Overview

Schema Version

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

Name

Lifestyle Intervention (LION) abdominal chemical shift–encoded MRI dataset

Link

https://pubs.rsna.org/doi/10.1148/ryai.230471

Indexing

Keywords: Obesity, Chemical shift–encoded MRI, Abdominal fat volume, Proton density fat fraction, nnU-Net, Water–fat MRI, Visceral adipose tissue, Subcutaneous adipose tissue, Liver fat, Muscle fat

Content: GI, MK, MR

RadLex: RID32693, RID11374, RID33245, RID11305, RID16574, RID33171, RID28832, RID50366, RID39492, RID11595

SNOMED: 414916001

Author(s)

Arun Somasundaram

Mingming Wu

Anna Reik

Selina Rupp

Jessie Han

Stella Naebauer

Daniela Junker

Lisa Patzelt

Meike Wiechert

Yu Zhao

Daniel Rueckert

Hans Hauner

Christina Holzapfel

Dimitrios C. Karampinos

Organization(s)

Department of Diagnostic and Interventional Radiology, Klinikum rechts der Isar, Technical University of Munich

Institute of Nutritional Medicine, School of Medicine, Technical University of Munich

TUM School of Computation, Information, and Technology

TUM School of Medicine and Health

Else Kröner Fresenius Center for Nutritional Medicine, School of Medicine, Technical University of Munich

Department of Computing, Imperial College London, UK

Department of Nutritional, Food and Consumer Sciences, Fulda University of Applied Sciences, Germany

Munich Institute of Biomedical Engineering and Munich Data Science Institute, Technical University of Munich

Contact

Corresponding author: Mingming Wu; email: ed.mut@uw.gnimgnim

Funding

German Federal Ministry of Education and Research (grant no. 01EA1709, IMaGENE 16DKWN075); German Research Foundation (project no. 450799851; 455422993/FOR 5298‑iMAGO‑P1); additional support to D.R. from BMBF, ERC, and Alexander von Humboldt Foundation.

Ethical review

Study protocol approved by the Ethical Committee of the Technical University of Munich (project no. 69/19S). Written informed consent obtained.

Comments

MRI body composition dataset from participants in the LION weight loss intervention used to develop and evaluate automated multiorgan segmentation (nnU‑Net) and quantify organ volumes and PDFF before and after an 8‑week low‑calorie diet.

Date

Published: 2024-05-29

References

[1] Somasundaram A, Wu M, Reik A, et al.. "Evaluating Sex-specific Differences in Abdominal Fat Volume and Proton Density Fat Fraction at MRI Using Automated nnU‑Net–based Segmentation". Radiology: Artificial Intelligence. 2024-07-01. doi:10.1148/ryai.230471. PMID: 38809148. PMCID: PMC11294970.

[2] . "Randomized Controlled Lifestyle Intervention (LION) Study; ClinicalTrials.gov". . . Available from: https://clinicaltrials.gov/ct2/show/NCT04023942

Dataset

Motivation

Automate multiorgan segmentation on quantitative water–fat MRI to quantify organ volumes and PDFF and evaluate sex-specific differences before and after caloric restriction in people with obesity.

Sampling

Participants with obesity (BMI 30–39.9 kg/m2) from the LION study; MRI at baseline (n=127) and after an 8‑week formula-based low-calorie diet (follow-up n=81).

Partitioning scheme

Ground truth labels available for 103 MRI datasets from 67 participants; 83 datasets used for training/validation (4:1 split) and 20 for testing; participant-level separation across splits.

Missing information

Public download link, image file formats, and detailed acquisition parameters are provided only in supplemental materials (Table S1).

Relationships between instances

Multiple time points per participant (baseline and post-intervention), with strict grouping of a participant’s scans into either training or test to avoid leakage.

External data

Not publicly available; Data generated or analyzed during the study are available from the corresponding author by request.

Confidentiality

Human subject MRI; institutional ethics approval and informed consent obtained.

Sensitive data

Contains human medical images and derived organ segmentations/PDFF measures.