036-5521. ; 48:2, s. 160-167
-
Tidskriftsartikel (refereegranskat)abstract
- Objective. Several classification systems have been launched to characterize Barrett's esophagus (BE) mucosa using magnification endoscopy with narrow band imaging (ME-NBI). The good accuracy and interobserver agreement described in the early reports were not reproduced subsequently. Recently, we reported somewhat higher accuracy of the classification developed by the Amsterdam group. The critical question then formulated was whether a structured learning program and the level of experience would affect the clinical usefulness of this classification. Material & methods: Two hundred and nine videos were prospectively captured from patients with BE using ME-NBI. From these, 70 were randomly selected and evaluated by six endoscopists with different levels of expertise, using a dedicated software application. First, an educational set was studied. Thereafter, the 70 test videos were evaluated. After classification of each video, the respective histological feedback was automatically given. Results. Within the learning process, there was a decrease in the time needed for evaluation and an increase in the certainty of prediction. The accuracy did not increase with the learning process. The sensitivity for detection of intestinal metaplasia ranged between 39% and 57%, and for neoplasia between 62% and 90%, irrespective of assessor's expertise. The kappa coefficient for the interobserver agreement ranged from 0.25 to 0.30 for intestinal metaplasia, and from 0.39 to 0.48 for neoplasia. Conclusion: Using a dedicated learning program, the ME-NBI Amsterdam classification system is suboptimal in terms of accuracy and inter- and intraobserver agreements. These results reiterate the questionable utility of corresponding classification system in clinical routine practice.
|
|
| 2. |
|
|
| 3. |
|
|
| 4. |
- Haraldsson, Erik, 1972, et al.
(författare)
-
Macroscopic appearance of the major duodenal papilla influences bile duct cannulation: a prospective multicenter study by the Scandinavian Association for Digestive Endoscopy Study Group for ERCP
- 2019
-
Ingår i: Gastrointestinal Endoscopy. - : Elsevier BV. - 0016-5107 .- 1097-6779. ; 90:6, s. 957-963
-
Tidskriftsartikel (refereegranskat)abstract
- Background and Aims: Certain appearances of the major duodenal papilla have been claimed to make cannulation more difficult during ERCP. This study uses a validated classification of the endoscopic appearance of the major duodenal papilla to determine if certain types of papilla predispose to difficult cannulation. Methods: Patients with a naïve papilla scheduled for ERCP were included. The papilla was classified into 1 of 4 papilla types before cannulation started. Time to successful bile duct cannulation, attempts, and number of pancreatic duct passages were recorded. Difficult cannulation was defined as after 5 minutes, 5 attempts, or 2 pancreatic guidewire passages. Results: A total of 1401 patients were included from 9 different centers in the Nordic countries. The overall frequency of difficult cannulation was 42% (95% confidence interval [CI], 39%-44%). Type 2 small papilla (52%; 95% CI, 45%-59%) and type 3 protruding or pendulous papilla (48%; 95% CI, 42%-53%) were more frequently difficult to cannulate compared with type 1 regular papilla (36%; 95% CI, 33%-40%; both P <.001). If an inexperienced endoscopist started cannulation, the frequency of failed cannulation increased from 1.9% to 6.3% (P <.0001), even though they were replaced by a senior endoscopist after 5 minutes. Conclusions: The endoscopic appearance of the major duodenal papilla influences bile duct cannulation. Small type 2 and protruding or pendulous type 3 papillae are more frequently difficult to cannulate. In addition, cannulation might even fail more frequently if a beginner starts cannulation. These findings should be taken into consideration when performing studies regarding bile duct cannulation and in training future generations of endoscopists. © 2019 American Society for Gastrointestinal Endoscopy
|
|
| 5. |
- Leenhardt, R., et al.
(författare)
-
Key research questions for implementation of artificial intelligence in capsule endoscopy
- 2022
-
Ingår i: Therapeutic Advances in Gastroenterology. - : SAGE Publications. - 1756-283X .- 1756-2848. ; 15
-
Tidskriftsartikel (refereegranskat)abstract
- Background: Artificial intelligence (AI) is rapidly infiltrating multiple areas in medicine, with gastrointestinal endoscopy paving the way in both research and clinical applications. Multiple challenges associated with the incorporation of AI in endoscopy are being addressed in recent consensus documents. Objectives: In the current paper, we aimed to map future challenges and areas of research for the incorporation of AI in capsule endoscopy (CE) practice. Design: Modified three-round Delphi consensus online survey. Methods: The study design was based on a modified three-round Delphi consensus online survey distributed to a group of CE and AI experts. Round one aimed to map out key research statements and challenges for the implementation of AI in CE. All queries addressing the same questions were merged into a single issue. The second round aimed to rank all generated questions during round one and to identify the top-ranked statements with the highest total score. Finally, the third round aimed to redistribute and rescore the top-ranked statements. Results: Twenty-one (16 gastroenterologists and 5 data scientists) experts participated in the survey. In the first round, 48 statements divided into seven themes were generated. After scoring all statements and rescoring the top 12, the question of AI use for identification and grading of small bowel pathologies was scored the highest (mean score 9.15), correlation of AI and human expert reading-second (9.05), and real-life feasibility-third (9.0). Conclusion: In summary, our current study points out a roadmap for future challenges and research areas on our way to fully incorporating AI in CE reading.
|
|
| 6. |
|
|
| 7. |
- Smedsrud, P. H., et al.
(författare)
-
Kvasir-Capsule, a video capsule endoscopy dataset
- 2021
-
Ingår i: Scientific Data. - : Springer Science and Business Media LLC. - 2052-4463. ; 8:1
-
Tidskriftsartikel (refereegranskat)abstract
- Artificial intelligence (AI) is predicted to have profound effects on the future of video capsule endoscopy (VCE) technology. The potential lies in improving anomaly detection while reducing manual labour. Existing work demonstrates the promising benefits of AI-based computer-assisted diagnosis systems for VCE. They also show great potential for improvements to achieve even better results. Also, medical data is often sparse and unavailable to the research community, and qualified medical personnel rarely have time for the tedious labelling work. We present Kvasir-Capsule, a large VCE dataset collected from examinations at a Norwegian Hospital. Kvasir-Capsule consists of 117 videos which can be used to extract a total of 4,741,504 image frames. We have labelled and medically verified 47,238 frames with a bounding box around findings from 14 different classes. In addition to these labelled images, there are 4,694,266 unlabelled frames included in the dataset. The Kvasir-Capsule dataset can play a valuable role in developing better algorithms in order to reach true potential of VCE technology.
|
|
