Search

Video laryngoscopy is an important diagnostic tool for head and neck cancers. The artificial intelligence (AI) system has been shown to monitor blind spots during esophagogastroduodenoscopy. This study aimed to test the performance of AI-driven intelligent laryngoscopy monitoring assistant (ILMA) for landmark anatomical sites identification on laryngoscopic images and videos based on a convolutional neural network (CNN).The laryngoscopic images taken from January to December 2018 were retrospectively collected, and ILMA was developed using the CNN model of Inception-ResNet-v2 + Squeeze-and-Excitation Networks (SENet). A total of 16,000 laryngoscopic images were used for training. These were assigned to 20 landmark anatomical sites covering six major head and neck regions. In addition, the performance of ILMA in identifying anatomical sites was validated using 4000 laryngoscopic images and 25 videos provided by five other tertiary hospitals.ILMA identified the 20 anatomical sites on the laryngoscopic images with a total accuracy of 97.60 %, and the average sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were 100 %, 99.87 %, 97.65 %, and 99.87 %, respectively. In addition, multicenter clinical verification displayed that the accuracy of ILMA in identifying the 20 targeted anatomical sites in 25 laryngoscopic videos from five hospitals was ≥95 %.The proposed CNN-based ILMA model can rapidly and accurately identify the anatomical sites on laryngoscopic images. The model can reflect the coverage of anatomical regions of the head and neck by laryngoscopy, showing application potential in improving the quality of laryngoscopy.

As a typical endocrine disruptor, bisphenol A (BPA) has been widely detected in various water bodies. Although the influence of BPA on traditional biological treatment system has been investigated, it is not clear whether it has potential impact on anaerobic ammonium oxidation (anammox) process. The short- and long-term influences of BPA on reactor operational performance, sludge characteristics and microbial community were investigated in this study. Results revealed that 1 and 3 mg L

Analysis about contents and distributions of heavy metal elements in soil is one of the primary matters in surveying geochemical environmental quality in Rizhao tea-planting areas. By using 1km×1km sampling data of surface soil in Rizhao tea-planting areas, Geostatistics method is adopted to analyze spatial distribution of heavy metal elements, and nemerow synthetic index method is adopted to assess environmental qualities of heavy metals and show the result out by Kriging interpolation. The assessment results are as follows: the distribution of all the heavy metals besides Cd, Pb is comparatively uniformity; From the result of the single pollution index, the gross part of research areas is clean, only Cd, Ni pollution existed in finitude areas; From the spatial distribution of nemerow synthetic pollution index, 88.41% of the research areas soil belongs to level I, and 6.44% belongs to level II, and 5.14% level III, while no area belongs to level IV and level V.

This paper shows the difficulties of the dwellings’ sustainable development in mountain areas on the basis of the fast pace of urbanization and the development of the dwellings in China, in terms of environmental resources, spatial form, regional culture and construction technologies. Then this paper analyzes the application possibilities of BIM on the sustainable dwellings in mountain areas through the discussion of the correlation between BIM and Sustainable Architecture, and proposes the research ideas of design methods.

This paper proposes a scheme of building in single chip microcomputer laboratory based on Proteus software simulation, Protel software to make PCB card. It proves the feasibility of scheme by analyzing some application examples. This scheme solves the problems of capital shortage for traditional single chip labs and difficulty in equipment maintenance to a certain extent.

This paper presents a new non-unit voltage protection algorithm for extra high voltage (EHV) transmission lines. This scheme is developed using wavelet analysis, in which the singularity of fault transient voltage signals in one terminal is utilized to discriminate clearly between internal and external faults. Lipschitz exponent (LE) is obtained from wavelet modulus maximum to detect singularity of signals. A typical 500-kV EHV transmission system has been simulated by ATP to evaluate the scheme. The simulation results show that this scheme is capable of providing correct responses under various system configurations and fault conditions