Ultrasound imaging has been widely used for preliminaryuddiagnosis as it is non-invasive and has good scope for theuddoctors to analyze many diseases. Lack of trained sonographersudmake ultrasound imaging diagnosis time consuming to detect anyudabnormality. Sometimes the problem cannot exactly be identifiedudwhich may lead to error in diagnosis. Hence in this paper weudpresent computer aided automatic detection of abnormality inudkidney on the ultrasound system itself, to decrease the time forudreports and not to depend on the sonographer. We classified theudkidney as normal and abnormal case. Segment the kidney regionudand extract Intensity histogram features and Haralick featuresudfrom Gray Level Cooccurnace Matrix (GLCM). These featuresudare calculated for a set of large data containing both normaludand abnormal cases. Abnormal case includes kidney stone, cystudand bacterial infection. Standard deviation for each parameter isudobserved, considered only those features with less deviation andudimplemented on FPGA Kintex board. If the range of mean valueudis 1.08 to 1.336, skewness is 2.882 to 7.708, Kurtosis is 1.06 toud71.152, Cluster Shade is 72 to 243, Homogeneity is 0.993 to 0.998,udthe observed kidney image is normal otherwise abnormal.
展开▼