25.07.2024

A research team has received approximately one million US dollars from the US National Institutes of Health (NIH) to develop an AI-based method for three-dimensional measurement of the choroid plexus in human brain scans. This project aims to enhance our understanding of these structures, which play a crucial role in brain and spinal cord function.

The cerebrospinal fluid (CSF) is a vital watery liquid circulating in the brain and spinal cord, providing nutrients, removing waste, and cushioning the brain. The primary sources of CSF are the choroid plexuses, highly branched structures within the brain’s cavities. Each person has four choroid plexuses, which, despite their small size, are essential for neurological health and are implicated in diseases like Alzheimer’s.

Image: AI-based measurement tool for images

The research team at DZNE has been awarded around one million US dollars for the development of an AI-based method to measure the "choroid plexus" three-dimensionally in human brain scans.

Products and exhibitors related to this topic

Exhibitors and products related to this topic can be found in the database of MEDICA:

AI-supported measurement method

Prof. Martin Reuter, an expert in AI in image analysis and research group leader at DZNE, is leading this project. The goal is to develop an AI-supported method to automatically identify and measure the choroid plexuses in brain scans, overcoming the challenges of manual segmentation, which is labor-intensive and error-prone. “Automated and precise measurements of these structures will help to better understand disease processes and normal brain changes over the course of life,” says Reuter.

Digital "dissection" of the brain

The project involves analyzing three-dimensional brain magnetic resonance images (MRI) from the NIH’s Human Connectome Project and other sources, including data from around 700 participants. Existing computer algorithms for brain segmentation are inadequate for the choroid plexuses. Thus, the team aims to develop a specialized, fully automatic tool to efficiently and reliably evaluate large brain MRI datasets, essential for studies with many participants, such as drug trials or aging studies like the DZNE’s Rhineland Study.

The DZNE will collaborate with US institutions, particularly the Beth Israel Deaconess Medical Center in Boston, a Harvard Medical School affiliate. The five-year project will result in software based on advanced AI, trained with example data to recognize the choroid plexuses in MRI scans. The development and validation of these algorithms are labor-intensive, highlighting the project’s comprehensive nature.

Future applications and open source software

Prof. Reuter hopes the resulting digital tool will be widely used in research. “We are going to design our tool so that it works with data of different resolutions and from different types of brain scanners. We also plan to make the software freely available within the open source FastSurfer project for brain MRI analysis, developed at DZNE,” he explains. This accessibility will enable broader use and further advancements in understanding neurological conditions.

MEDICA-tradefair.com; Source: DZNE

More about the DZNE at: www.dzne.de/en