Computer Aided Diagnosis System for Stone Detection and Early Detection of Kidney Stones | Science Publications

Journal of Computer Science

Dr. P. Thangaraj¹  Ms. P.R. Tamilselvi¹ 

关键词: Ultrasound images;    kidney stones;    early detection;    image segmentation;    Seeded Region Growing (SRG);    stone detection;    Intensity threshold;   

DOI  :  10.3844/jcssp.2011.250.254

学科分类：计算机科学（综合）

来源: Science Publications

【 摘 要 】

Problem statement: Most of the previous study in diagnosis of kidney stone identifies amere presence or absence of the stones in the kidney. However proposal in our study even present anearly detection of kidney stones which helps to change the diet conditions and prevent the formation ofstones. Approach: The study presented a scheme for ultrasound kidney image diagnosis for stone andits early detection based on improved seeded region growing based segmentation and classification ofkidney images with stone sizes. With segmented portions of the images the intensity thresholdvariation helps in identifying multiple classes to classify the images as normal, stone and early stonestages. The improved semiautomatic Seeded Region Growing (SRG) based image segmentationprocess homogeneous region depends on the image granularity features, where the interested structureswith dimensions comparable to the speckle size are extracted. The shape and size of the growingregions depend on this look up table entries. The region merging after the region growing alsosuppresses the high frequency artifacts. The diagnosis process is done based on the intensity thresholdvariation obtained from the segmented portions of the image and size of the portions compared to thatof the standard stone sizes (less than 2 mm absence of stone, 2-4 mm early stages and 5mm and abovepresence of kidney stones). Results: The parameters of texture values, intensity threshold variation andstones sizes are evaluated with experimentation of various Ultrasound kidney image samples takenfrom the clinical laboratory. The texture extracted from the segmented portion of the kidney imagespresented in our study precisely estimate the size of the stones and the position of the stones in thekidney which was not done in the earlier studies. Conclusion: The integrated improved SRG andclassification mechanisms presented in this study diagnosis the kidney stones presence and absencealong with the early stages of stone formation.

【 授权许可】

Unknown