Performance of a new integrated computer-assisted system (CADe/CADx) for detection and characterization of colorectal neoplasia.

BACKGROUND: 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.

Can a Polyp Detection and Characterization System Predict Complete Resection?

INTRODUCTION: Artificial Intelligence (AI) is one of the most evolving fields in endoscopy. We aimed to test if a system for polyp detection and polyp characterization can be used to predict complete endoscopic resection of colon adenomas. METHODS: We used the CAD-Eye AI system (Fujifilm Europe) in consecutive patients who received polypectomy using a cold snare. After resection, the submucosal space was flushed with water using an irrigation pump. Images were obtained using the CAD Eye system, and the characterization of the system was noted and afterward compared to histology of the removed specimen. RESULTS: In total, 17 polypectomies were observed, and in no case the AI was able to give information about resection status. First, the resection plane itself was classified as being adenomatous in all cases, while, second, all adenomas were resected completely, thus harboring no potential for overlying misinterpretations in the images. CONCLUSION: An AI system trained to characterize polyps in healthy surrounding colorectal mucosa cannot predict the state of resection after removal of the adenoma. This is explained by the training and programming. Endoscopists using AI from now on should learn about the basics of AI and the pitfalls in interpreting results from AI.

RiMINI - the influence of rifaximin on minimal hepatic encephalopathy (MHE) and on the intestinal microbiome in patients with liver cirrhosis: study protocol for a randomized controlled trial.

BACKGROUND: Hepatic encephalopathy (HE) is a clinically significant complication of liver cirrhosis impacting on the patients' quality of life. Minimal hepatic encephalopathy (MHE) is diagnosed by psychometric tests, found in up to 80 % of patients with liver cirrhosis and carries a high risk of progression to overt HE. Continuous therapy with rifaximin in combination with lactulose significantly reduces the risk of overt HE, recurrence of HE and HE-related hospitalizations in randomized, double-blind, placebo-controlled clinical trials. Rifaximin is approved for the therapy of overt HE in Germany. Treatment with lactulose has been shown to improve cognitive functions in patients with liver cirrhosis. Data from prospective clinical trials comparing the efficacy of rifaximin alone against a combination of rifaximin and lactulose in the treatment of MHE are scarce. Changes in the microbiome of the upper and lower gastrointestinal tract as a result of therapy with rifaximin have not yet been addressed in clinical studies. METHODS AND DESIGN: RiMINI is a monocentric exploratory pilot study on 60 patients with MHE as assessed by critical flicker frequency (CFF). Additionally, visual evoked potentials' (VEP) testing, electroencephalography (EEG) and psychometric testing (NCT-A) will be carried out. Patients will be randomized to treatment either with rifaximin alone (550 mg twice daily (bid) continuously for a period of 3 months) or with rifaximin (550 mg bid continuously) in combination with lactulose (30-60 ml daily) for 3 months. An esophagogastroduodenoscopy (EGD) will be performed at baseline, at the end of treatment and 6 and 12 weeks after the end of treatment to obtain gastric and duodenal biopsies and aspirates. The samples will be analyzed for their content of specific bacterial taxae by applying next generation sequencing (NGS) after rRNA isolation to identify the microbiome of the stomach and duodenum, and of the gut, in patients with liver cirrhosis and MHE before and after therapy. DISCUSSION: Differences of the effect of antibiotic therapy with rifaximin alone or in combination with lactulose on the clinical course of MHE are assessed. TRIAL REGISTRATION: The trial was registered as DRKS00006359 on March 17th 2015, with the universal trial number U1111-1163-9410 and with EudraCT2013-004414-18 .