An artificial intelligence algorithm is highly accurate for detecting endoscopic features of eosinophilic esophagitis.

The endoscopic features associated with eosinophilic esophagitis (EoE) may be missed during routine endoscopy. We aimed to develop and evaluate an Artificial Intelligence (AI) algorithm for detecting and quantifying the endoscopic features of EoE in white light images, supplemented by the EoE Endoscopic Reference Score (EREFS). An AI algorithm (AI-EoE) was constructed and trained to differentiate between EoE and normal esophagus using endoscopic white light images extracted from the database of the University Hospital Augsburg. In addition to binary classification, a second algorithm was trained with specific auxiliary branches for each EREFS feature (AI-EoE-EREFS). The AI algorithms were evaluated on an external data set from the University of North Carolina, Chapel Hill (UNC), and compared with the performance of human endoscopists with varying levels of experience. The overall sensitivity, specificity, and accuracy of AI-EoE were 0.93 for all measures, while the AUC was 0.986. With additional auxiliary branches for the EREFS categories, the AI algorithm (AI-EoE-EREFS) performance improved to 0.96, 0.94, 0.95, and 0.992 for sensitivity, specificity, accuracy, and AUC, respectively. AI-EoE and AI-EoE-EREFS performed significantly better than endoscopy beginners and senior fellows on the same set of images. An AI algorithm can be trained to detect and quantify endoscopic features of EoE with excellent performance scores. The addition of the EREFS criteria improved the performance of the AI algorithm, which performed significantly better than endoscopists with a lower or medium experience level.

POFUT1 mRNA expression as an independent prognostic parameter in muscle-invasive bladder cancer.

Muscle-invasive bladder cancer (MIBC) is characterized by high recurrence and rapid progression. Progression is linked to changes in glycan structures and altered levels of glycosyltransferases. The relationship of mRNA expression by glycosyltransferase genes B4GALT1, EXT1, MGAT5B, and POFUT1 to the probability of surviving MIBC after radical cystectomy has not yet been investigated. mRNA expression was analyzed using qRT-PCR in formalin-fixed and paraffin-embedded tumor samples (n = 105; 74% male patients and 26% female patients; median age = 72 years), correlated with histopathological variables, and evaluated by means of multivariable Cox regression analysis regarding to overall survival (OS), cancer-specific survival (CSS), and disease-free survival (DFS). Multivariable Cox regression analysis identified POFUT1 mRNA expression as superior prognostic marker, compared with currently used histological tumor stage methods, for CSS by MIBC patients following radical cystectomy. Thus, the patients with low POFUT1 mRNA were at a 4.9-fold greater risk for cancer-specific death according to the multivariable analysis (p = 0.0001). Low mRNA levels predicted poor survival according to the Kaplan-Meier analysis ((POFUT1:OS p = 0.0014; CSS p = 0.0007; DFS p = 0.0088); (EXT1:OS p = 0.0150; CSS p = 0.0130; DFS p = 0.0286); (B4GALT1:CSS p = 0.0134; DFS p = 0.0493)). A subgroup analysis of patients without lymph node metastasis (pN-; n = 73) indicated that low expression of POFUT1 predicted reduced OS (p = 0.0073), CSS (p = 0.0058,) and DSS (p = 0.0079). Low levels of POFUT1 mRNA are an independent prognostic indicator for OS and CSS in MIBC patients following radical cystectomy. This finding demonstrates the importance of altered glycosylation for the progress of MIBC.

ANLN and TLE2 in Muscle Invasive Bladder Cancer: A Functional and Clinical Evaluation Based on In Silico and In Vitro Data.

: Anilin actin binding protein (ANLN) and transducing-like enhancer protein 2 (TLE2) are associated with cancer patient survival and progression. The impact of their gene expression on progression-free survival (PFS) of patients with muscle invasive bladder cancer (MIBC) treated with radical cystectomy (RC) and subtype association has not yet been investigated. qRT-PCR was used to measure the transcript levels of ANLN and TLE2 in the Mannheim cohort, and validated in silico by The Cancer Genome Atlas (TCGA) cohort. Uni- and multivariate Cox regression analyses identified predictors for disease-specific survival (DSS) and overall survival (OS). In the Mannheim cohort, tumors with high ANLN expression were associated with lower OS and DSS, while high TLE2 expression was associated with a favorable OS. The TCGA cohort confirmed that high ANLN and low TLE2 expression was associated with shorter OS and disease-free survival (DFS). In both cohorts, multivariate analyses showed ANLN and TLE2 expression as independent outcome predictors. Furthermore, ANLN was more highly expressed in cell lines and patients with the basal subtype, while TLE2 expression was higher in cell lines and patients with the luminal subtype. ANLN and TLE2 are promising biomarkers for individualized bladder cancer therapy including cancer subclassification and informed MIBC prognosis.

Predictive value of lymphangiogenesis and proliferation markers on mRNA level in urothelial carcinoma of the bladder after radical cystectomy.

OBJECTIVE: To evaluate the mRNA expression of lymphangiogenesis and proliferation markers and to examine its association with histopathological characteristics and clinical outcome in patients with urothelial carcinoma of the bladder (UCB) after radical cystectomy (RC). PATIENTS AND METHODS: Gene expression analysis of the vascular endothelial growth -C and -D (VEGF-C/-D), its receptor VEGF receptor-3 (VEGFR-3), MKI67, and RACGAP1 was performed in 108 patients after radical cystectomy and their correlation with clinical-pathological parameters was investigated. Uni- and multivariate regression analyses were used to identify predictors for cancer-specific survival (CSS), recurrence-free survival (RFS) and overall survival (OS) after RC. RESULTS: The expression of RACGAP1 and VEGFR-3 showed an association with a higher pT stage (P = 0.049; P = 0.009). MKI67 showed an association with a high-grade urothelial carcinoma of the bladder (P = 0.021). VEGFR-3 expression was significantly associated with the presence of lymphovascular invasion (LVI) (P = 0.016) and lymph node metastases (pN+) (P = 0.028). With the univariate analysis, overexpression of VEGFR-3 (P = 0.029) and the clinical-pathological parameters pT stage (P < 0.0001), pN+ (P = 0.0004), LVI (P < 0.0001) and female gender (P = 0.021) were significantly associated with a reduced CSS. Multivariate analysis identified a higher pT stage (P = 0.017) and LVI (P = 0.008) as independent predictors for reduced CSS. Independent predictors for reduced OS were a higher pT stage (P = 0.0007) and LVI (P = 0.0021), while overexpression of VEGF-D was associated with better OS (P < 0.0001). CONCLUSIONS: The mRNA expression of the investigated markers showed associations with common histopathological parameters. Increased expression of VEGF-D is independently associated with better overall survival.