Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Symbrain: A large-scale dataset of MRI images for neonatal brain symmetry analysis

Arnaud Gucciardi, Safouane El Ghazouali, Francesca Venturini, Vida Groznik, Umberto Michelucci

TL;DR

This work addresses the scarcity of large-scale neonatal brain symmetry data by creating Symbrain, a dataset derived from the Developing Human Connectome Project. It generates 3150 coronal slices from 1050 neonatal/fetal MRI volumes and provides detailed midline annotations using straight and curved annotations to capture the brain's symmetry axis. The dataset, openly available on HuggingFace, supports training deep learning models for symmetry-based anomaly detection and links to clinical diagnosis and treatment planning in neonatal neurology. By enabling precise midline localization and curvature analysis, Symbrain facilitates reproducible research and development of automated symmetry assessment in neonatal brain MRI.

Abstract

This paper presents an annotated dataset of brain MRI images designed to advance the field of brain symmetry study. Magnetic resonance imaging (MRI) has gained interest in analyzing brain symmetry in neonatal infants, and challenges remain due to the vast size differences between fetal and adult brains. Classification methods for brain structural MRI use scales and visual cues to assess hemisphere symmetry, which can help diagnose neonatal patients by comparing hemispheres and anatomical regions of interest in the brain. Using the Developing Human Connectome Project dataset, this work presents a dataset comprising cerebral images extracted as slices across selected portions of interest for clinical evaluation . All the extracted images are annotated with the brain's midline. All the extracted images are annotated with the brain's midline. From the assumption that a decrease in symmetry is directly related to possible clinical pathologies, the dataset can contribute to a more precise diagnosis because it can be used to train deep learning model application in neonatal cerebral MRI anomaly detection from postnatal infant scans thanks to computer vision. Such models learn to identify and classify anomalies by identifying potential asymmetrical patterns in medical MRI images. Furthermore, this dataset can contribute to the research and development of methods using the relative symmetry of the two brain hemispheres for crucial diagnosis and treatment planning.

Symbrain: A large-scale dataset of MRI images for neonatal brain symmetry analysis

TL;DR

This work addresses the scarcity of large-scale neonatal brain symmetry data by creating Symbrain, a dataset derived from the Developing Human Connectome Project. It generates 3150 coronal slices from 1050 neonatal/fetal MRI volumes and provides detailed midline annotations using straight and curved annotations to capture the brain's symmetry axis. The dataset, openly available on HuggingFace, supports training deep learning models for symmetry-based anomaly detection and links to clinical diagnosis and treatment planning in neonatal neurology. By enabling precise midline localization and curvature analysis, Symbrain facilitates reproducible research and development of automated symmetry assessment in neonatal brain MRI.

Abstract

This paper presents an annotated dataset of brain MRI images designed to advance the field of brain symmetry study. Magnetic resonance imaging (MRI) has gained interest in analyzing brain symmetry in neonatal infants, and challenges remain due to the vast size differences between fetal and adult brains. Classification methods for brain structural MRI use scales and visual cues to assess hemisphere symmetry, which can help diagnose neonatal patients by comparing hemispheres and anatomical regions of interest in the brain. Using the Developing Human Connectome Project dataset, this work presents a dataset comprising cerebral images extracted as slices across selected portions of interest for clinical evaluation . All the extracted images are annotated with the brain's midline. All the extracted images are annotated with the brain's midline. From the assumption that a decrease in symmetry is directly related to possible clinical pathologies, the dataset can contribute to a more precise diagnosis because it can be used to train deep learning model application in neonatal cerebral MRI anomaly detection from postnatal infant scans thanks to computer vision. Such models learn to identify and classify anomalies by identifying potential asymmetrical patterns in medical MRI images. Furthermore, this dataset can contribute to the research and development of methods using the relative symmetry of the two brain hemispheres for crucial diagnosis and treatment planning.
Paper Structure (6 sections, 2 figures)

This paper contains 6 sections, 2 figures.

Table of Contents

  1. Introduction
  2. Dataset Description
  3. Materials and methods
  4. Slicing
  5. Annotations
  6. Dataset access

Figures (2)

  • Figure 1: Representative visualization of the slices on the T1w and T2 volumes, at the three different depths selected. D1: 76px 1, D2: 101px 2, D3: 126px.
  • Figure 2: Comparison of straight and curved midline manual annotation on T1w and T2w slice samples. Left: straight line annotation with two points. Center: curved annotation made of nine control points. Right: visual comparison of the two annotations. Even on a seemingly symmetric brain image, minor curvature changes are visible.