Label-free prediction of vascular connectivity in perfused microvascular networks in vitro.

Background And Objective: Continuous monitoring and in-situ assessment of microvascular connectivity have significant implications for culturing vascularized organoids and optimizing the therapeutic strategies. However, commonly used methods for vascular connectivity assessment heavily rely on fluorescent labels that may either raise biocompatibility concerns or interrupt the normal cell growth process. This study provides a new avenue for label-free and continuous assessment of organoid or tumor vascularization in vitro.

Methods: To address this issue, a Vessel Connectivity Network (VC-Net) was developed for label-free assessment of vascular connectivity. To validate the VC-Net, microvascular networks (MVNs) were cultured in vitro and their microscopic images were acquired at different culturing conditions as a training dataset. The VC-Net employs a Vessel Queue Contrastive Learning (VQCL) method and a class imbalance algorithm to address the issues of limited sample size, indistinctive class features and imbalanced class distribution in the dataset. The VC-Net successfully evaluated the vascular connectivity with no significant deviation from that by fluorescence imaging.

Results: The proposed VC-Net successfully differentiated the connectivity characteristics between normal and tumor-related MVNs. Without damaging the culture system, the platform predicts MVNs connectivity with a Dice of the best 0.811. In comparison with those cultured in the regular microenvironment, the averaged connectivity of MVNs cultured in the tumorrelated microenvironment decreased by 30.8%, whereas the non connectivity area increased by 37.3%.

Conclusions: This method solves the problem of limited sample size caused by unclear class features, imbalanced class distribution, and high experimental costs in MVNs connectivity datasets. VC-Net has been proven to be an unlabeled and effective method for identifying vascular connectivity.