Fully Automated Cyst Segmentation in Ultrasound Images of Kidney

A. Eslami, M. Jahed, and M. Naroienejad (Iran)


Snake, Modified GGVF, Wavelet, Gibbs probability func tion.


Cyst is one of the most common lesions in kidney and ul trasound imaging is appropriate tool for detecting these le sions. This study develops an automated approach for cyst segmentation in kidney's ultrasound images. The approach includes three steps: initially, ultrasound image is trans formed under a special function derived from Gibbs joint probability function. This transform suppresses noise and discriminates cyst and other tissues. Next, transformed im age is decomposed to its low resolution component. Seg mentation, morphological operations and coarse boundary detection (performed in low resolution) determines the ini tial contour employed in the final step. In last step, precise edge detection is performed in unity resolution using active contours model. Proposed approach is designed such that it overcomes noise, imaging artifacts and handles multi cyst cases. Coarse segmentation and then fine boundary extrac tion is an efficient scheme since segmentation is performed in low resolution (where SNR is relatively high) and lesion boundary is extracted precisely in high resolution (where details available).

Important Links:

Go Back