The brain of a mouse - taken with fluorescence microscopy using tissue clearing...
The brain of a mouse - taken with fluorescence microscopy using "tissue clearing" - a technique that for the first time made the large and small brain vessels visible simultaneously.
Source: Ertürk Lab / Institute for Stroke and Dementia Research

Smart algorithm analyses whole brain vasculature

Diseases of the brain are often associated with typical vascular changes. Now, scientists at LMU University Hospital Munich, Helmholtz Research Centre for Environmental Health and the Technical University of Munich (TUM) have come up with a technique for visualising the structures of all the brain's blood vessels – right down to the finest capillaries – including any pathological changes. So far, they have used the technique, which is based on a combination of biochemical methods and artificial intelligence, to capture the whole brain vasculature of a mouse.

Changes in the blood vessels are a hallmark of numerous brain disorders – from traumatic brain injury to stroke. Even diseases such as Alzheimer's show changes in the fine capillaries. In short, analysing the blood vessels is key to understanding both normal and pathological brain function. "Now we have come much closer to achieving that goal", explains Ali Ertürk, Director of the Institute for Tissue Engineering and Regenerative Medicine at Munich's Helmholtz Centre and Principal Investigator at the Institute for Stroke and Dementia Research at the LMU University Hospital Munich.

As a first step, Ertürk's team succeeded in visualising the vascular system of mouse brains with high-resolution fluorescent microscopy without having to cut up the specimens into small sections. In order to do this, they refined the technique of tissue cleaning, in which biological tissues are treated with special dyes to render them transparent for fluorescent microscopy. "Previously, this technique could only be used to scan either the large vessels of the brain or the small ones", says Mihail Ivilinov Todorov, a doctoral student studying under Ertürk.

Therefore the Munich-based scientists took the new approach of combining two dyes. "That gave us some great images of the brain vasculature including the capillaries", adds the biologist.

Vascular network captured using AI

Applying artificial intelligence, researchers from the team led by Björn Menze, Professor for Machine Learning in Biomedical Imaging at the Technical University of Munich, used these images to reconstruct the entire vascular network of the brain right down to its finest details. Such a reconstruction yields more than just images – it also allows a quantitative analysis of the vascular structures. “For example, we can statistically record the diameters of the various blood vessels or their bifurcations for different areas of the brain”, says Johannes Paetzold, doctoral student in Menze’s group.

"Over the past few years, we have developed a deep learning algorithm that specialises in detecting blood vessels in medical images", Menze explains. "This was the first time we applied it to a whole brain." The algorithm was able to reliably distinguish between blood vessels and other tissue even though some areas in the original fluorescence images were not well-illuminated and some details were distorted due to light reflections or other errors.
Understanding and diagnosing brain disorders

Mihail Ivilinov Todorov plans to use the statistical data in order to investigate vascular changes caused by stroke, while Björn Menze is looking to study the global structures of the vascular system in order to understand the role of anatomical differences in brain disorders, for example.

The method could also be used in everyday clinical practice: "With our system, we are likely to be able to analyse the small tissue specimens from human tumours with greater accuracy", Ertürk asserts. Cancerous tissue is permeated by blood vessels, and analysing their structure helps in staging a tumour. "This may have an optimising effect on treatment", Ertürk adds. The biologist also plans to use the new method to realise his vision for the future: the production of human organs on a 3D printer. For that to happen, a knowledge of the organ's precise vascular structure – among many other things – will be vital.

Subscribe to our newsletter

Related articles

AI, holographic microscopy beat scientists at analyzing immunotherapy​

AI, holographic microscopy beat scientists at analyzing immunotherapy​

AI is helping researchers decipher images from a new holographic microscopy technique needed to investigate a key process in cancer immunotherapy “live” as it takes place.

Biomedical research: deep learning outperforms machine learning

Biomedical research: deep learning outperforms machine learning

Deep-learning methods have the potential to offer substantially better results, generating superior representations for characterizing the human brain.

What happens when your brain can't tell which way is up or down?

What happens when your brain can't tell which way is up or down?

Using virtual reality, researchers found that people differ in how much they are influenced by their visual environment.

A wireless chip shines light on the brain

A wireless chip shines light on the brain

Researchers have developed a chip that is powered wirelessly and can be surgically implanted to read neural signals and stimulate the brain with both light and electrical current.

BCI training reduces phantom limb pain

BCI training reduces phantom limb pain

Scientists used brain-computer-interface to train the brains of patients to reduce phantom-hand pain.

Your new lab partner: the robot scientist

Your new lab partner: the robot scientist

Researchers have built an intelligent mobile robot scientist that can work 24-7, carrying out experiments by itself.

VR study: our visual world of color is incorrect

VR study: our visual world of color is incorrect

A study finds that people are aware of surprisingly limited color in their peripheral vision; much of our sense of a colorful visual world is likely constructed by our brain.

VR supports the treatment of children with brain injury

VR supports the treatment of children with brain injury

Research confirms the efficiency of using computer-based programmes and virtual reality for improving children's attention and social skills.

Is virtual reality not suited to visual memory?

Is virtual reality not suited to visual memory?

Researchers have found that virtual reality may interfere with visual memory.

Popular articles