Abstract
The development and validation of deep learning methods to reconstruct magnetic resonance (MR) images from undersampled acquisitions (i.e., fast MR) rely on access to raw k-space data. However, public resources remain limited. This paper presents Calgary-Campinas 2.0 (), an extension of a previously published dataset, containing high-resolution 3D multi-coil brain MR k-space data from 256 acquisitions across 144 subjects. Those scans were acquired using 12-channel and 32-channel coil configurations. In addition to the data expansion, the new release provides longitudinal metadata for repeated scans, including same-day, short-term, and longer-term scan pairs. This structure enables evaluation of reconstruction beyond single-scan quality, including generalization across coil configurations, scan-rescan repeatability, and prior-informed longitudinal reconstruction, in which previous scans may guide the reconstruction of follow-up acquisitions. The dataset captures a longitudinal acquisition setting, with data collected over multiple years across scanner software and hardware updates. provides a benchmark resource for developing and evaluating MR image reconstruction methods under longitudinal, varying but controlled acquisition conditions. MR image reconstruction raw k-space undersampled k-space accelerated MR multi-coil MR longitudinal MR
Links to Paper and Supplementary Materials
Main Paper (Open Access Version): https://papers.miccai.org/miccai-2026-sat/paper/RIME_020.pdf
SharedIt Link: Not yet available
SpringerLink (DOI): Not yet available
Supplementary Material: Not Submitted
Link to Open Review
Open Review Page: https://openreview.net/forum?id=TJrShYtHnx
BibTex
@InProceedings{SchSus_3D_MICCAISAT2026,
author = { Schmid, Susanne AND Dubljevic, Natalia AND Shamaei, Amirmohammad AND Bento, Mariana AND Rittner, Letícia AND Frayne, Richard AND Souza, Roberto},
title = { { 3D Multi-Coil Brain MR k-Space Dataset for Deep Learning-Based Undersampled Reconstruction } },
booktitle = {Medical Image Computing and Computer Assisted Intervention -- MICCAI 2026 Workshops and Challenges},
year = {2026},
publisher = {Springer Nature Switzerland},
volume = {LNCS 17277},
month = {pending},
page = {pending}
}