Deep learning for wireless capsule endoscopy: a systematic review and meta-analysis.

BACKGROUND AND AIMS: Deep learning is an innovative algorithm based on neural networks. Wireless capsule endoscopy (WCE) is considered the criterion standard for detecting small-bowel diseases. Manual examination of WCE is time-consuming and can benefit from automatic detection using artificial intelligence (AI). We aimed to perform a systematic review of the current literature pertaining to deep learning implementation in WCE. METHODS: We conducted a search in PubMed for all original publications on the subject of deep learning applications in WCE published between January 1, 2016 and December 15, 2019. Evaluation of the risk of bias was performed using tailored Quality Assessment of Diagnostic Accuracy Studies-2. Pooled sensitivity and specificity were calculated. Summary receiver operating characteristic curves were plotted. RESULTS: Of the 45 studies retrieved, 19 studies were included. All studies were retrospective. Deep learning applications for WCE included detection of ulcers, polyps, celiac disease, bleeding, and hookworm. Detection accuracy was above 90% for most studies and diseases. Pooled sensitivity and specificity for ulcer detection were .95 (95% confidence interval [CI], .89-.98) and .94 (95% CI, .90-.96), respectively. Pooled sensitivity and specificity for bleeding or bleeding source were .98 (95% CI, .96-.99) and .99 (95% CI, .97-.99), respectively. CONCLUSIONS: Deep learning has achieved excellent performance for the detection of a range of diseases in WCE. Notwithstanding, current research is based on retrospective studies with a high risk of bias. Thus, future prospective, multicenter studies are necessary for this technology to be implemented in the clinical use of WCE.

Agreement between Fetal Brain Ultrasonography and Magnetic Resonance Imaging in the Measurements of the Corpus Callosum and Transverse Cerebellar Diameter.

As the use of magnetic resonance imaging of the fetal brain has evolved, the need to understand its efficiency in the biometry of the fetal brain has broadened. This study aimed to assess the level of agreement and correlation between the two cardinal imaging methods of fetal neuroimaging, ultrasonography (US) and magnetic resonance imaging (MRI), by measuring the corpus callosum (CC) and transverse cerebellar diameter (TCD) in terms of length and percentile. Measurements of CC and TCD length and percentile were documented over a 7-year span in a tertiary referral medical center. All US and MRI examinations were performed in the customary planes and subcategorized by valid reference charts. Exclusion and inclusion criteria were set before the collection and processing of the data. A total of 156 fetuses out of 483 were included in the study. A positive, strong correlation and agreement were found (r = 0.78; ICC = 0.76) between US and MRI in TCD measurements. For CC length measurement, a moderate correlation and moderate agreement (r = 0.51; ICC = 0.49) between US and MRI was observed. TCD and CC percentiles had lower levels of correlation and agreement compared with the length variables. Our study indicates good agreement between MRI and US in the assessment of TCD measurement as a part of antenatal neuroimaging. Furthermore, while the two techniques are not always compatible, they are complementary methods.

NLRP3 inflammasome activity is upregulated in an in-vitro model of COPD exacerbation.

BACKGROUND: Chronic obstructive pulmonary disease (COPD) is an inflammatory disease characterized by a progressive and irreversible deterioration of lung function. Exacerbations of COPD have prolonged negative effects on pulmonary function and a major impact on health status and outcomes. NLRP3 inflammasome is a cardinal component of the inflammatory response, with marked evidence in stable and exacerbations of COPD. The aim of our study was to evaluate the NLRP3 inflammasome activity during COPD exacerbation by using an in vitro model. METHODS: A549 cells were stimulated with different concentrations (10%, 4%, 2%) of cigarette smoke extract (CSE) with or without LPS (0.1µg/ml) for 24 hours. Cell viability was assessed by using XTT test. Levels of inflammatory cytokines (IL-8, MCP-1, and IL-1ß) were measured by ELISA and the activity level of NLRP-3 was evaluated by flow cytometry. RESULTS: Cells exposed to CSE present an increase in inflammatory cytokines (IL-8 and MCP-1) production in a dose-dependent manner. Incubation with LPS to these cells results in higher levels of IL-8 and MCP-1 compared to stimulation of CSE alone. NLRP3 inflammasome activity and IL-1ß levels were significantly increased in cells exposed to both CSE and LPS compared to CSE alone. CONCLUSIONS: NLRP3 inflammasome is upregulated in an in-vitro model of COPD and COPD exacerbation. Our findings provide novel biomarkers for COPD exacerbation and may present new targets for future research.