HyKid: An Open MRI Dataset with Expert-Annotated Multi-Structure and Choroid Plexus in Pediatric Hydrocephalus

2025-09-23

AI Summary

Pediatric hydrocephalus imaging assessment is hindered by the absence of publicly available, high-quality pediatric MRI datasets with choroid plexus annotations. Method: We introduce the first open-source, 3D MRI benchmark dataset specifically for pediatric hydrocephalus, comprising 48 high-resolution (1-mm isotropic) scans and expert-refined multi-structure segmentation masks—including the first fine-grained choroid plexus annotations. To enhance low-resolution acquisitions, we employ slice-to-volume reconstruction; additionally, retrieval-augmented generation extracts structured clinical information from radiology reports. Contribution/Results: Quantitative analysis reveals a strong correlation between choroid plexus volume and total cerebrospinal fluid volume (*p* < 0.001), establishing it as a promising imaging biomarker—achieving an AUC of 0.87 in hydrocephalus prediction. This dataset serves as a foundational resource for algorithm development, pathophysiological investigation, and clinical translation in pediatric neuroimaging.

Technology Category

• Computer Vision: 3D Computer Vision
• Machine Learning: Neuro-Symbolic Learning
• Data Mining & Knowledge Management: Mining of Visual, Multimedia & Multimodal Data

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Security and Privacy: Data transparency and provenance
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Evaluation of hydrocephalus in children is challenging, and the related research is limited by a lack of publicly available, expert-annotated datasets, particularly those with segmentation of the choroid plexus. To address this, we present HyKid, an open-source dataset from 48 pediatric patients with hydrocephalus. 3D MRIs were provided with 1mm isotropic resolution, which was reconstructed from routine low-resolution images using a slice-to-volume algorithm. Manually corrected segmentations of brain tissues, including white matter, grey matter, lateral ventricle, external CSF, and the choroid plexus, were provided by an experienced neurologist. Additionally, structured data was extracted from clinical radiology reports using a Retrieval-Augmented Generation framework. The strong correlation between choroid plexus volume and total CSF volume provided a potential biomarker for hydrocephalus evaluation, achieving excellent performance in a predictive model (AUC = 0.87). The proposed HyKid dataset provided a high-quality benchmark for neuroimaging algorithms development, and it revealed the choroid plexus-related features in hydrocephalus assessments. Our datasets are publicly available at https://www.synapse.org/Synapse:syn68544889.

Problem

• Lack of expert-annotated MRI datasets for pediatric hydrocephalus evaluation
• Limited choroid plexus segmentation in publicly available hydrocephalus datasets
• Need for high-quality benchmarks for neuroimaging algorithm development

Innovation

• Slice-to-volume algorithm reconstructs high-resolution MRI
• Retrieval-Augmented Generation framework extracts clinical data
• Choroid plexus volume serves as potential biomarker