Ensemble of Deep Learning Cascades for Segmentation of Blood Vessels in Confocal Microscopy Images.

Detection, segmentation, and quantification of microvascular structures are the main steps towards studying microvascular remodeling. Combined with appropriate staining, confocal microscopy imaging enables exploration of the full 3D anatomical characteristics of microvascular systems. Segmentation of confocal microscopy images is a challenging task due to complexity of anatomical structures, staining and imaging issues, and lack of annotated training data. In this paper, we propose a deep learning system for robust segmentation of cranial vasculature of mice in confocal microscopy images. The proposed system is an ensemble of two deep-learning cascades consisting of two coarse-to-fine subnetworks with skip connections in between. One cascade aims to improve sensitivity, while the other aims to improve precision of the segmentation results. Our experiments on mice cranial vasculature showed promising results achieving segmentation accuracy of 92.02% and dice score of 81.45% despite being trained on very limited confocal microscopy data.

The role of Thomsen-Friedenreich antigen in adhesion of human breast and prostate cancer cells to the endothelium.

Interactions of metastatic cancer cells with vasculatory endothelium are critical during early stages of cancer metastasis. Understanding the molecular underpinnings of these interactions is essential for the development of new efficacious cancer therapies. Here we demonstrate that cancer-associated carbohydrate T antigen plays a leading role in docking breast and prostate cancer cells onto endothelium by specifically interacting with endothelium-expressed beta-galactoside-binding protein, galectin-3. Importantly, T antigen-bearing glycoproteins are also capable of mobilizing galectin-3 to the surface of endothelial cells, thus priming them for harboring metastatic cancer cells. The T antigen-mediated, tumor-endothelial cell interactions could be efficiently disrupted using synthetic compounds either mimicking or masking this carbohydrate structure. High efficiency of T antigen-mimicking and T antigen-masking inhibitors of tumor cell adhesion warrants their further development into antiadhesive cancer therapeutics.

MULTISCALE TENSOR ANISOTROPIC FILTERING OF FLUORESCENCE MICROSCOPY FOR DENOISING MICROVASCULATURE.

Fluorescence microscopy images are contaminated by noise and improving image quality without blurring vascular structures by filtering is an important step in automatic image analysis. The application of interest here is to automatically extract the structural components of the microvascular system with accuracy from images acquired by fluorescence microscopy. A robust denoising process is necessary in order to extract accurate vascular morphology information. For this purpose, we propose a multiscale tensor with anisotropic diffusion model which progressively and adaptively updates the amount of smoothing while preserving vessel boundaries accurately. Based on a coherency enhancing flow with planar confidence measure and fused 3D structure information, our method integrates multiple scales for microvasculature preservation and noise removal membrane structures. Experimental results on simulated synthetic images and epifluorescence images show the advantage of our improvement over other related diffusion filters. We further show that the proposed multiscale integration approach improves denoising accuracy of different tensor diffusion methods to obtain better microvasculature segmentation.