Deep Learning for Virtual Histological Staining of Bright-Field Microscopic Images of Unlabeled Carotid Artery Tissue

Purpose Histological analysis of artery tissue samples is a widely used method for diagnosis and quantification of cardiovascular diseases. However, the variable and labor-intensive tissue staining procedures hinder efficient and informative histological image analysis. Procedures In this study, we developed a deep learning-based method to transfer bright-field microscopic images of unlabeled tissue sections into equivalent bright-field images of histologically stained versions of the same samples. We trained a convolutional neural network to build maps between the unstained images and histologically stained images using a conditional generative adversarial network model. Results The results of a blind evaluation by board-certified pathologists illustrate that the virtual staining and standard histological staining images of rat carotid artery tissue sections and those involving different types of stains showed no major differences. Quantification of virtual and histological H&E staining in carotid artery tissue sections showed that the relative errors of intima thickness, intima area, and media area were lower than 1.6 %, 5.6 %, and 12.7 %, respectively. The training time of deep learning network was 12.857 h with 1800 training patches and 200 epoches. Conclusions This virtual staining method significantly mitigates the typically laborious and time-consuming histological staining procedures and could be augmented with other label-free microscopic imaging modalities.

Decoding the transcriptome of atherosclerotic plaque at single-cell resolution

Atherogenesis involves an interplay of inflammation, tissue remodeling and cellular transdifferentiation (CTD), making it especially difficult to precisely delineate its pathophysiology. Here we examine the single-cell transcriptome of entire atherosclerotic core (AC) plaques and patient-matched proximal adjacent (PA) portions of carotid artery tissue from patients undergoing carotid endarterectomy. We use a novel tissue dissociation strategy, single-cell RNA sequencing, and systems-biology approaches to analyze the transcriptional profiles of six main cell populations and identify key gene drivers of pathogenic biological processes in vascular smooth muscle cells (VSMCs) and endothelial cells (ECs). Our results reveal an anatomic continuum whereby PA cells promote and respond to inflammatory processes and eventually transition through CTD into matrix-secreting cells in the AC. Inflammatory signaling in PA ECs is driven by IL6, while TNFa signaling defines inflammation in both PA ECs and VSMCs. Furthermore, we identify POSTN, SPP1 and IBSP in AC VSMCs, and ITLN1, SCX and S100A4 in AC ECs as key drivers of CTD in the atherosclerotic core. These results establish an anatomic framework for atherogenesis and suggest a site-specific strategy for disruption of disease progression.

Vascular impact of quercetin administration in association with moderate exercise training in experimental type 1 diabetes

Hyperglycemia and oxidative stress have a major role in the pathogenesis of diabetic vascular complications. In this study, we investigated the efficacy of combining quercetin treatment with moderate exercise training in reversing diabetes-induced oxidative stress and ultrasound modifications in rat carotid arteries. The diabetic Wistar rats were divided into sedentary groups and trained groups. The trained animals went through a regular moderate exercise by swimming (5 weeks). Some non-diabetic and diabetic rats were daily treated with quercetin (30 mg/kg, for 5 weeks). At the end of the study, the imaging evaluation required to assess the effects of diabetes on carotid arteries was performed by micro-ultrasound (MU). The diabetic rats presented atherosclerotic plaques, with an increase in the echogenicity of the carotid artery wall, carotid intima-media thickness (CIMT), and carotid wall thickness, while the diabetic trained rats treated with quercetin presented normal values of these parameters. Malondialde-hyde (MDA) levels, superoxide dismutase (SOD) antioxidant enzyme activity, reduced glutathione (GSH) levels and the reduced (GSH) to oxidized (GSSG) glutathione ratio were determined in the carotid artery tissue. Diabetes caused elevated MDA levels and a decrease in SOD activity, GSH levels and GSH/GSSG ratio in the carotid artery tissue. Treating diabetic rats with quercetin combined with moderate exercise training reversed all these oxidative stress parameters. Our results show that this combination, quercetin and moderate exercise training, can be a good treatment strategy for the vascular complications of diabetes by attenuating hyperglycemia-mediated oxidative stress.

Repair of interrupted aortic arch using autologous pulmonary artery tissue

There are several options for the repair of interrupted aortic arch. Direct anastomosis may cause several problems including anastomotic site stenosis, left main bronchus compression, and acute-angled aortic arch. Interposition of a prosthetic graft has no growth potential. We present a case of 34-month-old child with interrupted aortic arch, which was repaired using a pulmonary autograft tube.