Automated Detection and Diameter Estimation for Mouse Mesenteric Artery using Semantic Segmentation

Abstract

BackgroundPressurized myography is useful for the assessment of small artery structure and function, and widely used in the field of cardiovascular research. However, this procedure requires technical expertise for the sample preparation and effort to choose an appropriate size of artery. In this study we sought to develop an automatic artery-vein differentiation and size measurement system utilizing the U-Net-based machine learning algorithms. Methods and ResultsWe used 654 independent mesenteric artery images from 59 mice for the model training and validation. Our segmentation model yielded 0.744 {+/-}0.031 in IoU and 0.881 {+/-}0.016 in Dice coefficient with 5-fold cross validation. The vessel size and the lumen size calculated from the predicted vessel contours demonstrated a strong linear correlation with the manually determined vessel sizes (R = 0.722 {+/-}0.048, p<0.001 for vessel size and R = 0.908 {+/-}0.027, p<0.001 for lumen size). Lastly, we assessed the relation between the vessel size before and after dissection using pressurized myography system. We observed a strong positive correlation between the wall/lumen ratio before dissection and the lumen expansion ratio (R2 = 0.671, p<0.01). Using multivariate binary logistic regression, two models estimating whether the vessel met the size criteria (lumen size of 160 to 240 m) were generated with area under the ROC curve of 0.761 for the upper limit and 0.747 for the lower limit. ConclusionOur novel image analysis method with U-Net could streamline the experimental approach and may facilitate cardiovascular research.