Noninvasive detection of hepatic lipidosis in dairy cows with calibrated ultrasonographic image analysis

摘要

The aim was to test the accuracy of calibrated digital analysis of ultrasonographic hepatic images for diagnosing fatty liver in dairy cows. Digital analysis was performed by means of a novel method, computer-aided ultrasound diagnosis (CAUS), previously published by the authors. This method implies a set of pre- and postprocessing steps to normalize and correct the tran-scutaneous ultrasonographic images. Transcutaneous hepatic ultrasonography was performed before surgical correction on 151 German Holstein dairy cows (mean ± standard error of the means; body weight: 571 ± 7 kg; age: 4.9 ± 0.2 yr; DIM: 35 ± 5) with left-sided abomasal displacement. Concentration of triacylglycerol (TAG) was biochemically determined in liver samples collected via biopsy and values were considered the gold standard to which ultrasound estimates were compared. According to histopathologic examination of biopsies, none of the cows suffered from hepatic disorders other than hepatic lipidosis. Hepatic TAG concentrations ranged from 4.6 to 292.4 mg/g of liver fresh weight (FW). High correlations were found between the hepatic TAG and mean echo level (r = 0.59) and residual attenuation (ResAtt; r = 0.80) obtained in ultrasonographic imaging. High correlation existed between ResAtt and mean echo level (r = 0.76). The 151 studied cows were split randomly into a training set of 76 cows and a test set of 75 cows. Based on the data from the training set, ResAtt was statistically selected by means of stepwise multiple regression analysis for hepatic TAG prediction (R~2 = 0.69). Then, using the predicted TAG data of the test set, receiver operating characteristic analysis was performed to summarize the accuracy and predictive potential of the differentiation between various mea-rnsured hepatic TAG values, based on TAG predicted from the regression formula. The area under the curve values of the receiver operating characteristic based on the regression equation were 0.94 (<50 vs. ≥50 mg of TAG/g of FW), 0.83 (<100 vs. ≥100 mg of TAG/g of FW), and 0.97 (<50 vs. ≥100 mg of TAG/g of FW). The CAUS methodology and software for digitally analyzing liver ultrasonographic images is considered feasible for noninvasive screening of fatty liver in dairy herd health programs. Using the single parameter linear regression equation might be ideal for practical applications.