Ultra Wideband radar system for bladder monitoring applications

The aim of this study is to address the management of urinary problems by detecting changes in the volume of urine within the human bladder using low cost, low power, wearable Ultra Wideband (UWB) sensors and signal processing techniques. The paper describes experiments on the classification of six three-layer dielectrically representative bladder phantoms, mimicking a range of muscle and bladder wall-to-wall distances. The process involves the illumination of the bladder with a UWB pulse. Due to the dielectric contrast between urine and bladder wall tissue at microwave frequencies, an electromagnetic reflection is generated at both the anterior and posterior bladder wall. These reflections are recorded, the salient features are extracted and processed by a classification algorithm to estimate the volume of urine present in the bladder. To evaluate the prototype system, a number of physical bladder phantoms were constructed, each mimicking bladders of different volumes. Principal Component Analysis (PCA) was applied and the processed features were classified by a K-Nearest Neighbour learning algorithm to estimate the state of the bladder (small, medium or full). The paper describes the bladder phantom prototype systems and the experimental setup. Results illustrate detection of phantom bladder states with an accuracy of up to 91%.