AV-casNet: Fully Automatic Arteriole-Venule Segmentation and Differentiation in OCT Angiography.

Automatic segmentation and differentiation of retinal arteriole and venule (AV), defined as small blood vessels directly before and after the capillary plexus, are of great importance for the diagnosis of various eye diseases and systemic diseases, such as diabetic retinopathy, hypertension, and cardiovascular diseases. Optical coherence tomography angiography (OCTA) is a recent imaging modality that provides capillary-level blood flow information. However, OCTA does not have the colorimetric and geometric differences between AV as the fundus photography does. Various methods have been proposed to differentiate AV in OCTA, which typically needs the guidance of other imaging modalities. In this study, we propose a cascaded neural network to automatically segment and differentiate AV solely based on OCTA. A convolutional neural network (CNN) module is first applied to generate an initial segmentation, followed by a graph neural network (GNN) to improve the connectivity of the initial segmentation. Various CNN and GNN architectures are employed and compared. The proposed method is evaluated on multi-center clinical datasets, including 3 ×3 mm2 and 6 ×6 mm2 OCTA. The proposed method holds the potential to enrich OCTA image information for the diagnosis of various diseases.

CellVisioner: A Generalizable Cell Virtual Staining Toolbox based on Few-Shot Transfer Learning for Mechanobiological Analysis.

Visualizing cellular structures especially the cytoskeleton and the nucleus is crucial for understanding mechanobiology, but traditional fluorescence staining has inherent limitations such as phototoxicity and photobleaching. Virtual staining techniques provide an alternative approach to addressing these issues but often require substantial amount of user training data. In this study, we develop a generalizable cell virtual staining toolbox (termed CellVisioner) based on few-shot transfer learning that requires substantially reduced user training data. CellVisioner can virtually stain F-actin and nuclei for various types of cells and extract single-cell parameters relevant to mechanobiology research. Taking the label-free single-cell images as input, CellVisioner can predict cell mechanobiological status (e.g., Yes-associated protein nuclear/cytoplasmic ratio) and perform long-term monitoring for living cells. We envision that CellVisioner would be a powerful tool to facilitate on-site mechanobiological research.

Fabrication and Biomedical Applications of Heart-on-a-chip.

Heart diseases have become the main killer threatening human health, and various methods have been developed to study heart disease. Among them, heart-on-a-chip has emerged in recent years as a method for constructing disease (or normal) models in vitro and is considered as a promising tool to study heart diseases. Compared with other methods, the advantages of heart-on-a-chip include the high portability, high throughput, and the capability to mimic microenvironments in vivo. It has shown a great potential in disease mechanism study and drug screening. In this paper, we review the recent advances in heart-on-a-chip, including the fabrication methods (e.g., 3D bioprinting) and biomedical applications. By analyzing the structure of the existing heart-on-a-chip, we proposed that a highly integrated heart-on-a-chip includes four elements: Microfluidic chips, cells/microtissues, microactuators to construct the microenvironment, and microsensors for results readout. Finally, the current challenges and future directions of heart-on-a-chip are discussed.