Reconstruction of X-ray images
We have presented an integrated approach in retrieving, reconstructing, and storing images obtained from noisy X-rays in this study. The X-ray images are used to detect human body's invisible parts. The problem of blurring and uneven illumination is always faced. Although it is partially solved by the physicians via lighting the X-rays, this method is not working properly in some cases such as Vesico Ureteral Reflux disease. This may cause loss of some meaningful part of the information and failure in diagnosis process. In order to decrease such errors, some computational methods has been developed by means of image processing. Due to its very nature, reconstruction, retrieving and registration of x-ray images has been chosen as a subject of this study. We have begun attacking the problem of reconstruction and extraction, then started to generate multi-layer hierarchical solutions. We have tried so many different approaches for each layer in our experiments. In each experiment, some methods produced accurate results, some methods did not. Thus, we have exerted every effort to optimize the solution for each layer. Although we have worked with limited number of sample images,(due to the problem of retrieving x-rays which is seen in this case) the results show us that, all the samples that we have processed, could have been reconstructed and stored as we have expected.Storing of the huge amount of data is an another problem in our area of interest, because of image characteristics. Every kidney image consists of nearly 120.000 (around 300x400) pixels. However, in our case, the boundaries of kidney region are sufficient for diagnosis. In other words, storing the boundaries instead of complete image has the same precision. We detected and stored the kidney's boundary coordinates on both x and y axis. Although this was sufficient for our study, we have decided to develop a much more flexible file format by ordering x and y coordinate couples in counter clockwise direction with the same information for further studies such as computer aided diagnosis systems.