Analysis of Kidney stone Detection by Reaction diffusion Level Set Segmentation and Xilinx System Generator
Kotapati Kasi Viswanath, Ramalingam Gunasundari, Syed Aathif Hussain · 2015
The abnormalities of the kidney can be identified by ultrasound imaging has structural abnormalities like kidney swelling, change in its position appearance, formation of stones, cysts, cancerous cells, congenital anomalies and blockage of urine etc. For surgical operations it is very important to identify the exact and accurate location of stone in the kidney. The ultrasound images are of low contrast and contain speckle noise. This makes the detection of kidney abnormalities rather challenging task. Thus preprocessing of ultrasound images is carried out on Xilinx System generator (XSG) and implemented on Vertex-5 (XC5VLX50T) FPGA to remove speckle noise. In preprocessing, first image restoration is done to reduce speckle noise then it is applied to Gabor filter for smoothening. Next the resultant image is enhanced using convolution. The preprocessed ultrasound image is segmented using reaction diffusion (RD) level set segmentation (LSS), since it yields better results. it uses a two-step splitting methods to iteratively solve the RD-LSS equation, first step is iterating LSS equation, and then solving the diffusion equation. The second step is to regularize the level set function which is the obtained from first step for better stability. The RD is included for LSS for eliminating of anti-leakages on image boundary. The RD-LSS does not require any expensive re-initialization and it is very high speed of operation. The RD-LSS results are compared with distance regularized level set evolution (DRLSE1), DRLSE1 and DRLSE2. Extracted region of the kidney after segmentation is applied to Symlets, Biorthogonal (bio3.7, bio3.9 & bio4.4) and Daubechies wavelet subbands to extract energy levels. These energy level gives an indication about presence of stone in that particular location which significantly vary from that of normal energy level. These energy levels are trained by Multilayer Perceptron (MLP) and Back Propagation (BP) ANN to identify the type of stone with an accuracy of 99.1%.