The Batch-Resourcing Angiogenesis Tool (BRAT) to enable high-content microscopy screening of microvascular networks.
Krek, H.; Murphy, A. R.; McKinnon, R.; Franco, R. A.; Allenby, M. C.
Show abstract
Vessel forming assays are a valuable in vitro technology to evaluate the vasculogenic and angiogenic potential of different cell types, matrix proteins, and soluble factors. Recent advances in high-content microscopy allow for vascular morphogenesis assays to be captured in real-time and in high-throughput screening purposes. Unfortunately, existing microvascular network quantification algorithms are either inaccurate, not user-friendly, or manually analyse one image at a time, unfavourable to high-content screening applications. This manuscript introduces BRAT, the Batch-Resourcing Angiogenesis Tool, a computer algorithm with an open-source graphic user interface to efficiently segment, skeletonize, and analyse large batches of vascular network images with high accuracy. Benchmarked across diverse clinical and cultured microvascular network images, BRAT is the most sensitive vascular network image analysis tool (94.5%) and exhibits leading accuracy (93.3%). BRATs multi-threaded processing automatically analysed 886 microscopy images at a speed of 0.17 seconds/image (2:29 minutes) on a performance computer or 2.31 seconds/image (34:04) on a typical laptop. This is 10-to-100 fold more time-efficient than existing tools, which require 12 to 16 seconds of direct user input per image. BRAT is broadly useful to analyse vessel networks of different endothelial cell types cultured on 2D substrates and within 3D biomaterials. BRAT represents a powerful approach for the accurate and high-content screening of vessel forming assays for disease models, regenerative medicines, and therapeutic testing.
Matching journals
The top 11 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- ConfluentFUCCI for fully-automated analysis of cell-cycle progression in a highly dense collective of migrating cells 95%
- FalseColor-Python: a rapid intensity-leveling and digital-staining package for fluorescence-based slide-free digital pathology 94%
- Caveolae and scaffold detection from single molecule localization microscopy data using deep learning 94%
Similar papers in this journal
- Reconstructing microvascular network skeletons from 3D images: what is the ground truth? 94%
- The mathematics of erythema: Development of machine learning models for artificial intelligence assisted measurement and severity scoring of radiation induced dermatitis 93%
- MultiHeadGAN: A Deep Learning Method for Low Contrast Retinal Pigment Epithelium Cells Segmentation in Fluorescent Flatmount Microscopy Images 92%
Similar papers in this journal
- Deep-learning-assisted SICM for enhanced real-time imaging of nanoscale biological dynamics 93%
- Precision 1070 nm Ultrafast Laser-induced Photothrombosis (PLP) of Depth-targeted Vessels in vivo 91%
- A high-resolution microscopy system for biological studies of cold-adapted species under physiological conditions 90%
Similar papers in this journal
- AngioNet: A Convolutional Neural Network for Vessel Segmentation in X-ray Angiography 94%
- Generating synthetic data in digital pathology through diffusion models: a multifaceted approach to evaluation 94%
- Investigating Clot-flow Interactions by Integrating Intravital Imaging with In Silico Modeling for Analysis of Flow, Transport, and Hemodynamic Forces. 93%
Similar papers in this journal
- CellSNAP: A fast, accurate algorithm for 3D cell segmentation in quantitative phase imaging 93%
- Segmentation of the Urothelium in Optical Coherence Tomography Images with Dynamic Contrast 92%
- Small Training Dataset Convolutional Neural Networks for Application Specific Super-Resolution Microscopy 91%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.