Label-free Prediction of Vascular Connectivity in Perfused Microvascular Networks in vitro

2025-02-25

AI Summary

Current microvascular connectivity assessment relies on fluorescent labeling, posing biocompatibility risks and perturbing physiological processes. To address this, we propose a label-free, real-time connectivity evaluation method for *in vitro* perfused microvascular networks (MVNs). We introduce the Vessel Queue Contrastive Learning (VQCL) framework—a novel integration of contrastive learning and class-imbalance optimization—designed to overcome challenges of limited samples, ambiguous feature representations, and skewed label distributions. Experimental validation demonstrates that our method achieves performance statistically indistinguishable from fluorescence-based ground truth (*p* > 0.05). It successfully discriminates between normative and tumor-associated MVNs, quantitatively revealing a 30.8% reduction in vascular connectivity and a 37.3% expansion of non-perfused regions in the latter. This work provides a generalizable, non-invasive analytical tool for organoid vascularization studies and mechanistic investigations of the tumor microenvironment.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Calibration & Uncertainty Quantification
• Search and Optimization: Evaluation and Analysis

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

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. 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. In addition, the proposed VC-Net successfully differentiated the connectivity characteristics between normal and tumor-related MVNs. In comparison with those cultured in the regular microenvironment, the averaged connectivity of MVNs cultured in the tumor-related microenvironment decreased by 30.8%, whereas the non-connected area increased by 37.3%. This study provides a new avenue for label-free and continuous assessment of organoid or tumor vascularization in vitro.

Problem

• Label-free vascular connectivity assessment
• Overcoming fluorescent label limitations
• Differentiating normal and tumor-related microvascular networks

Innovation

• Label-free vascular connectivity assessment
• Vessel Queue Contrastive Learning method
• Class imbalance algorithm application