In vivo assessment of subcutaneous fat in dogs by real-time ultrasonography and image analysis

Background: Systems for estimating body condition score (BCS) are currently used in canine practice to monitor fatness levels. These tools are cheap and easy to use but lack the necessary precision to monitor small changes in body fat, particularly during weight control treatments or in research. The present work aims to study the application of real-time ultrasonography (RTU) together with image analysis in the assessment of subcutaneous fat depots in dogs. Ultrasound images were collected from five anatomical locations (chest, flank, abdomen, thigh and lumbar) from 28 healthy dogs of different breeds and with a body weight (BW) ranging from 5.2 to 33.0 kg. BCS was collected by visual appraisal using a 5-point scale. Subcutaneous fat thickness (SFT) was estimated from RTU images, using the average of three measurements taken in fat deposits located above the muscles represented in each image. Correlations were established between SFT and BW or BCS as well as a classification of BCS-based fatness [overweight (BCS = 4), ideal (BCS = 3) and lean (BCS = 2)]. Results: SFT was found to differ between the five regions considered (P < 0.001). Abdomen and thigh were the areas displaying the widest variation for the different dogs included in the study and also those correlating most with BW, in contrast to the chest, which showed the least variation. Overall, a strong correlation was found between BCS and SFT. The highest correlations were established for the flank, abdomen and lumbar areas. In every anatomical area, a decrease in SFT was observed across all three BCS classes, ranging from 48 to 65 % among overweight and ideal dogs, and from 46 to 83 % among ideal and lean dogs. Conclusions: Preliminary data showed that within this population there was a strong correlation between BCS and SFT estimated from RTU images. It was also observed that RTU measurements for fat thickness differed among the anatomical points surveyed suggesting differences in their sensitivity to a change in BCS. The images displaying the best prediction value for fatness variations were those collected at the lumbar and abdomen areas.