Urgent.News

What's breaking now, across thousands of outlets.

Science

A large, comprehensive labeled MRI dataset of the human lateral ventricle choroid plexus

The choroid plexus (ChP) is a highly vascularized structure located in the brain ventricles that plays important roles in multiple central nervous system functions. ChP enlargement has been implicated in many neuropsychiatric conditions such as multiple sclerosis, depression, schizophrenia, and Alzheimer's disease. However, limitation in the accuracy of the current segmentation tools highlight…

The choroid plexus (ChP) is a highly vascularized structure found in the brain's ventricles, playing crucial roles in various central nervous system functions. Enlargement of the ChP has been linked to numerous neuropsychiatric conditions, including multiple sclerosis, depression, schizophrenia, and Alzheimer's disease. Current segmentation tools, however, lack the necessary accuracy for reliable quantification of ChP volume in both healthy and clinical human populations.

A significant challenge lies in the ChP's shape and size variations among individuals. Currently, there are no extensive ChP datasets available for comprehensive training of segmentation models. To address this gap, researchers have introduced DataPlex, a collection comprising 700 structural MRI brain images. In these images, the lateral ventricle ChP has been meticulously labeled and verified by expert human raters to ensure accuracy.

DataPlex stands out as a well-balanced and representative dataset, encompassing a wide range of scanning parameters, demographics, and clinical profiles. Each labeled image within the dataset includes subject-level information, facilitating further analysis. Importantly, DataPlex will be made open source, enabling the development of reliable segmentation tools for studying the human lateral ventricle ChP.

Written by urgent.news from bioRxiv's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at biorxiv.org →

More in Science

More from Sunday 11 October →