Skip to main content

Measuring leakage through the blood-brain barrier

Research team: Dr. Matt Albrecht, Mr. Corey Giles, Prof. John Mamo, Dr. Ryu Takechi, Dr. Virgine Lam
CIC specialist: Dr. Kevin Chai

The brain is unusual compared to other organs in that it has a very dense vascular network, but tightly restricts the passage of molecules from the blood into the brain tissues – referred to as the blood-brain barrier (BBB).  In many disease processes, from mild conditions through to traumatic brain injury, the barrier function lessens and molecules leak through.

A current research focus at the Curtin Health Innovation Research Institute (CHIRI) is the relationship between leakage across the BBB and cognitive decline.  Several teams are examining the effect of dietary and lifestyle interventions, environmental toxins and medications on the function of the BBB, and its relationship to ageing, dementia and other neurodegenerative diseases.

In the laboratory of Professor John Mamo and Associate Professor Ryusuke Takechi, Dr Matt Albrecht, Dr Virginie Lam and Mr Corey Giles detect leakage across the BBB by measuring the spread of a blood-based protein that shouldn’t normally exist in brain tissue.  Microscope images of brain slices are collected from mouse models that have had interventions that may impair, restore or maintain BBB function.  Fluorescence staining of the brain tissue allows visualisation of the blood protein, both within capillary structures and in areas of leakage.  Capillaries appear as distinct branch-like structures with well defined edges, while leakage appears as diffuse unformed fluorescence.

Manually quantifying the leakage in these images is extremely time consuming and as studies become bigger, microscopes become better, and data acquisition becomes faster, the number of images generated can keep a researcher busy annotating them for months.  It is painstaking, tedious work, and consistency between different researcher annotations is difficult to achieve due to normal human variation in attention and strategy.

The group teamed up with Dr Kevin Chai of the CIC to see if machine learning could be used to automate capillary image processing and measurement of BBB leakage.  During initial experimentation, they trained a convolutional neural net using a set of images that had already been manually annotated, presenting it with only the raw images and the leakage scores.  Unfortunately, the trained algorithm was only moderately successful in predicting leakage scores for other previously-annotated images.

The researchers then tried machine learning on a different set of images that had been annotated using a more labour-intensive method – a ‘mask’ is created for each image by manually identifying and blocking out the segments of capillaries they don’t want to measure, making it easier to measure the amount of diffuse leakage remaining that surround the capillaries.  When the neural net was trained using a data set containing manually-masked images it learned to take a raw image, automatically segment out the capillaries (effectively assimilating the masking technique), and then calculate an accurate leakage score.

Validating the improved algorithm against a new image set classified by Giles (who had manually masked and classified the training data) resulted in a correlation of 96 per cent against the manual measurements.  Testing it against new images that had been classified by Albrecht gave a correlation of 80 per cent, highlighting the difference between individual researcher manual annotations.

This application of machine learning can classify 1,000 capillary images in under two minutes, whereas an expert researcher would need approximately one month to complete the same task.  Additional stress testing and training of the model using different experimental image sets is expected to further improve its accuracy.

The power in this method is that through the selection of an appropriate training data set, the model can be applied to many different medical research applications where the discrimination between well-defined edges, whether on the vessel or cellular scale, and other more diffuse features is of interest.