Reanimate is a C++ library to simulate fluid and mass transport in microvascular tissue. The main goal of this project is to provide a simple and flexible framework to simulate blood flow, interstitial flow, and tracer or drug delivery in large microvascular networks. These networks are imported as weighted, undirected graphs which represent a network(s) of blood vessels generated either synthetically or by segmenting and skeletonising biomedical images.

An unsupervised deep learning tool for vascular network segmentation. VAN-GAN offers an accessible and efficient solution for the segmentation of vascular networks from 3D images without the need for human-annotated labels.

A Python package which utilises a 3-dimensional CNN to perform segmentation of 3D images using Keras. The 3D CNN is based on the U-Net architecture but extended for volumetric delineation with 3D spatial convolutions.

Hyperparameters can be fine-tuned using Talos by automating and performing quantitative evaluation during training.

A Python project to generate synthetic vascular networks which utilises Linenmayer Systems (L-Systems).

V-System uses stochastic rules and parameters in the L-System grammar to generate synthetic 3D blood vessels.

A trained 3D CNN to segment tumour region-of-interest (ROI) from raster-scan optoacoustic mesoscopy (RSOM) 3D image volumes. Segmentation allows delineation of tumour ROIs from surrounding tissue to provide an estimate of the tumour boundary and consequently tumour volume.

CNN model trained use generalised 3D CNN framework.