Automatic quantification of the microvascular density on whole slide images, applied to paediatric brain tumours

TL;DR

This paper presents an automated, training-free algorithm to quantify microvascular density in whole slide images of paediatric brain tumours, correlating well with tumour grade and applicable to various tumor types.

Contribution

The authors developed a novel algorithm for automatic microvascular density measurement on whole slide images without training, handling large, heterogeneous datasets efficiently.

Findings

High-quality segmentation of vessel walls in heterogeneous slides

Strong correlation between microvascular density and tumour grade

Rapid computation time of less than an hour per slide

Abstract

Angiogenesis is a key phenomenon for tumour progression, diagnosis and treatment in brain tumours and more generally in oncology. Presently, its precise, direct quantitative assessment can only be done on whole tissue sections immunostained to reveal vascular endothelial cells. But this is a tremendous task for the pathologist and a challenge for the computer since digitised whole tissue sections, whole slide images (WSI), contain typically around ten gigapixels. We define and implement an algorithm that determines automatically, on a WSI at objective magnification $40\times$, the regions of tissue, the regions without blur and the regions of large puddles of red blood cells, and constructs the mask of blur-free, significant tissue on the WSI. Then it calibrates automatically the optical density ratios of the immunostaining of the vessel walls and of the counterstaining, performs a colour deconvolution inside the regions of blur-free tissue, and finds the vessel walls inside these regions by selecting, on the image resulting from the colour deconvolution, zones which satisfy a double-threshold criterion. A mask of vessel wall regions on the WSI is produced. The density of microvessels is finally computed as the fraction of the area of significant tissue which is occupied by vessel walls. We apply this algorithm to a set of 186 WSI of paediatric brain tumours from World Health Organisation grades I to IV. The segmentations are of very good quality although the set of slides is very heterogeneous. The computation time is of the order of a fraction of an hour for each WSI on a modest computer. The computed microvascular density is found to be robust and strongly correlates with the tumour grade. This method requires no training and can easily be applied to other tumour types and other stainings.