Overview

Schema Version

https://atlas.rsna.org/schemas/2025-11/dataset.json

Name

Neuroblastoma T2/T2*-weighted MRI radiomics reproducibility cohort (PRIMAGE)

Link

https://doi.org/10.1148/ryai.230208

Indexing

Keywords: radiomics, neuroblastoma, pediatric, T2-weighted MRI, T2*-weighted MRI, normalization, resampling, segmentation, mask erosion, mask dilation, reproducibility, repeatability

Content: MR, OI, PD

RadLex: RID35976, RID39085, RID4454, RID50307, RID10796

SNOMED: 432328008, 87364003

Author(s)

Diana Veiga-Canuto

Matías Fernández-Patón

Leonor Cerdà Alberich

Ana Jiménez Pastor

Armando Gomis Maya

Jose Miguel Carot Sierra

Cinta Sangüesa Nebot

Blanca Martínez de las Heras

Ulrike Pötschger

Sabine Taschner-Mandl

Emanuele Neri

Adela Cañete

Ruth Ladenstein

Barbara Hero

Ángel Alberich-Bayarri

Luis Martí-Bonmatí

Organization(s)

Instituto de Investigación Sanitaria La Fe (Grupo de Investigación Biomédica en Imagen)

Hospital Universitari i Politècnic La Fe, Valencia, Spain

QUIBIM SL, Valencia, Spain

Universitat Politècnica de València, Spain

St. Anna Children’s Cancer Research Institute, Vienna, Austria

University of Pisa, Italy

University Children’s Hospital of Cologne, University of Cologne, Germany

Contact

Corresponding author: Diana Veiga-Canuto, email: moc.liamg@cagievanaid

Funding

European Union Horizon 2020 research and innovation action PRIMAGE project (topic SC1-DTH-07-2018), grant agreement no. 826494.

Ethical review

Approved by Ethics Committee for Investigation with Medicinal Products of the University and Polytechnic La Fe Hospital (code 2018/0228); informed consent waived due to observational, retrospective design.

Date

Published: 2024-06-12

References

[1] Veiga-Canuto D, Fernández-Patón M, Cerdà Alberich L, Jiménez Pastor A, Gomis Maya A, Carot Sierra JM, Sangüesa Nebot C, Martínez de las Heras B, Pötschger U, Taschner-Mandl S, Neri E, Cañete A, Ladenstein R, Hero B, Alberich-Bayarri Á, Martí-Bonmatí L. "Reproducibility Analysis of Radiomic Features on T2-weighted MR Images after Processing and Segmentation Alterations in Neuroblastoma Tumors". Radiology: Artificial Intelligence. 2024;6(4):e230208. 2024-06-12. doi:10.1148/ryai.230208. PMID: 38864742. PMCID: PMC11294951.

Dataset

Motivation

Evaluate reproducibility and stability of radiomics features from T2/T2*-weighted MR images of neuroblastic tumors under different preprocessing and segmentation mask alterations.

Sampling

Retrospective international multicenter cohort from 2002–2023 within PRIMAGE; inclusion of T2-weighted spin-echo, T2-weighted fat-suppressed, T2-weighted STIR, and T2*-weighted gradient-echo fat-saturation images meeting inclusion criteria.

Relationships between instances

Some patients contributed two MR sequences at different time points (diagnosis and/or after initial chemotherapy). 92 patients had one image; 327 patients had two images. Sequences performed separately and independently.

Noise

Original MR images heterogeneous across institutions and scanners; denoising filters (ADF, bilateral, curvature flow) were evaluated.

Sensitive data

Pediatric oncology imaging data.