Augmented-reality-based surgical navigation for endoscope retrograde cholangiopancreatography: A phantom study.

BACKGROUND: Endoscope retrograde cholangiopancreatography is a standard surgical treatment for gallbladder and pancreatic diseases. However, surgeons is at high risk and require sufficient surgical experience and skills. METHODS: (1) The simultaneous localisation and mapping technique to reconstruct the surgical environment. (2) The preoperative 3D model is transformed into the intraoperative video environment to implement the multi-modal fusion. (3) A framework for virtual-to-real projection based on hand-eye alignment. For the purpose of projecting the 3D model onto the imaging plane of the camera, it uses position data from electromagnetic sensors. RESULTS: Our AR-assisted navigation system can accurately guide physicians, which means a distance of registration error to be restricted to under 5 mm and a projection error of 5.76 ± 2.13, and the intubation procedure is done at 30 frames per second. CONCLUSIONS: Coupled with clinical validation and user studies, both the quantitative and qualitative results indicate that our navigation system has the potential to be highly useful in clinical practice.

City-Wide Traffic Flow Forecasting Using a Deep Convolutional Neural Network.

City-wide traffic flow forecasting is a significant function of the Intelligent Transport System (ITS), which plays an important role in city traffic management and public travel safety. However, this remains a very challenging task that is affected by many complex factors, such as road network distribution and external factors (e.g., weather, accidents, and holidays). In this paper, we propose a deep-learning-based multi-branch model called TFFNet (Traffic Flow Forecasting Network) to forecast the short-term traffic status (flow) throughout a city. The model uses spatiotemporal traffic flow matrices and external factors as its input and then infers and outputs the future short-term traffic status (flow) of the whole road network. For modelling the spatial correlations of the traffic flows between current and adjacent road segments, we employ a multi-layer fully convolutional framework to perform cross-correlation calculation and extract the hierarchical spatial dependencies from local to global scales. Also, we extract the temporal closeness and periodicity of traffic flow from historical observations by constructing a high-dimensional tensor comprised of traffic flow matrices from three fragments of the time axis: recent time, near history, and distant history. External factors are also considered and trained with a fully connected neural network and then fused with the output of the main component of TFFNet. The multi-branch model is automatically trained to fit complex patterns hidden in the traffic flow matrices until reaching pre-defined convergent criteria via the back-propagation method. By constructing a rational model input and network architecture, TFFNet can capture spatial and temporal dependencies simultaneously from traffic flow matrices during model training and outperforms other typical traffic flow forecasting methods in the experimental dataset.

Microbial production of cis-1,2-dihydroxy-cyclohexa-3,5-diene-1-carboxylate by genetically modified Pseudomonas putida.

Arene cis-diols are interesting chemicals because of their chiral structures and great potentials in industrial synthesis of useful chiral chemical products. Pseudomonas putida KT2442 was genetically modified to transform benzoic acid (benzoate) to 1,2-dihydroxy-cyclohexa-3,5-diene-1-carboxylic acid (DHCDC) or named benzoate cis-diol. BenD gene encoding cis-diol dehydrogenase was deleted to generate a mutant named P. putida KTSY01. Genes benABC encoding benzoate dioxygenase were cloned into plasmid pSYM01 and overexpressed in P. putida KTSY01. The recombinant bacteria P. putida KTSY01 (pSYM01) showed strong ability to transform benzoate to DHCDC. DHCDC of 2.3 g/L was obtained with a yield of 73% after 24 h of cultivation in shake flasks incubated under optimized growth conditions. Transformation of benzoate carried out in a 6-L fermentor using a benzoate fed-batch process produced over 17 g/L DHCDC after 48 h of fermentation. The average DHCDC production rate was 0.356 g L(-1) h(-1). DHCDC purified from the fermentation broth showed a purity of more than 95%, and its chemical structure was confirmed by nuclear magnetic resonance.

Genetic engineering of Pseudomonas putida KT2442 for biotransformation of aromatic compounds to chiral cis-diols.

Toluene dioxygenase (TDO) catalyzes asymmetric cis-dihydroxylations of aromatic compounds. Pseudomonas putida KT2442 (pSPM01) harboring TDO genes could effectively biotransform a wide-range of aromatic substrates into their cis-diols products. In shake-flask culture, approximately 2.7gl(-1) benzene cis-diols, 8.8gl(-1) toluene cis-diols and 6.0gl(-1) chlorobenzene cis-diols were obtained from the biotransformation process. Furthermore, vgb gene encoding Vitreoscilla hemoglobin protein (VHb) which enhances oxygen microbial utilization rate under low dissolved oxygen concentration was integrated into P. putida KT2442 genome. The oxidation ability of the mutant strain P. putida KTOY02 (pSPM01) harboring TDO gene was increased in the presence of VHb protein. As a result, approximately 3.8, 15.1 or 6.8gl(-1) different cis-diols production was achieved in P. putida KTOY02 (pSPM01) grown in shake-flasks when benzene, toluene or chlorobenzene was used as the substrate. The above results indicate that P. putida KT2442 could be used as a cell factory to biotransform aromatic compounds.

Microbial transformation of benzene to cis-3,5-cyclohexadien-1,2-diols by recombinant bacteria harboring toluene dioxygenase gene tod.

Toluene dioxygenase (TDO) catalyzes asymmetric cis-dihydroxylation of aromatic compounds. To achieve high efficient biotransformation of benzene to benzene cis-diols, Pseudomonas putida KT2442, Pseudomonas stutzeri 1317, and Aeromonas hydrophila 4AK4 were used as hosts to express TDO gene tod. Plasmid pSPM01, a derivative of broad-host plasmid pBBR1MCS-2 harboring tod from plasmid pKST11, was constructed and introduced into the above three strains. Their abilities to catalyze the biotransformation of benzene to benzene cis-diols, namely, cis-3,5-cyclohexadien-1,2-diols abbreviated as DHCD, were examined. In shake-flask cultivation under optimized culture media and growth condition, benzene cis-diols production by recombinant P. putida KT2442 (pSPM01), P. stutzeri 1317 (pSPM01), and A. hydrophila 4AK4 (pSPM01) were 2.68, 2.13, and 1.17 g/l, respectively. In comparison, Escherichia coli JM109 (pSPM01) and E. coli JM109 (pKST11) produced 0.45 and 0.53 g/l of DHCD, respectively. When biotransformation was run in a 6-l fermenter, DHCD production in P. putida KT2442 (pSPM01) was approximately 60 g/l; this is the highest DHCD production yield reported so far.