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

<b><i>Background:</i></b> Pressurized myography is useful for the assessment of small artery structures and function. However, this procedure requires technical expertise for sample preparation and effort to choose an appropriate sized artery. In this study, we developed an automatic artery/vein differentiation and a size measurement system utilizing machine learning algorithms. <b><i>Methods and Results:</i></b> We used 654 independent mouse mesenteric artery images for model training. The model yielded an Intersection-over-Union of 0.744 ± 0.031 and a Dice coefficient of 0.881 ± 0.016. The vessel size and lumen size calculated from the predicted vessel contours demonstrated a strong linear correlation with manually determined vessel sizes (<i>R</i> = 0.722 ± 0.048, <i>p</i> &#x3c; 0.001 for vessel size and <i>R</i> = 0.908 ± 0.027, <i>p</i> &#x3c; 0.001 for lumen size). Last, we assessed the relation between the vessel size before and after dissection using a pressurized myography system. We observed a strong positive correlation between the wall/lumen ratio before dissection and the lumen expansion ratio (<i>R</i> = 0.832, <i>p</i> &#x3c; 0.01). Using multivariate binary logistic regression, 2 models estimating whether the vessel met the size criteria (lumen size of 160–240 μm) were generated with an area under the receiver operating characteristic curve of 0.761 for the upper limit and 0.747 for the lower limit. <b><i>Conclusion:</i></b> The U-Net-based image analysis method could streamline the experimental approach.