RESUMEN
In recent years, the development of portable microscopy devices that enable the noninvasive bedside evaluation of the mucosal microcirculation in critically ill patients has expanded the research on this level of the cardiovascular system. Several semi-quantitative scores have been defined to assess the peripheral perfusion, based on videos of the microcirculation. However, they are cumbersome and time-consuming processes, highlighting the need for the development of automated software techniques, to reduce physicians workload and ensure prompt and objective patient evaluation. We developed a rapid, automatic method for the quantitative assessment of erythrocyte velocities in Incident Dark Field (IDF) illumination videos of capillary flow. The technique, based on Kalman filter object tracking, was tested in 35 IDF videos against space-time diagrams, showing high correlation (r = 0.96) and agreement (bias = 3.3 µm/s) with space-time diagrams (STD), below 200 µm/s.