Digital labeling for 3D histology: segmenting blood vessels without a vascular contrast agent using deep learning

Imaging the microstructure of the arterial wall - ex vivo to in vivo potential

Microstructural imaging enables researchers to visualise changes in the arterial wall, allowing for (i) a deeper understanding of the role of specific components in arterial mechanics, (ii) the observation of cellular responses, (iii) insights into pathological alterations in tissue microstructure, and/or (iv) advancements in tissue engineering aimed at replicating healthy native tissue. In this prospective review, we present various imaging modalities spanning from ex vivo to in vivo applications within arterial tissue. The pros, cons, and sensitivities of these modalities are highlighted. By consolidating the latest advancements in microstructural imaging of arterial tissue, the authors aim for this paper to serve as a guide for researchers designing experiments at various stages. Furthermore, the integration of non-invasive, non-destructive imaging techniques into studies provides an additional layer of microstructural information, enhancing scientific findings, improving our understanding of disease, and potentially enabling earlier or more effective diagnostic capabilities. STATEMENT OF SIGNIFICANCE: Imaging the specific microstructural components of the arterial wall provides critical insights into vascular biology, mechanics, and pathology. It enables the visualisation of key structural components and their roles in arterial function, supports the analysis of cell-matrix interactions, and reveals microarchitectural changes associated with disease progression. This level of specificity also informs the design of biomimetic materials and scaffolds in tissue engineering, facilitating the replication of native arterial properties. By synthesising recent developments in microstructural imaging techniques, this paper serves as a reference for investigators designing experiments across a range of vascular research applications. Moreover, the incorporation of non-invasive, non-destructive imaging methods offers a means to acquire detailed microstructural data without compromising tissue integrity. This enhances the interpretability and translational potential of findings, deepens our understanding of vascular disease mechanisms, and may ultimately contribute to the development of earlier and more precise diagnostic approaches.

A Simple and Fast Optical Clearing Method for Whole-Mount Fluorescence In Situ Hybridization (FISH) Imaging

We report a single-step optical clearing method that is compatible with RNA fluorescence in situ hybridization (FISH) imaging. We previously demonstrated microscopy imaging with immunohistochemistry and genetic reporters using a technique called lipid-preserving refractive index matching for prolonged imaging depth (LIMPID). Our protocol reliably produces high-resolution three-dimensional (3D) images with minimal aberrations using high magnification objectives, captures large field-of-view images of whole-mount tissues, and supports co-labeling with antibody and FISH probes. We also custom-designed FISH probes for quail embryos, demonstrating the ease of fabricating probes for use with less common animal models. Furthermore, we show high-quality 3D images using a conventional fluorescence microscope, without using more advanced depth sectioning instruments such as confocal or light-sheet microscopy. For broader adoption, we simplified and optimized 3D-LIMPID-FISH to minimize the barrier to entry, and we provide a detailed protocol to aid users with navigating the thick and thin of 3D microscopy.

ML-driven segmentation of microvascular features during histological examination of tissue-engineered vascular grafts

Introduction

The development of next-generation tissue-engineered medical devices such as tissue-engineered vascular grafts (TEVGs) is a leading trend in translational medicine. Microscopic examination is an indispensable part of animal experimentation, and histopathological analysis of regenerated tissue is crucial for assessing the outcomes of implanted medical devices. However, the objective quantification of regenerated tissues can be challenging due to their unusual and complex architecture. To address these challenges, research and development of advanced ML-driven tools for performing adequate histological analysis appears to be an extremely promising direction.

Methods

We compiled a dataset of 104 representative whole slide images (WSIs) of TEVGs which were collected after a 6-month implantation into the sheep carotid artery. The histological examination aimed to analyze the patterns of vascular tissue regeneration in TEVGs in situ. Having performed an automated slicing of these WSIs by the Entropy Masker algorithm, we filtered and then manually annotated 1,401 patches to identify 9 histological features: arteriole lumen, arteriole media, arteriole adventitia, venule lumen, venule wall, capillary lumen, capillary wall, immune cells, and nerve trunks. To segment and quantify these features, we rigorously tuned and evaluated the performance of six deep learning models (U-Net, LinkNet, FPN, PSPNet, DeepLabV3, and MA-Net).

Results

After rigorous hyperparameter optimization, all six deep learning models achieved mean Dice Similarity Coefficients (DSC) exceeding 0.823. Notably, FPN and PSPNet exhibited the fastest convergence rates. MA-Net stood out with the highest mean DSC of 0.875, demonstrating superior performance in arteriole segmentation. DeepLabV3 performed well in segmenting venous and capillary structures, while FPN exhibited proficiency in identifying immune cells and nerve trunks. An ensemble of these three models attained an average DSC of 0.889, surpassing their individual performances.

Conclusion

This study showcases the potential of ML-driven segmentation in the analysis of histological images of tissue-engineered vascular grafts. Through the creation of a unique dataset and the optimization of deep neural network hyperparameters, we developed and validated an ensemble model, establishing an effective tool for detecting key histological features essential for understanding vascular tissue regeneration. These advances herald a significant improvement in ML-assisted workflows for tissue engineering research and development.

Deep learning-based vessel extraction in 3D confocal microscope images of cleared human glioma tissues

Comprehensive visualization and accurate extraction of tumor vasculature are essential to study the nature of glioma. Nowadays, tissue clearing technology enables 3D visualization of human glioma vasculature at micron resolution, but current vessel extraction schemes cannot well cope with the extraction of complex tumor vessels with high disruption and irregularity under realistic conditions. Here, we developed a framework, FineVess, based on deep learning to automatically extract glioma vessels in confocal microscope images of cleared human tumor tissues. In the framework, a customized deep learning network, named 3D ResCBAM nnU-Net, was designed to segment the vessels, and a novel pipeline based on preprocessing and post-processing was developed to refine the segmentation results automatically. On the basis of its application to a practical dataset, we showed that the FineVess enabled extraction of variable and incomplete vessels with high accuracy in challenging 3D images, better than other traditional and state-of-the-art schemes. For the extracted vessels, we calculated vascular morphological features including fractal dimension and vascular wall integrity of different tumor grades, and verified the vascular heterogeneity through quantitative analysis.