1,721,295 research outputs found
Impact of artificial intelligence on colorectal polyp detection
No full textSince colonoscopy and polypectomy were introduced, Colorectal Cancer (CRC) incidence and mortality decreased significantly. Although we have entered the era of quality measurement and improvement, literature shows that a considerable amount of colorectal neoplasia is still missed by colonoscopists up to 25%, leading to an high rate of interval colorectal cancer that account for nearly 10% of all diagnosed CRC. Two main reasons have been recognised: recognition failure and mucosal exposure. For this purpose, Artificial Intelligence (AI) systems have been recently developed that identify a "hot" area during the endoscopic examination. In retrospective studies, where the systems are tested with a batch of unknown images, deep learning systems have shown very good performances, with high levels of accuracy. Of course, this setting may not reflect actual clinical practice where different pitfalls can occur, like suboptimal bowel preparation or poor examination technique. For this reason, a number of randomised clinical trials have recently been published where AI was tested in real time during endoscopic examinations. We present here an overview on recent literature addressing the performance of Computer Assisted Detection (CADe) of colorectal polyps in colonoscopy
Clinical outcomes following stent placement in refractory benign esophageal stricture: a systematic review and meta-analysis
No full textBACKGROUND: The management of refractory benign esophageal strictures (RBESs) is challenging. Stent placement has been proposed as a possible rescue strategy. We performed a systematic review and meta-analysis to examine the efficacy of this strategy in the long-term resolution of dysphagia.
METHODS:
PubMed, SCOPUS, and Google Scholar were searched (up to January 2015). Studies recruiting adults with RBES treated with stent placement were eligible. The success, adverse event, and migration rates were pooled by means of a random-effect model to obtain odds with a 95 % confidence interval (CI).
RESULTS:
Eighteen studies (444 patients) were eligible for inclusion. The pooled clinical success rate was 40.5 % (95 %CI 31.5 % - 49.5 %), yielding odds of 0.68 (95 %CI 0.46 - 0.98) with high heterogeneity (I(2) = 65.0 %). The meta-regression analysis showed stricture etiology as the only influencing factor. Treatment with self-expanding plastic (SEPSs) and metal stents (SEMSs) did not result in significantly higher success rates than treatment with biodegradable stents (BDSs) (46.2 % vs. 40.1 % vs. 32.9 %, respectively). The migration rate was 28.6 % (95 %CI 21.9 % - 37.1 %), yielding odds of 0.40 (95 %CI 0.28 - 0.59), with migration rates for SEPSs and SEMSs reported as being not significantly higher than BDSs (33.3 % vs. 31.5 % vs. 15.3 %, respectively). The adverse event rate was 20.6 % (95 %CI 15.3 % - 28.1 %), yielding odds of 0.26 (95 %CI 0.18 - 0.39) with no significant difference between stent types (19.4 % vs. 21.9 % vs. 21.9 %, respectively).
CONCLUSIONS:
Stent placement in patients with RBES is effective in about 40 % of cases. Further studies should investigate whether the clinical success rate varies according to the stricture etiology.(PROSPERO registration number: CRD42015019017.)
Primary drainage of distal malignant biliary obstruction: A comparative network meta-analysis
No full textBackground: The effectiveness of various primary upfront drainage techniques for distal malignant biliary obstructions (dMBO) is not well-established. Objective: To compare the technical and clinical success rates and adverse event (AE) rates of various primary drainage techniques. Methods: We systematically reviewed RCTs comparing the technical and clinical success and AE rates of EUS-choledochoduodenostomy (CDS) with lumen-apposing metal stent (LAMS), EUS-CDS with self-expandable metal stents (SEMS), EUS-hepaticogastrostomy (HGS), ERCP, and PTBD performed upfront. Results: Six RCTs involving 583 patients were analyzed. EUS-CDS with LAMS showed significantly higher technical success compared to EUS-CDS with SEMS (RR 1.21, 95 % CI 1.07-1.37) and ERCP (RR 1.17, 95 % CI 1.07-1.28). EUS-CDS with LAMS had the highest rank in technical success (SUCRA = 0.86). The clinical success rate was also higher with EUS-CDS with LAMS than with ERCP (RR 1.12, 1.01-1.25). PTBD was the worst ranked procedure for safety (SUCRA score = 0.18), while EUS-CDS with LAMS was the top procedure for procedural time (SUCRA score = 0.83). Conclusion: EUS-CDS with LAMS has the highest technical and clinical success rates and is significantly superior to ERCP as the upfront technique for dMBO treatment. PTBD should be abandoned as first-line treatment due to the poor safety profile
Performance of a new integrated computer-assisted system (CADe/CADx) for detection and characterization of colorectal neoplasia
No full textBACKGROUND: Use of artificial intelligence may increase detection of colorectal neoplasia at colonoscopy by improving lesion recognition (CADe) and reduce pathology costs by improving optical diagnosis (CADx). METHODS: A multicenter library of ≥ 200 000 images from 1572 polyps was used to train a combined CADe/CADx system. System testing was performed on two independent image sets (CADe: 446 with polyps, 234 without; CADx: 267) from 234 polyps, which were also evaluated by six endoscopists (three experts, three non-experts). RESULTS: CADe showed sensitivity, specificity, and accuracy of 92.9 %, 90.6 %, and 91.7 %, respectively. Experts showed significantly higher accuracy and specificity, and similar sensitivity, while non-experts + CADe showed comparable sensitivity but lower specificity and accuracy than CADe and experts. CADx showed sensitivity, specificity, and accuracy of 85.0 %, 79.4 %, and 83.6 %, respectively. Experts showed comparable performance, whereas non-experts + CADx showed comparable accuracy but lower specificity than CADx and experts. CONCLUSIONS: The high accuracy shown by CADe and CADx was similar to that of experts, supporting further evaluation in a clinical setting. When using CAD, non-experts achieved a similar performance to experts, with suboptimal specificity
Single-session double-stent placement in concomitant malignant biliary and duodenal obstruction with a cautery-tipped lumen apposing metal stent
No full textThe worst adverse event for an endoscopist after esophageal stent placement: an aortoesophageal fistula
No full textTen quality indicators for endoscopic submucosal dissection: what should be monitored and reported to improve quality
No full textIn the last decade, endoscopic submucosal dissection (ESD) has become more popular in Asia and, more recently, also in Europe and North America, however the issue of quality control has never been raised. Therefore, there is an urgent need to identify possible quality indicators to monitor as part of internal audit process. This is particularly compelling, since the diffusion of ESD outside Asian, super-expert, high-volume, tertiary referral centers. In the current review, we raised the issue of quality control for ESD and proposed a list of ten possible quality indicators that should be monitored by each endoscopist and reported in every study reporting results on ESD procedures. We feel that these quality indicators should be used in clinical practice by endoscopists to benchmark the data with the internationally recommended standards
Standard needle versus needleless injection modality: animal study on different fluids for submucosal elevation
No full textSubmucosal injection is currently used in GI endoscopy to reduce resection risks and to perform submucosal dissection; it is usually performed via an injection needle or via a needleless device. The aim of the study was to compare 2 submucosal injection modalities (needle-assisted vs needleless) by using substances with different viscosities METHODS: Needle and needleless injections were compared by assessing the efficacy of tissue elevation with 5 different substances in an ex vivo porcine model. The height of the submucosal elevation was measured after 0(t0), 10(t1) and 30 minutes after injection(t2). Viscosity of the solution was also measured
- …
