No detailed descriptions exist of the collateral intercostal artery which can provide an accurate anatomical basis for ensuring a low rate of vascular complications during thoracocentesis and thoracoscopy. Consequently the present study was undertaken to provide information on the origin, size and topographic relationships of the collateral intercostal artery. Ninety cadaveric adult intercostal spaces were dissected using standard procedures. The collateral intercostal arteries were exposed throughout their full length and measured at the points within the intercostal spaces considered to be the most important for clinical purposes. The posterior intercostal arteries and their collateral branches were observed to decrease in size from posterior to anterior; however, no significant differences were present in their size in the first four intercostal spaces. Based on these findings the usual thoracocentesis or thoracoscopy technique, in which it is recommended that puncture is done as close as possible to the superior margin of the inferior rib, may lead to collateral intercostal artery laceration and considerable bleeding. A subtle, but important, modification to this technique is suggested aimed at achieving safer access to the intercostal space. In the modified technique, the puncture should be made in the middle of the intercostal space, thereby reducing the possibility of laceration of the collateral intercostal artery.
sensitivity, specificity and global accuracy at different score thresholds. Results Image processing speed by the algorithm was 33 ms/ image. This is much faster than the average human visual response latency which is estimated at 70-100 ms. The algorithm was able to detect Barrett's neoplasia with sensitivity of 93%, specificity of 78% and global accuracy of 83% (see figure (1) below for examples of algorithm detection). Conclusions We developed and validated an early AI algorithm with high sensitivity and reasonable specificity when compared with PIVI criteria. The ultra short image processing time would suggest this algorithm may be suitable for real time detection of Barrett's neoplasia. We will develop this model further for use during real time endoscopy.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.