A collaborative contour detector by gradient and active contours for ultrasound kidney images

ABSTRACT In the process of urinary system disease diagnosis, a complete kidney contour is crucial to estimate its size, area, volume and other properties. These properties can effectively help doctors diagnosis and prepare treatment plans. However, ultrasound images suffer from low signal-to-noise ratio, speckle, missing boundaries and other artefacts. Traditional contour detection algorithms can hardly extract a continuous and accurate kidney contour. To solve the problem, we propose a collaborative contour detector by gradient and active contour. It not only can make sure that the extracted contour is continuous and accurate but also is simple and suitable to use in practice. Both the simulated experiments and clinical experiments show that the proposed algorithm achieves a good performance in ultrasound kidney images and can effectively assist doctors in diagnosis.