Venous gas emboli (VGE) are bubbles that are seen circulating in the blood of some divers for several hours postdive using ultrasound. Larger and more numerous VGE are statistically associated with a higher risk of decompression sickness (DCS), but the relationship is not a direct one. Differences in VGE and DCS risk have been documented among individuals and in the same individual — even with identical dives. Importantly, VGE evolution postdive varies dramatically, so getting frequent measurements may be important for understanding the influence of VGE on other physiological mechanisms in diving. Toward this goal, researchers at UNC are working on obtaining thousands of ultrasound recordings to be used in refining automated algorithms for VGE detection.
Venous gas emboli (VGE) are bubbles that grow from dissolved nitrogen that is present in the tissues when a diver ascends. VGE are detectable using ultrasound imaging, especially in echocardiography (ultrasound imaging of the heart), where they appear as bright spots circulating in the venous heart chambers. In diving research, the videos of the bubbles flowing through the heart are then analyzed by trained graders who score the bubbling on a severity scale that correlates it to the risk of DCS. An alternative assessment based on manual bubble counting is more reproducible and easier to learn for non-medically trained people and offers advantages for computer automation. One major drawback to this method in widespread use in decompression research, however, is that it is time-consuming.
In this study, we are developing an online application for the public to use for manual counting of venous gas emboli in echocardiograms. This web tool will allow volunteers to aid in our collection of fully counted echocardiograms, which will help us build machine-learning algorithms to automate this task in the future. An automated method for VGE counting would facilitate the speed of decompression research in the field and improve our understanding of how these bubbles are related to decompression sickness.