An Image Processing Method for Kidney Stone Segmentation in CT Scan image
Abstract : This paper presents a technique for detection of kidney stones through different steps of image processing. The first step is the image pre-processing using filters in which image gets smoothed as well as the noise is removed from the image. Image enhancement is a part of preprocessing which is used to enhance the image which is achieved with power law transformation. Next, the image segmentation is performed on the preprocessed image using thresholding technique. The imaging modality used is CT because it has low noise compared to other modalities such as x-ray and ultrasound.
The kidney malfunctioning can be life intimidating. Hence early detection of kidney stone is essential. Precise identification of kidney stone is vital in order to ensure surgical operations success. The ultrasound images of kidney comprise speckle noise and are of low contrast which makes the identification of kidney abnormalities a difficult task. As a result, the doctors may find identification of small stones and the type is difficult and challenging for identify the small kidney stones and their type appropriately. To address this issue, a reaction diffusion level set segmentation is proposed to identify location of the stone; it is implemented in real time on Vertex-2Pro FPGA with Virology HDL using Xilinx System Generator blocks from Mat lab 2012a which is compatible with xilinx13.4 ISE and lifting scheme wavelets sub bands are employed for extraction of the energy levels of the stone. The results are analyzed using MLP-BP ANN algorithms for classification and its type of stone.
The clarity of segmented output is fail in some case.
Segmentation based on the selected slice, Remaining false positive in the segmented output.
Still containing unwanted regions in the output result. In the case of the irregular height abdomen, the program impossible to provide the correct result.
Segmentation accuracy was relatively low.
We propose an efficient image-driven method for the automatic segmentation of the heart from CT scans. The methodology relies on image processing techniques such as multi-thresholding based on statistical local and global features, mathematical morphology, or image filtering, but it also exploits the available prior knowledge about the cardiac structures involved. The development of such a segmentation system comprises two major tasks: initially, a pre-processing stage in which the region of interest (ROI) is delimited and the statistical parameters are computed; and next, the segmentation procedure itself, which makes use of the data obtained during the previous stage. Our fully automatic approach improves on the state of the art through both computation speed and simplicity of implementation.
Detect in initial stage
High accuracy
Low complexity
To detect the size and location of the stone with low execution time.
|