A multicentre longitudinal brain metastasis imaging dataset with lesion segmentations and clinical data

Abstract Brain metastases exhibit substantial variability in lesion burden, morphology and treatment response. Longitudinal imaging linked to lesion annotations and clinical histories can support quantitative studies of this heterogeneity. We describe a multicentre dataset from seven Spanish hospitals comprising 443 patients diagnosed between 2007 and 2022, with follow-up imaging for 216 patients. The collection contains 2842 magnetic resonance image, including 1092 three dimensional (3D) contrast-enhanced T1-weighted, 833 T2-weighted and 917 FLAIR (fluid-attenuated inversion recovery) images. Semiautomatic 3D-segmentation with expert review provides annotations for 1291 unique lesions represented by 2303 lesion observations across imaging time points. Separate labels identify contrast-enhancing and non-enhancing or necrotic tumour components, and lesion identifiers are maintained during follow-up. Accompanying records describe primary tumour characteristics, treatments, imaging dates and clinical outcomes, together with acquisition metadata and 107 morphological and radiomic features. The dataset supports research on lesion detection and segmentation, longitudinal response assessment, imaging biomarkers and mathematical models of brain metastasis growth and treatment response.

Authors

Institutions

Publication Details

Journal
Research Square
Published
2026-11-09
DOI
https://doi.org/10.21203/rs.3.rs-11637027/v1
Primary Topic
Brain Metastases and Treatment
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

A multicentre longitudinal brain metastasis imaging dataset with lesion segmentations and clinical data

Belén Luque, Ana Ortiz de Méndivil, María Vidal-Denis, Elisabet González-Del Portillo et al.
Research Square
Brain Metastases and Treatment
preprint

A multicentre longitudinal brain metastasis imaging dataset with lesion segmentations and clinical data

Belén Luque, Ana Ortiz de Méndivil, María Vidal-Denis, Elisabet González-Del Portillo, David Albillo, Natalia Carballo, Julián Pérez-Beteta, Ismael Fernández‐Hernández, Estanislao Arana, Manuel Llorente, José Villanueva-García, Beatriz Ocaña-Tienda, R Morcillo, Fátima Nagib-Raya, Beatriz Asenjo, Victor M. Pérez-Garcı́a, Luís A. Pérez-Romasanta, Zhao Hui Chen Zhou, David Molina-García, Ana Ramos, Silvia Bordel-Vozmediano, Miguel Perales-Patón, Yahir Y. Calderón-Silva
preprint en

Abstract

Abstract Brain metastases exhibit substantial variability in lesion burden, morphology and treatment response. Longitudinal imaging linked to lesion annotations and clinical histories can support quantitative studies of this heterogeneity. We describe a multicentre dataset from seven Spanish hospitals comprising 443 patients diagnosed between 2007 and 2022, with follow-up imaging for 216 patients. The collection contains 2842 magnetic resonance image, including 1092 three dimensional (3D) contrast-enhanced T1-weighted, 833 T2-weighted and 917 FLAIR (fluid-attenuated inversion recovery) images. Semiautomatic 3D-segmentation with expert review provides annotations for 1291 unique lesions represented by 2303 lesion observations across imaging time points. Separate labels identify contrast-enhancing and non-enhancing or necrotic tumour components, and lesion identifiers are maintained during follow-up. Accompanying records describe primary tumour characteristics, treatments, imaging dates and clinical outcomes, together with acquisition metadata and 107 morphological and radiomic features. The dataset supports research on lesion detection and segmentation, longitudinal response assessment, imaging biomarkers and mathematical models of brain metastasis growth and treatment response.

Research Square
Complejo Hospitalario de Salamanca (ES), Hospital Universitario Rey Juan Carlos (ES), Hospital Universitario 12 De Octubre (ES), Fundación Instituto Valenciano de Oncología (ES), Hospital Regional Universitario de Málaga (ES), Hospital General Universitario de Ciudad Real (ES), Hospital Universitario HM Sanchinarro (ES), MD Anderson Cancer Center Madrid (ES), University of Göttingen (DE), University of Castilla-La Mancha (ES)
Brain Metastases and Treatment
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon