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

This paper presents an annotated dataset of brain MRI images designed to advance the field of <PRE_TAG><PRE_TAG><PRE_TAG>brain symmetry</POST_TAG></POST_TAG></POST_TAG> study. Magnetic resonance imaging (MRI) has gained interest in analyzing <PRE_TAG><PRE_TAG><PRE_TAG>brain symmetry</POST_TAG></POST_TAG></POST_TAG> in <PRE_TAG><PRE_TAG><PRE_TAG>neonatal infants</POST_TAG></POST_TAG></POST_TAG>, 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 <PRE_TAG><PRE_TAG>hemisphere symmetry</POST_TAG></POST_TAG>, which can help diagnose neonatal patients by comparing hemispheres and anatomical regions of interest in the brain. Using the <PRE_TAG><PRE_TAG>Developing Human Connectome Project dataset</POST_TAG></POST_TAG>, this work presents a dataset comprising <PRE_TAG><PRE_TAG><PRE_TAG>cerebral images</POST_TAG></POST_TAG></POST_TAG> extracted as slices across selected portions of interest for clinical evaluation . All the extracted images are annotated with the brain's <PRE_TAG><PRE_TAG>midline</POST_TAG></POST_TAG>. All the extracted images are annotated with the brain's <PRE_TAG><PRE_TAG>midline</POST_TAG></POST_TAG>. 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 <PRE_TAG><PRE_TAG>deep learning model</POST_TAG></POST_TAG> application in neonatal cerebral MRI <PRE_TAG><PRE_TAG>anomaly detection</POST_TAG></POST_TAG> from <PRE_TAG><PRE_TAG>postnatal infant scans</POST_TAG></POST_TAG> thanks to <PRE_TAG><PRE_TAG>computer vision</POST_TAG></POST_TAG>. Such models learn to identify and classify anomalies by identifying potential <PRE_TAG><PRE_TAG>asymmetrical patterns</POST_TAG></POST_TAG> in <PRE_TAG><PRE_TAG>medical MRI images</POST_TAG></POST_TAG>. Furthermore, this dataset can contribute to the <PRE_TAG><PRE_TAG>research and development</POST_TAG></POST_TAG> of methods using the <PRE_TAG><PRE_TAG>relative symmetry</POST_TAG></POST_TAG> of the two brain hemispheres for <PRE_TAG><PRE_TAG>crucial diagnosis</POST_TAG></POST_TAG> and <PRE_TAG><PRE_TAG>treatment planning</POST_TAG></POST_TAG>.