Comparative study on artificial intelligence systems for detecting early esophageal squamous cell carcinoma between narrow-band and white-light imaging

BACKGROUND Non-magnifying endoscopy with narrow-band imaging(NM-NBI)has been frequently used in routine screening of esophagus squamous cell carcinoma(ESCC).The performance of NBI for screening of early ESCC is,however,significantly affected by operator experience.Artificial intelligence may be a unique approach to compensate for the lack of operator experience.AIM To construct a computer-aided detection(CAD)system for application in NMNBI to identify early ESCC and to compare it with our previously reported CAD system with endoscopic white-light imaging(WLI).METHODS A total of 2167 abnormal NM-NBI images of early ESCC and 2568 normal images were collected from three institutions(Zhongshan Hospital of Fudan University,Xuhui Hospital,and Kiang Wu Hospital)as the training dataset,and 316 pairs of images,each pair including images obtained by WLI and NBI(same part),were collected for validation.Twenty endoscopists participated in this study to review the validation images with or without the assistance of the CAD systems.The diagnostic results of the two CAD systems and improvement in diagnostic efficacy of endoscopists were compared in terms of sensitivity,specificity,accuracy,positive predictive value,and negative predictive value.RESULTS The area under receiver operating characteristic curve for CAD-NBI was 0.9761.For the validation dataset,the sensitivity,specificity,accuracy,positive predictive value,and negative predictive value of CAD-NBI were 91.0%,96.7%,94.3%,95.3%,and 93.6%,respectively,while those of CAD-WLI were 98.5%,83.1%,89.5%,80.8%,and 98.7%,respectively.CAD-NBI showed superior accuracy and specificity than CAD-WLI(P=0.028 and P≤0.001,respectively),while CAD-WLI had higher sensitivity than CAD-NBI(P=0.006).By using both CAD-WLI and CAD-NBI,the endoscopists could improve their diagnostic efficacy to the highest level,with accuracy,sensitivity,and specificity of 94.9%,92.4%,and 96.7%,respectively.CONCLUSION The CAD-NBI system for screening early ESCC has higher accuracy and specificity than CAD-WLI.Endoscopists can achieve the best diagnostic efficacy using both CAD-WLI and CAD-NBI.

Relationship of sleep duration and annual changes in sleep duration with the incidence of gastrointestinal cancers:a prospective cohort study

Background:Prospective analyses have yet to identify a consistent relationship between sleep duration and the incidence of gastrointestinal(GI)cancers.The effect of changes in sleep duration on GI cancer incidence has scarcely been studied.Therefore,we aimed to examine the association between baseline sleep duration and annual changes in sleep duration and GI cancer risk in a large population-based cohort study.Methods:A total of 123,495 participants with baseline information and 83,511 participants with annual changes in sleep duration information were prospectively observed from 2006 to 2015 for cancer incidence.Cox proportional-hazards models were used to calculate hazard ratios(HRs)and their confidence intervals(CIs)for GI cancers according to sleep duration and annual changes in sleep duration.Results:In baseline sleep duration analyses,short sleep duration(≤5 h)was significantly associated with a lower risk of GI cancer in females(HR:0.31,95%CI:0.10-0.90),and a linear relationship between baseline sleep duration and GI cancer was observed(P=0.010),especially in males and in the>50-year-old group.In the annual changes in sleep duration analyses,with stable category(0 to-15 min/year)as the control group,decreased sleep duration(≤-15 min/year)was significantly associated with the development of GI cancer(HR:1.29;95%CI:1.04-1.61),especially in the>50-year-old group(HR:1.32;95%CI:1.01-1.71),and increased sleep duration(>0 min/year)was significantly associated with GI cancer in females(HR:2.89;95%CI:1.14-7.30).Conclusions:Both sleep duration and annual changes in sleep duration were associated with the incidence of GI cancer.

Monte Carlo Simulation on Layered Polymeric Films

Thin films of polymer blends composed of alternating copolymer, diblock copolymer and/or homopolymer are studied using Monte Carlo simulation. A multilayer morphology is observed in the film, that is, the blended polymers assemble into individual domains arranged from interior to the surfaces of the film. The coexisting components residing throughout the neighboring domains in the film make no distinguishable interface between any neighboring domains. By this means, it forms a vertical composition gradient in the polymeric film. Being different from layer-by-layer deposition of polyelectrolyte or hydrogen bonding approach etc., the layered structure in this study is formed by polymer blending in one step. Alternating copolymers are found to be essential components to form vertical composition gradient （layered structure） in thin films.